Modification of the Statistics Program Courses and Study Plans Prepared by The Accreditation Committee of the Statistics Program Dr. Ayman Baklizi, Program Director and Chair of the Accreditation Committee Dr. Adil Eltayeb (Member) Dr. Ameen Alawneh (Member) June 2010 1 Table of Contents 1. Introduction………………………………………………………………….3 2. The Mission, Program Objectives and Learning Outcomes…………………5 3. Other General Program related Issues……………………………………….8 4. The Modified Study Plan for the Major ……………………………………10 5. Brief Course Descriptions..............................................................................15 6. The Minor in Statistics………………………..…………………………….25 7. The Course Math 251“Mathematics for Statistics”………………………....28 8. Course Syllabi.................................................................................................31 2 Introduction 3 Introduction The Department of Mathematics, Statistics, and Physics at QU is currently engaged in an intensive preparation for the specialized accreditation of its undergraduate statistics program. As a part of the accreditation process, a team of assessors from the Royal Statistical Society (RSS) conducted a comprehensive evaluation visit to the department from 2 to 6 March 2008 to consider its application for the accreditation. The visiting team toured the department and the university, met with the program staff and held separate open meeting for a group of undergraduate students. On the basis of their observations and after analyzing relevant documents provided by the department, the team prepared and submitted an assessment report. The assessment report gives a rigorous academic review of the program in the areas of curriculum, management, support facilities and student welfare. The RSS report, also, raised some critical issues regarding the program design and structure, and included several recommendations and suggestions for enhancement. The present document is developed in response to the visiting team report. It focuses on the issues addressed in their assessment report and on the corresponding recommended actions concerning the curriculum. The modifications include developing new courses, modifying some existing courses and the necessary changes in prerequisites. Included below are the study plans for the major in Statistics-Minor in Business or Minor in computer science and the study plan for the Minor in Statistics. The course short syllabi for the courses are also included. 4 The Program mission, objectives and learning outcomes 5 The Mission The mission of the Statistics Program at Qatar University is to provide quality education with student-centered learning environment to produce high level graduates. The program aims at blending theory with practice by involving the students with interactive learning processes including research projects with real situations covering data collection and description to data analysis using the various modern day technologies and communicating the results precisely and effectively. The program allows the graduates to think as problem solvers with innovation and creativity and they will be equipped with the skills and knowledge to potentially provide consulting services to the various academic and professional sectors in the Qatari society. Program Objectives 1- Gain knowledge in the principles of statistics and its application to the other related fields of applications. 2- Build Strong theoretical background for the statistical techniques used. 3- Have a good understanding of the statistical principles and methods necessary to collect data including experimental design and statistical surveys. 4- Have a good training in statistical computing necessary to conduct different kinds of data analysis. 5- Gain the ability to provide sound "statistical consultation" to users of statistics in the different disciplines. 6- Acquire the ability to communicate effectively orally and in writing to undertake statistical tasks. 7- Promote critical learning skills and enabling students to be lifelong learners Student Learning Outcomes Students will be able to 1. Collect and give advice on how to collect data that conform with the statistical principles of data collection. 2. Design or give advise on to design surveys and experiments to obtain high quality data. 3. Describe various types of data numerically and graphically. 4. Analyze the various types of data that arise in the various types of scientific investigations. 5. Use effectively the statistical packages to conduct the various types of statistical tasks. 6. Write and present professional statistical reports and communicate effectively with the various users of statistics. 7. Demonstrate the theoretical basis of the statistical methods used in a given situation 6 Matrix of Compulsory Courses Mapped to Program Learning Outcomes 211 221 101 231 332 361 371 499 Student Learning Outcomes 312 322 102 333 481 1. Collect and give advice on how to collect data that conform with the statistical principles of data collection 2. Design or give advise on to design surveys and experiments to obtain high quality data * 3. Describe various types of data numerically and graphically * * * * * * * * * * * * 4. Analyze the various types of data that arise in the various types of scientific investigations 5. Use effectively the statistical packages to conduct the various types of statistical tasks. 6. Write and present professional statistical reports and communicate effectively with the various users of statistics 7. Demonstrate the theoretical basis of the statistical methods used in a given situation * * * * * * * * * * 7 Other General Program Related Issues 8 During the last months, considerable attention was paid to the marketing of the Statistics Program. Several steps were undertaken to communicate with statistics users outside the university. As for prospective students, presently in schools or in the foundation program, an action plan was set that includes participation in and organizing open days. This is to introduce them to the statistics program and the possible opportunities for graduates in statistics. Work on the Statistics Program is currently going on to enhance and improve the content and presentation of the relevant information for the prospective students. Qatar Statistical Authority (QSA) is an official governmental body that is responsible of many tasks including censuses and surveys of various types. This is a place where there is a high demand for Qatari statisticians. Contacts were began between Statistics Program of Qatar university and QSA to start cooperation. Some Statistics students will do their graduate projects that are relevant to the QSA needs. Job opportunities are open their to the extent that they are willing to support statistics students on the condition of working with them after graduation. Some activities during the university and college open days were already done. There is an action plan for the marketing of Statistics that include open days especially for the Statistics program. These are expected to be done during Spring 2010 semester. During the last year, some of the Statistics Program members: Attended the University Open Day for female students on 11/3/2009. Attended the CAS Open Day for male students on 9/11/2009 at the foundation building. Attended the CAS Open Day for female students on 11/11/2009 at the foundation building. Presented PowerPoint slides about the program and employment opportunities in Statistics. Two Statistics students participated in this event. Participated in the Statistical Symposium, Qatar Statistical Authority, November 2008 Arranged A scientific trip to the Supreme Council of Education December 2008 Arranged A scientific trip to Qatar Statistic Authority May 2009 Attended the Strategic Qatarization Plan meeting April 2009 Participated together with some the senior students in the High Level Meeting on Mainstreaming Sectoral Statistical System (QSA) October 2009 Held several meetings as well as in the public presentation highlighting the statistics program activities. Other activities include A student handbook, career booklet together with some posters and guides are currently under preparation. Work is started on updating and improving the website of the Statistics Program. Student’s Club: Dr. Adil Yousif is currently the supervisor. The club produces Monthly newsletter. Student Advisor: Dr. Mohanad Alkhasawneh is currently the advisor of all Statistics students. Curriculum Committee: It is formed with three members. Strategic Plan: A committee for strategic planning is formed in the department and the work was started with well defined goals, objectives and action plan. 9 The Modified Study Plan 10 Study Plan College: Arts and Sciences Program: Dept.: Mathematics, Statistics and Physics Major Statistics – Minor Business Degree: Bachelor of Science (B. Sc.) Total credit hours required for graduation: 120 Credit Hours Program starts on: Fall Semester Maximum No. of admitted students: Male Admitting Criteria : Foundation Program Graduation Project: ---------- Practical Training: ---------- Academic Year: 2010-2011 25 Female: 40 General Outline for the Study Plan: Requirement Cr. Hrs Required University Requirements 33 College Requirements --- Major Compulsives 39 Major Electives 12 Supporting Compulsives 12 The Minor 24 Total 120 11 University Requirements: 33 Credit Hours Note: The research skills package was removed because some of its courses was covered by the major Group Requirement Total Credit Hours Course ARAB 100 Arabic Language 1 Arabic Language 6 2 English Language 3 Islamic Culture 4 Critical Thinking 3 5 History 3 6 Communications Skills 3 7 General Knowledge 3 8 Humanities for science track 6 ARAB 200 Arabic Language II ENGL 202 English Language I Post Foundation ENGL 203 English Language II Post Foundation 6 DAWA 111 Islamic Culture 3 Major Compulsive Courses: (39 Credit Hours) Course No. Credit Hours Course Name Pre-requisite(s): No. / Name --- Semester offered STAT 101 3 Statistics I Fall STAT 102 3 Statistics II STAT 101 STAT 211 3 Introduction to Probability Math 102 and STAT 101 Fall STAT 221 3 Mathematical Statistics I Math 251 and STAT 211 Spring STAT 231 3 Applied Regression Analysis STAT 102 and STAT 211 Spring STAT 312 3 Stochastic Processes STAT 211 and Math 251 Fall STAT 322 3 Mathematical Statistics II STAT 221 Fall STAT 332 3 Design of Experiments STAT 102 and STAT 211 Fall STAT 333 3 Time Series STAT 231 Spring STAT 361 3 Sampling Methods STAT 102 and STAT 211 Spring STAT 371 3 Statistical Packages STAT 231 Fall STAT 481 3 Multivariate Analysis STAT 322 and Math 231 Fall STAT 499 3 Graduation Project Department Approval Spring Spring 12 Major Elective Courses: (12 Credit Hours) Course No. Credit Hours STAT 241 3 Biostatistics STAT 102 or STAT 151 STAT 242 3 Demography STAT 102 Spring STAT 341 3 Actuarial Statistics I STAT 102 and STAT 211 Spring STAT 343 3 Applied Survival Analysis STAT 102 STAT 344 3 Quality Control STAT 102 and STAT 211 STAT 372 3 Statistical Simulation STAT 211 Fall STAT 381 3 Categorical Data Analysis STAT 231 Spring STAT 382 3 Nonparametric Methods STAT 221 Fall STAT 434 3 Generalized Linear Models STAT 322 Fall STAT 442 3 Actuarial Statistics II STAT 341 Fall STAT 445 3 Reliability and Life Testing STAT 322 Spring STAT 464 3 Environmental Statistics STAT 312 and STAT 361 Spring STAT 482 3 Bayesian Statistics STAT 322 Fall STAT 498 3 Special Topics Department Approval Fall Course Name Pre-requisite(s):No. / Name Semesters offered Fall Fall Spring Supporting Compulsive Courses: (12 Credit Hours) Course No. Credit Hours Pre-requisite(s):No. / Name Course Name MATH 101 3 Calculus (1) --- MATH 102 3 Calculus (2) MATH 101 MATH 251 3 Mathematics for Statistics MATH 102 MATH 231 3 Linear Algebra MATH 102 The Minor (24 Credit Hours) The students have the following choices for their minor; a- Minor in Computer Science b- Minor in Business c- Minor in Sociology Important Remarks Statistics students are not allowed to take STAT 151, STAT 154 or STAT 350. Statistics students with minor in Sociology are not allowed to take SOCI 261. Statistics students with minor in Business are not allowed to take STAT 220 or STAT 222. 13 Course Sequencing: Study Plan First Semester (15 Credit Hours) Second Semester (15 Credit Hours) STAT 101 Statistics I STAT 102 Statistics II MATH 101 Calculus (1) MATH 102 Calculus (2) University Requirement 1 University requirement 4 University Requirement 2 University Requirement 5 University Requirement 3 University Requirement 6 Third Semester (15 Credit Hours) Fourth Semester (15 Credit Hours) STAT 211 Introduction to Probability STAT 221 Mathematical Statistics I MATH 251 Mathematics for Statistics STAT 231 Applied Regression Analysis MATH 231 Linear Algebra University Requirement 9 University requirement 7 University Requirement 10 University Requirement 8 University Requirement 11 Fifth Semester (15 Credit Hours) Sixth Semester (15 Credit Hours) STAT 322 Mathematical Statistics II STAT 333 Time Series STAT 371 Statistical Packages STAT 332 Design of Experiments STAT 312 Stochastic Processes STAT 361 Sampling Methods Minor 1 Minor 3 Minor 2 Minor 4 Seventh Semester (15 Credit Hours) STAT 481 Multivariate Analysis Eighth Semester (15 Credit Hours) STAT 499 Graduation Project Major Elective 1 Major Elective 3 Major Elective 2 Major Elective 4 Minor 5 Minor 7 Minor 6 Minor 8 14 Brief COURSE DESCRIPTIONS 15 Course Description: Course Number: STAT 101 Course Name: Statistics I Credit Hours: 3 (2+2) Pre-requisite: None Semester Offered: Fall Course Content: Basic concepts, Population.Types of data, Sampling methods, Tables and graphs. Descriptive Statistics, Basic probability concepts, Random experiment. Sample space, Rules of probability. Counting techniques. Conditional probability. Independence, Discrete and continuous random variables. Sampling distributions, The Student-t distribution, F – distribution and Chi-Square distribution, Point estimation. Confidence intervals for a single population, Testing hypotheses for a single population. Statistical software like Minitab and Excel are used. Course Number: STAT 102 Course Name: Statistics II Credit Hours: 3 (2+2) Pre-requisite: STAT 101 Semester Offered: Spring Course Content: Chi-Square Procedures, The Chi-square distribution. Chi-square goodness of fit test. Contingency tables. Association. Chi-square test for independence. The F-distribution. The completely randomized design. Multiple comparisons. The randomized block design. The two factor factorial design, Simple regression equation. Inference about the regression quantities. Nonparametric Statistics, The sign test and Wilcoxon signed rank test, the Wilcoxon rank sum test. The kruskall-Wallis test. The Friedman test. The Spearman correlation coefficient. Statistical software like Minitab and Excel are used. Course Number: STAT 211 Course Name: Introduction to Probability Credit Hours: 3 (2+2) Pre-requisite: MATH 102 and STAT 101 Semester Offered: Fall Course Content : Random experiment. Sample spaces, Events. Axioms and rules of probability. Equally likely sample spaces. Counting techniques, Conditional probability. Random variables. Expected values. Moment generating function. Probability generating function, Probability distributions, uniform, Bernoulli, 16 binomial, geometric, negative binomial, Poisson and hypergeometric. exponential, gamma, beta and normal. Discrete and continuous bivariate random variables. Joint, Marginal and conditional distributions. Course Number: STAT 221 Course Name: Mathematical Statistics I Credit Hours: 3 (2+2) Pre-requisite: STAT 211 and MATH 251 Semester Offered: Spring Course Content: The Multinomial and multivariate normal distributions. Functions of random variables. 2 Transformation techniques. Sampling Distributions, the t, the , and the F distributions. The distribution of a single order statistic. The joint distribution of two order statistics. Distributions of functions of order statistics. Limit Theorems, Convergence in distribution, Convergence in Probability, Laws of large numbers. Limiting distributions. The Central limit theorem. Course Number: STAT 231 Course Name: Applied Regression Analysis Credit Hours: 3 (2+2) Pre-requisite: STAT 102 and STAT 211 Semester Offered: Spring Course Content: Simple Linear Regression; Residual Analysis; Autocorrelation; Multiple Regression; Parameter Estimation and Testing; Model Selection Procedures; Polynomial Regression; Indicator Variables; Multicollinearity; Outliers and Influential Observation. Statistical software like Minitab, SPSS and R are used. Course Number: STAT 241 Course Name: Biostatistics Credit Hours: 3 (2+2) Pre-requisite: STAT 102 or STAT 151 Semester Offered: Fall Course Content : Methods of Sampling in Medical Studies; Summarizing and Presenting Medical Data; Demographic Statistics; Survival Analysis; Analysis of Cross Tabulation; Inference for Means; Parametric and Non-Parametric with applications to medical data; Multiple Linear, Logistic, Poisson and Cox regression applied to medical data; Sample Size Determination. Statistical software like Minitab and Excel are used. 17 Course Number: STAT 242 Course Name: Demography Credit Hours: 3 (2+2) Pre-requisite: STAT 102 Semester Offered: Spring Course Contents: Basic Concepts, Meaning of population, Demographic rates. Period rates. Person years. Growth rate. The concept of cohort. The crude death rate. Age-specific death rates. The Lexis diagram. Mortality rates. Single-failure indices. The standardized death rate. The standardized mortality ratio. Life Tables, Multiple Decrement Life Tables, Fertility and Reproduction, Modeling Age Patterns Course Number: STAT 312 Course Name: Stochastic Processes Credit Hours: 3 (2+2) Pre-requisite: STAT 211 and MATH 251 Semester Offered: Fall Course Content : Elements of Stochastic Processes; Discrete Time Markov Chains; Random Walks; Branching Processes; Poisson Processes; Birth and Death Processes; Queuing Systems; Renewal Processes. Basic theory of martingales and Brownian motion. Applications to stochastic financial modeling. . Course Number: STAT 322 Course Name: Mathematical Statistics II Credit Hours: 3 (2+2) Pre-requisite: STAT 221 Semester Offered: Fall Course Content: Consistency, Sufficiency, the exponential family of distributions. Completeness of a family of distributions. Theory of Point Estimation, Criteria for judging point estimators. The mean squared error and the variance. Unbiasedness, Rao-Blackwell Theorem. Uniformly minimum variance unbiased estimation. Lower bounds of the variance of unbiased estimators. Information. Efficiency of an estimator. Maximum likelihood method. Moments method. Least squares method. Comparisons between the different methods. Interval estimation, Pivotal quantities. A General method for confidence intervals. Large sample confidence interval. Test of hypotheses, most powerful test. Neyman-Pearson lemma. Uniformly most powerful test. Uniformly most powerful unbiased test. Likelihood ratio test. Sequential tests. Large sample tests. 18 Course Number: STAT 332 Course Name: Designs of Experiments Credit Hours: 3 (2+2) Pre-requisite: STAT 102 and STAT 211 Semester Offered: Fall Course Content : Principles of Experimental Design; Completely Randomized designs; Randomized Complete Block designs; Latin Square designs; Incomplete Block Designs; Factorial Experiments; Split Plot; Analysis of Covariance. Statistical software like Minitab, SPSS and R are used. Course Number: STAT 333 Course Name: Time Series Credit Hours: 3 (2+2) Pre-requisite: STAT 231 Semester Offered: Spring Course Content: This course discusses the analysis of time series data and their use in prediction and forecasting. The course presents various methods including time series regression, smoothing techniques and the Box-Jenkins methodology. The emphasize is on the applied side of the subject utilizing statistical packages like R, SPSS and Minitab. Course Number: STAT 341 Course Name: Actuarial Statistics I Credit Hours: 3 (2+2) Pre-requisite: STAT 102 and STAT 211 Semester Offered: Spring Course contents: Actuarial models, classifying and creating distributions.Frequency and severity with coverage models, deductibles, policy limits and coinsuranse. Aggregrate loss models, compoubd models, computing aggregate claims distributions, comparison beteen the various computing methods. Discrete and Continuous time ruin models. 19 Course Number: STAT 343 Course Name: Applied Survival Analysis Credit Hours: 3 (2+2) Pre-requisite: STAT 102 Semester Offered: Fall Course contents: Censored data, types of censoring, examples of survival data analysis, the survival function, the hazard function, Nonparametric Methods, Life tables, the Product-Limit Estimator of the survival function, comparing two survival distributions (Mantel-Haenszel test), Parametric Survival Distributions and Inference, Goodness of Fit for Survival, Parametric Regression Models, Cox’s Proportional Hazards Model. Statistical software like Minitab, SPSS and R are used. Course Number: STAT 344 Course Name: Quality Control Credit Hours: 3 (2+2) Pre-requisite: STAT 102 and STAT 211 Semester Offered: Spring Course Content: Analysis of Control Charts for Variables and Attributes; Histogram Analysis; Process Capability; Standard Acceptance Sampling Plans; Process Reliability. Statistical software like Minitab and SPSS are used. Course Number: STAT 361 Course Name: Sampling Methods Credit Hours: 3 (2+2) Pre-requisite: STAT 102 and STAT 211 Semester Offered: Spring Course Content: Principles of sampling; questionnaire Design; Simple random sampling; Stratified and Cluster Sampling; Ratio and Regression estimation; Systematic Sampling; Multistage and Multiphase Sampling; Determination of the sample Size; Non-response and Non-sampling Errors Adjustment. 20 Course Number: STAT 371 Course Name: Statistical Packages Credit Hours: 3 (2+2) Pre-requisite: STAT 231 Semester Offered: Fall Course Content: Detailed use and full exploitation of Statistical Packages such as SPSS, MINITAB, R and SAS in working with Data; Topics include Data Entry, checking, manipulation and Analysis. Comparison between the different packages, their advantages and disadvantages. Weeknesses and strengths are discussed. Effective use of Statistical packages in solving real life problems. Advanced features of statistical packages. Course Number: STAT 372 Course Name: Statistical Simulation Credit Hours: 3 (2+2) Pre-requisite: STAT 211 Semester Offered: Fall Course Content: Generating of Discrete and Continuous Random Variables; Bootstrapping; Variance Reduction Techniques; Model Design and Simulation with Applications Including Queuing and other Applications; Verification and Validation of the Model. Using Statistical software like Minitab, SPSS and R. Course Number: STAT 381 Course Name: Categorical Data Analysis Credit Hours: 3 (2+2) Pre-requisite: STAT 231 Semester Offered: Spring Course Content : Contingency Tables; Measures of Association; Exact and Asymptotic methods for 2x2 and rxc Contingency Tables; Probit and Logistic Regression Models for Binary Data; Loglinear Models for Multiway Contingency Tables. Statistical software like Minitab, SPSS and R are used. 21 Course Number: STAT 382 Course Name: Non-Parametric Methods Credit Hours: 3 (2+2) Pre-requisite: STAT 221 Semester Offered: Fall Course Content: Basic Concepts of Non-Parametric Methods; Testing and Estimation for one, Two, and Several sample Problems; Independent and Paired; Location and Dispersion Problems; Goodness of Fit Tests; Tests for Trends and Association; Analysis of variance of Ranked Data; Pittman Efficiency of NonParametric Methods. Statistical software like Minitab, SPSS and R are used. Course Number: STAT 434 Course Name: Generalized Linear Models Credit Hours: 3 (2+2) Pre-requisite: STAT 322 Semester Offered: Fall Course Contents: The Exponential family of distributions, Properties of distributions in the Exponential family, Generalized linear models, Examples, Inference in Generalized Linear Models, Model Adequacy and Diagnostics, The deviance statistic, The residuals, modifications of the residuals and model checks based on the residuals. Special Cases of Generalized Linear Models, Normal theory linear models, Binary logistic regression, Nominal and ordinal logistic regression, Poisson regression and Loglinear models. Statistical software like Minitab, SPSS and R are used. Course Number: STAT 442 Course Name: Actuarial Statistics II Credit Hours: 3 (2+2) Pre-requisite: STAT 341 Semester Offered: Fall Course Content: Construction of Empirical Models, estimation for grouped and modified data, kernel density estimators. Parametric Statistical methods, estimation and confidence intervals in actuarial models. Model Selection, graphical methods, goodness of fit techniques. Credibility theory, Simulation of actuarial models, Case study examples. 22 Course Number: STAT 445 Course Name: Reliability and Life Testing Credit Hours: 3 (2+2) Pre-requisite: STAT 322 Semester Offered: Spring Course Content: Reliability Concepts; Component and System Reliability; Notions of Aging; Lifetime Distributions and Hazard Functions; Types of Censoring; Nonparametric Estimation of Reliability Function; Kaplan-Meier and Nelson Estimators; Parametric Inference Procedures for Exponential, Weibull and Extreme Value Distributions; Proportional Hazards Regression Model; Accelerated Life Testing; StressStrength Models. Statistical software like Minitab, SPSS and R are used. Course Number: STAT 464 Course Name: Environmental Statistics Credit Hours: 3 (2+2) Pre-requisite: STAT 312 & STAT 361 Semester Offered: Spring Course Content: Stochastic processes in the Environment. Fitting probability models to Environmental data. Tail Exponential Method. Poisson Processes and its application. Negative binomial model (Contagion and True Models). Capture-Recapture Method, Distance Sampling, Composite sampling, Introduction of Rank Set sampling methods, adaptive cluster sampling and adaptive allocation methods. Course Number: STAT 481 Course Name: Multivariate Analysis Credit Hours: 3 (2+2) Pre-requisite: STAT 322 and Math 231 Semester Offered: Fall Course Content: Organization of Multivariate Data; Multivariate Distributions; Mahalanobis Distance; Hotelling's T2; Multivariate Analysis of Variance and Regression; Data Reduction Techniques; Discriminant 23 and Classification Analysis; Canonical Correlation Analysis. Statistical software like Minitab, SPSS and R are used. Course Number: STAT 482 Course Name: Bayesian Statistics Credit Hours: 3 (2+2) Pre-requisite: STAT 322 Semester Offered: Fall Course contents: Nature of Bayesian Statistics, Prior and posterior distributions. Noninformative priors. Jeffereys rule. Conjugate priors. Bayesian Inference, Quadratic loss function and Bayes estimators, Highest posterior density intervals, Bayesian tests of hypothesis. Bayesian methods in the normal and some other distributions. Approximate Bayesian Methods, Asymptotic approximations of the Bayes estimator, The Lindley and Tierney-Kadane methods, Markov chain Monte Carlo methods and the Gibbs sampler. Course Number: STAT 498 Course Name: Special Topics Credit Hours: 3 Pre-requisite: Departmental Approval Semester Offered: Fall Course Content: Studies topics in statistics that are not part of the regular offerings. Topics will be selected by statistics faculty members as appropriate. In each offering, a topic of the choice of the instructor will be studied in depth as a regular course. Course Number: STAT 499 Course Name: Graduation Project Credit Hours: 3 Pre-requisite: Departmental Approval Semester Offered: Spring Course Content: A variety of skills learned throughout the curriculum are combined by expecting students to work through a variety of cases studies. Students are expected to collect data and analyze the data individually. Oral and written research reports suitable in format and content are required. 24 the Minor in Statistics 25 The Minor in Statistics Data collection and analysis is an important part in many scientific investigations in various academic disciplines. Some study programs request the student to take one or two statistics courses as part of their curriculum. However, in many situations, deeper and more sophisticated knowledge of Statistics is beneficial, not only during undergraduate studies and graduation projects, but also in their graduate studies where research, data collection, data analysis and the related issues are essential. To fullfil this need, the minor in Statistics is developed where the students are expected to get firm foundation in Statistics so that they can collect and analyze their data with the help of statistical packages like Minitab, SPSS and Excel. The following study plan for the Minor in Statistics is designed to help in achieving these goals and objectives with the desired learning outcomes. The Study Plan for the Minor in Statistics College: Arts and Sciences Dept.: Mathematics, Statistics and Physics Program: Minor in Statistics Total hours required: 24 Credit hours The Minor in Statistics is open for all Qatar University students who major in any field other than statistics. Minor Outlines Compulsive Credit Hours 18 Elective Credit Hours 6 Total 24 Compulsive Courses (18 Cr. Hrs.) Course No. Course Name Pre-requisite(s): STAT 101 Statistics 1 --- STAT 102 Statistics 2 STAT 101 STAT 211 Introduction to Probability MATH 102 and STAT 101 26 STAT 231 Applied Regression Analysis STAT 102 and STAT 211 STAT 361 Sampling Methods STAT 102 and STAT 211 STAT 371 Statistical Packages STAT 231 Elective Courses (6 Cr. Hrs) Credit hours Course No. Course Name STAT 221 Mathematical Statistics 1 3 STAT 241 Biostatistics 3 STAT102 or STAT 151 STAT 242 Demography 3 STAT 102 STAT 332 Design of Experiments 3 STAT 333 Time Series 3 STAT 343 Applied Survival Analysis 3 STAT 344 Quality Control 3 STAT 102 and STAT 211 STAT 372 Statistical Simulation 3 STAT 211 STAT 381 Categorical Data Analysis 3 STAT 382 Nonparametric Statistics 3 Pre-requisite(s) STAT 211 and MATH 251 STAT 102 and STAT 211 STAT 231 STAT 102 STAT 231 STAT 221 Note: Course descriptions are given in previous section 27 The course MATH 251 “MatheMatics for statistics” 28 The Royal Statistical Society commented that there are necessary mathematical areas not covered by the courses in the (2004) plan. On the other hand, some mathematical material that are covered is not needed by statistics students. To solve this problem a new course is developed which contains the relevant mathematical background needed by statistics students to replace the earlier courses Calculus 3 and Calculus 4. The course contents are determined following the recommendations of the Royal Statistical Society and the several meetings within the statistics program and with the mathematics program. The new course proposal was submitted for university approval separately by the Mathematics Program. The course short syllabus is given in the following page. 29 Mathematics for Statistics 123- Course Number: Credit Hours: Prerequisites: Math 251 3 (4+0) MATH 102 COURSE OBJECTIVES 450123- To develop the ability to evaluate limits and differentiate functions of several variables and use them in some applied problems. To provide students with the skills of multiple integration for functions of several variables. To acquaint students with the basic concepts of differential equations with emphasis on first order ordinary differential equations. To introduce the students to some basic concepts of numerical analysis. To make use of Mathematical software as Mathematica in applications. To introduce Gamma, Beta and Error functions and provide skills to use them for evaluation of some integrals. SYLLABUS ITEMS Functions of Several Variables: Elementary examples including Quadric surfaces, Limits and Continuity, Notion of differentiability, Partial derivatives, Mean value theorem, Chain rules, Maximum and Minimum values, Lagrange’s Multipliers. Multiple Integrals: Double integrals and triple integrals, Properties, Evaluation by repeated integrals, Polar coordinates. First Order Differential Equations: Classification, Initial-value problems, Separable variables, Linear equations. Introduction to partial Differential Equations: Method of separation of variables for some basic linear partial differential equations. Numerical Solution of nonlinear equations: Iterative techniques including the Bisection method for single equations, and the Newton-Raphson method for nonlinear systems of equations, Applications with Mathematical software. Numerical Integration: The Trapezoid rule, The Simpson’s rule, Applications with Mathematical software. 30 Some special functions: Gamma function, Beta function, Error function, Applications REFERENCES Calculus, by James Stewart, 6th Edition, 2008, Brooks/Cole. Differential Equations With Boundary Problems, D. G. Zill and M. Cullen, 4th Edition, 1997, Brooks/Cole Publishing Company. Advanced Engineering Mathematics, Erwin Kreyszig, 7th Edition, 1993, John Wiley and sons, Inc. Course SYLLABI 31 32 COLLEGE OF ARTS AND SCIENCES DEPARTMENT of MATHEMATICS, STATISTICS AND PHYSICS STAT 101 Statistics I Course Information Course Title: Statistics I Course Number: STAT 101 Credit Hours: 3 (2+2) Course Status: Major Compulsive Course Prerequisite: None Course Description Basic concepts. Types of data, Sampling methods, Tables and graphs. Descriptive Statistics, Basic probability concepts,Random experiment. Sample spaces, Rules of probability. Counting techniques. Conditional probability. Independence, Discrete and continuous random variables. Sampling distributions, The Student-t distribution, F – distribution and Chi-Square distribution, Point estimation. Confidence intervals for a single population. Testing hypotheses for a single population. Statistical software like Excel and Minitab will be used. Course Objectives The course aims at: 1234567- Demonstrating the need for statistical tools, their meaning and concepts. Acquainying the student with the basic data collection techniques. Emphasizing the descriptive statistical analysis of data and their interpretation. Acquainting the student with the basic concepts of probability and probability distributions. Introducing the concept of sampling distributions and some commonly used ones. Acquainting the student with the basic concepts and procedures of statistical inference. Emphasize the use of computers and/or scientific calculators in practical applications. Learning Outcomes By the end of this course, students will be able to: 1- Collect some types of data in accordance with statistical principles. 33 2- Describe various types of data numerically and graphically. Compute basic probabilities. Use computers to find probabilities and quantiles of some common distributions. Formulate and solve some basic inferential statistics problems. Use computers to carry out statistical inference about a population mean, a population proportion and a population variance. 7- Interpret the results of a data analysis concerning a population mean, a population proportion and a population variance. 3456- Content Distribution Week 1 2 3 4 5 6 7 8 9 10 11 12 13 14 Topics Statistics. Population. Types of data. Sampling techniques Tables and graphs. Displaying quantitative data. Descriptive Statistics Measure of central tendency, Measures of dispersion Measures of skewness and kurtosis, Z–scores, Percentiles and Quartiles). Random experiment. Sample space. Axioms of probability. Rules of probability. Counting techniques Conditional probability. Independence. The theorem of total probability. Bayes’ Theorem. Discrete and continuous random variables. Probability distributions The Bernoulli, Binomial, and Poisson distributions. The Normal distribution. The central limit theorem. Sampling distributions of sample statistics, the mean, median, variance. The Student-t distribution, F – distribution and Chi-Square distribution. Point estimation. Confidence intervals for a single population (mean, proportion and variance) Testing hypothesis, type 1 error and type 2 error. The power of the test Testing hypotheses for a single population (mean, proportion and variance Large sample intervals and tests for the population mean or proportion. Assessment: Midterm Exams, Final Exam, Assignments, Quizzes. References 1- Statistics. McClave and Sincich, 2003, 9th edition, Prentice-Hall. 2- Elementary Statistics. Bluman, 2008, 7th edition, McGraw-Hill. 3- Introductory Statistics Neil, A. Weiss, 2008, 8th edition, Addison Wesley. 34 35 COLLEGE OF ARTS AND SCIENCES DEPARTMENT of MATHEMATICS, STATISTICS AND PHYSICS STAT 102 Statistics II Course Information Course Title: Statistics II Course Number: STAT 102 Credit Hours: 3 (2+2) Course Status: Major Compulsive Course Prerequisite: STAT 101 Course Description Chi-Square Procedures. Chi-square goodness of fit test. Contingency tables. Association. Chi-square test for independence. The completely randomized design. Multiple comparisons. The randomized block design. The two factor factorial design, Simple regression equation. Inference about the regression quantities. Nonparametric Statistics, The sign test and Wilcoxon signed rank test, the Wilcoxon rank sum test. The kruskall-Wallis test. The Friedman test. The Spearman correlation coefficient. Statistical software like Excel and Minitab will be used. Course Objectives The course aims at: 4- Acquainting students with Chi-Square procedures for testing homogeneity, independence and goodness of fit. 5- Introducing the basic ideas of experimental design and analysis of variance. Giving an introduction to regression and correlation analyses. Introducing the students to nonparametric techniques and their applications. 67- Learning Outcomes By the end of this course, students will be able to: 1- Formulate and test hypotheses concerning frequency data 2- Distinguish between the various type of frequency data collection techniques 3- Analyze data from experimental designs and interpret the results 4- Choose the suitable design for a given problem 5- Conduct regression and correlation analyses and interpret the results 36 6- Check the assumptions of statistical inference procedures and use nonparametric alternatives when the assumptions are not satisfied 7- Use statistical software to analyze the data Content Distribution Topics Week 1 2 3 4 5 6 7 8 9 10 11 12 13 14 Confidence intervals for the difference of two population means based on paired and independent samples. Confidence intervals for proportions. Confidence intervals for the ratio of two variances Testing hypothesis for the equality of two populations (means, proportions and variances) Chi-square goodness of fit test Contingency tables. Association. Chi-square test for independence The completely randomized design. Multiple comparisons The randomized block design. The two factor factorial design. The regression equation. The coefficient of determination Linear correlation. Inference about the regression quantities. Prediction. Assumptions and residual plots. The sign test and Wilcoxon signed rank test for paired samples The Wilcoxon rank sum test for two independent samples. The kruskall-Wallis test The Friedman test. The Spearman correlation coefficient Assessment: Midterm Exams, Final Exam, Assignments, Quizzes. References 1- Statistics. McClave and Sincich, 2003, 9th edition, Prentice-Hall. 2- Elementary Statistics. Bluman, 2008, 7th edition, McGraw-Hill. 3- Introductory Statistics Neil, A. Weiss, 2008, 8th edition, Addison Wesley. 37 COLLEGE OF ARTS AND SCIENCES DEPARTMENT of MATHEMATICS, STATISTICS AND PHYSICS STAT 211 Introduction to Probability Course Information Course Title: Introduction to Probability Course Number: STAT 211 Credit Hours: 3 (2+2) Course Status: Major Compulsive Course Prerequisite: MATH 102 and STAT 101 Course Description Random experiment. Sample spaces, Events. Axioms and rules of probability. Equally likely sample spaces. Counting techniques, Conditional probability. Random variables. Expected values. Moment generating function. Probability generating function, Probability distributions, uniform, Bernoulli, binomial, geometric, negative binomial, Poisson and hypergeometric. exponential, gamma, beta and normal. Discrete and continuous bivariate random variables. Joint, Marginal and conditional distributions. Course Objectives The course aims at: 1- Familiarizing the student with the foundations of probability and the basic probability tools and methods. 2- Acquainting students with random variables and probability distributions. 3- Acquainting students with some discrete and continuous probability models. 4- Introducing some probability theorems and their useful applications. 5- Familiarizing students with some multidimensional random variables. 6- Familiarizing students with some mathematical tools needed in statistics. Learning Outcomes By the end of this course, students will be able to: 1- Calculate probabilities and other relevant quantities from probability distributions 2- Select the suitable probability distributions for certain problems 38 3- Derive the expectations, moment generating functions and the cumulative distribution functions for certain probability distributions 4- Use inequalities and certain theorems to establish certain useful properties of probability distributions 5- Work with certain multivariate distributions and derive marginal and conditional probability distributions Content Distribution Week 1 2 3 4 5 6 7 8 9 10 11 12 13 14 Topics Probability as a long-term behavior of events under identical conditions. Random experiment. Sample spaces, Events. Axioms and rules of probability. Equally likely sample spaces. Counting techniques, Combinations and Permutations, Combinatoric formulae, Conditional probability. Independence of events The theorem of total probability. Bayes’ rule Random variables. Discrete and continuous random variables Distribution function. Probability mass function and probability density function. Expected value. Variance. Moments of random variables Chebychev’s theorem. Moment generating function. Probability generating function. Some discrete distributions: uniform, Bernoulli, binomial, geometric, negative binomial, Poisson and hypergeometric Some continuous distributions: uniform, exponential, gamma, beta and normal Moment and probability generating functions for specific distributions Discrete and continuous bivariate random variables. Joint, Marginal and conditional distributions Assessment: Midterm Exams, Final Exam, Assignments, Quizzes. References 1- John E. Freund's Mathematical Statistics. Miller & Miller, 7th Edition, 2003, Prentice Hall. 2- Probability and Mathematical Inference. Hogg and Tanis, 8th Edition, 2009, Prentice Hall. 3- Introduction to Mathematical Statistics. Hogg, Craig and McKean, 6th Edition, 2004, Prentice Hall. 39 40 COLLEGE OF ARTS AND SCIENCES DEPARTMENT of MATHEMATICS, STATISTICS AND PHYSICS STAT 221 Mathematical Statistics I Course Information Course Title: Mathematical Statistics I Course Number: STAT 221 Credit Hours: 3 (2+2) Course Status: Major Compulsive Course Prerequisite: MATH 251 and STAT 211 Course Description The Multinomial and multivariate normal distributions. Functions of random variables. Transformation 2 techniques. Sampling Distributions, the t, the , and the F distributions. The distribution of a single order statistic. The joint distribution of two order statistics. Distributions of functions of order statistics. Limit Theorems, Convergence in distribution, Convergence in Probability, Laws of large numbers. Limiting distributions. The Central limit theorem Course Objectives The course aims at: 1- Acquainting students with some basic statistical tools needed to develop some statistical theorems and applications. 2- Developing the skills needed to obtain sampling distributions of some important statistics. 3- Acquainting the students with the basic theory of order statistics and the related problems. 4- Developing the important ideas of limiting distributions and convergence of random variables and their use in statistics. Learning Outcomes By the end of this course, students will be able to: 1- Obtain the distribution of certain functions of random variables 41 2- Obtain the distributions of order statistics and the related quantities 3456- Prove some basic mathematical statistics theorems Use theorems to derive the sampling distributions of some statistics Derive the large sample distributions of some important statistics State, prove and use the central limit theorem and laws of large numbers Content Distribution Week 1 2 3 4 5 6 7 8 9 10 11 12 13 14 Topics Special multivariate distributions, the Multinomial The multivariate normal distributions. Functions of a single random variable. Transformation techniques. Jacobians. Distribution function technique Functions of more than one random variable. Transformation techniques. Jacobians. Distribution function technique The moment and probability generating function technique 2 Sampling from the normal distribution. Distribution of mean and variance. The t, the , and the F distributions. The distributions of a single and two order statistics. Distributions of functions of order statistics like the range. Convergence in distribution Convergence in Probability Laws of large numbers Limiting distributions The Central limit theorem Applications Assessment: Midterm Exams, Final Exam, Assignments, Quizzes. References 1- John E. Freund's Mathematical Statistics. Miller & Miller, 7th Edition, 2003, Prentice Hall. 2- Introduction to Mathematical Statistics. Hogg, Craig and McKean, 6th Edition, 2004, Prentice Hall. 3- An Introduction to mathematical Statistics. By Larsen and Mood, 4th Edition, 2005, Prentice Hall. 42 43 COLLEGE OF ARTS AND SCIENCES DEPARTMENT OF MATHEMATICS, STATISTICS AND PHYSICS STAT 231 Applied Regression Analysis Course Information Course Title: Applied Regression Analysis Course Number: STAT 231 Credit Hours: 3(2+2) Course Status: Major Compulsory Course Prerequisite: STAT 102 and STAT 211 Course Description This course covers regression models with emphasis on linear regression models. Model fitting and checking procedures. Model building and model adequacy checking. Diagnostics with remedial procedures. Inference techniques on the regression quantities are considered with applications to many real life problems. Statistical software like Minitab, SPSS and R will be used. Course Objectives The course aims at: 1- Introducing simple regression and correlation analysis with the model building process. 2- Acquainting students with methods and concept of multiple regression and correlation. 3- Developing the ability to build regression models. 4- Acquainting students with the non linear regression theory. 5- Familiarizing the student with the statistical software tools used for applying regression analysis Learning Outcomes By the end of this course, students will be able to: 1- Fit simple linear regression models 2- Interpret the results of the simple linear regression analysis 44 3- Build Multiple regression models 4- Check regression assumptions and undertake remedial actions 5- Use statistical software like Minitab, R or SPSS Content Distribution Week 1 2 3 4 5 6 7 8 9 10 11 12 13 14 Topics Revision of some key concepts in statistics and preparation to the coming course contents Simple linear Regression models. Least squares estimation of regression parameters. Inference in simple regression models Diagnostics and remedies Applications Multiple regression models. General Linear regression model in matrix terms. Estimation of regression coefficients. Fitted values and residuals. Analysis of variance results. Inferences about regression parameters. Estimation of mean response and prediction of new observation. Diagnostics and remedial measures. Applications Use of indicators variables as regressors. Overview of model-building process. All-Possible-Regression procedures for variables reductions. Forward stepwise Regression and other automatic-search procedures for variables reductions Applications Identifying outlying Y observations: studentized deleted residuals. Identifying outlying X observations: hat matrix. Multicolinearity. Influential observations, Remedial measures Nonlinear regression models Assessment: Midterm Exams, Final Exam, Assignments, Mini Projects, Lab assignments. References 1- Applied Linear Regression Models. Neter Kutner Nachtshem Wasserman, 4th Edition, 2004, Irwin. 2- Regression Analysis by Examples. Samprit Chatterjee and Hadi, A., 4th Edition, 2006, John Wiley and sons, Inc. 3- Applied Regression Analysis. Draper and Smith, Press, 3rd Edition, 1998, John Wiley and sons, Inc. 45 COLLEGE OF ARTS AND SCIENCES DEPARTMENT OF MATHEMATICS, STATISTICS AND PHYSICS STAT 241 Biostatistics Course Information Course Title: Biostatistics Course Number: STAT 241 Credit Hours: 3(2+2) Course Status: Major Elective Course Prerequisite: STAT 102 Course Description Methods of Sampling in Medical Studies; Summarizing and Presenting Medical Data; Demographic Statistics; Survival Analysis; Analysis of Cross Tabulation; Inference for Means; Parametric and NonParametric with applications to medical data; Multiple Linear, Logistic, Poisson and Cox regression applied to medical data; Sample Size Determination. Statistical software like Minitab and Excel are used. Course Objectives The course aims are: 1- To familiarize students with basic methods of sampling for collection of data and use of follow-up surveys in biomedical and health studies.. 2- To review different methods of estimation of parameters, testing of hypothesis and regression models with applications to medical studies. 3- To introduce analysis of contingency tables techniques relevant to medical data. 4- To introduce the design of biostatistical studies 5- To familiarize students with different measures of Demography and life tables. Learning Outcomes By the end of this course, students will be able to: 1- Present and describe medical data 2- Construct and interpret life tables 3- Calculate and interpret some biostatistical measures like the odds ratio. 46 4- Analyze survival regression models like the proportional hazards and the parametric life regression models. 5- Analyze data in the form of contingency tables arising from biostatistical designs 6- Use statistical software like Minitab, R or SPSS for data analysis Content Distribution Week 1 2 3 4 5 6 7 8 9 10 11 12 13 14 Topics Basic techniques of data collection Cross-sectional data, Follow-up surveys Elements of estimation and testing of hypothesis with applications to medical data Simple linear regression applied problems arising in medical studies Analysis of variance for medical data designs Contingency tables. Relative risk. Odds ratio Test of independence. Test for goodness of fit, Applications Nonparametric methods with medical data Measures of mortality Life-Tables and follow up studies Measures of fertility. Measures of population growth. Concept of stable populations. Projection of population. Logistic regression Survival regression models, Cox’s regression model Assessment: Midterm Exams, Final Exam, Assignments, Mini Projects, Lab assignments. References 1- Introductory Biostatistics. Chap T. Lee, 2003, 1st edition, John Wiley, N. Y. 2- Biostatistics: A Foundation for Analysis in Health Sciences. Wayne. W. Daniel, 1998, 7th edition, John Wiley and Sons, Inc. 3- Applied Statistics. Parimal Mukhopadhay, 1999, New Central, Calcutta. 4- Medical Biostatistics. Abhaya Indrayan, Series Volume: 7, 2000, Marcel Dekker, Inc. 5- An Introduction to Medical Statistics. Martin Bland, 3rd edition, 2000, Oxford Press. 47 COLLEGE OF ARTS AND SCIENCES DEPARTMENT of MATHEMATICS, STATISTICS AND PHYSICS STAT 242 Demography Course Information Course Title: Demography Course Number: STAT 242 Credit Hours: 3 (2+2) Course Status: Major Elective Course Prerequisite: STAT 102 Course Description Basic Concepts, Meaning of population, Demographic rates. Period rates. Person years. Growth rate. The concept of cohort. The crude death rate. Age-specific death rates. The Lexis diagram. Mortality rates. Single-failure indices. The standardized death rate. The standardized mortality ratio. Life Tables, Multiple Decrement Life Tables, Fertility and Reproduction, Modeling Age Patterns Course Objectives The course aims are: 1- To acquaint the student with the basic concepts in demography including the population and the rates of various types. 2- To acquaint the students with the methods of calculating Age-Specific rates and probabilities. 3- To give the student an introduction to life tables and multiple decrement life tables. 4- To introduce the students to fertility rates, cohort fertility and reproduction measures. 5- To give the student a good knowledge in population projections and modeling age patterns Learning Outcomes By the end of this course, students will be able to: 12345- Calculate the crude death rate, age specific death rates and mortality rates Construct and use life tables Use multiple decrement life tables Analyze fertility data Analyze age patterns of migration 48 Content Distribution Week 1 2 3 4 5 6 7 8 9 10 11 12 13 14 Topic Meaning of population. Demographic rates. Period rates. Person years. Growth rate. The concept of cohort The crude death rate. Age-specific death rates The Lexis diagram. Mortality rates Single-failure indices. The standardized death rate. The standardized mortality ratio. The life table. Life table construction Life table interpretation. Life tables and mortality Multiple decrement life tables and its algebra Dependent and independent death rates Fertility rates. Age specific fertility rates Period fertility. Cohort fertility. Age patterns of mortality. Age patterns of fertility Age patterns of migration Birth interval analysis Assessment: Midterm Exams, Final Exam, Assignments, Mini Projects. References 1- Demographic Methods Hinde, A. (1998). Arnold, London 2- Demographic methods and concepts Rowland, D.T. (2003). Oxford Press 49 COLLEGE OF ARTS AND SCIENCES DEPARTMENT OF MATHEMATICS, STATISTICS AND PHYSICS STAT 312 Stochastic Processes Course Information Course Title: Stochastic Processes Course Number: STAT 312 Credit Hours: 3(2+2) Course Status: Major Compulsory Course Prerequisite: STAT 211 and MATH 251 Course Description Elements of Stochastic Processes; Discrete Time Markov Chains; Random Walks; Branching Processes; Poisson Processes; Birth and Death Processes; Queuing Systems; Renewal Processes. Basic theory of martingales and Brownian motion. Aapplications to stochastic financial modeling. Course Objectives The course aims are: 1- To develop an awareness of the use of stochastic processes to build adequate mathematical models for random phenomena evolving in time. 2- To understand notions of long-time behavior including transience, recurrence, and equilibrium to answer basic questions in several applied situations including branching processes and random walk. 3- To introduce students to basic concepts, techniques and results associated primarily with the elementary theory of Markov processes. 4- To introduce students to basic queuing models involving exponential arrivals and departures. 5- To familiarize the student with concepts of Matingales and Brownian motion. 6- To familiarize the student with some applications of stochastic processes in finanancial modeling. Learning Outcomes By the end of this course, students will be able to: 1- Construct transition matrices in Markov chains and calculate various types of transition probabilities 50 23456- Classify states and Markov chains according to their long term behavior Use Poisson processes for modeling various phenomena Use queuing models with exponential arrivals and departures to model real life situations Derive the probabilities for the birth death process and renewal theory Calculate measures of performance of systems modeled by stochastic processes Content Distribution Week 1 2 3 4 5 6 7 8 9 10 11 12 13 14 Topics Definitions, basic concepts and classification of general stochastic processes. Markov property, Chapman-Kolmogorov equations Representation of chains using digraphs and stochastic matrices Classification of states, Ergodicity Limiting behavior of Markov chains Random walks (absorption probability, mean time to absorption) Branching processes (Galton-Watson criticality theorem, extinction probabilities) Definition, Poisson process Pure birth and pure death processes, birth and death processes Measures of effectiveness, M/M/1 M/M/s and M/G/1 queues Applications in Reliability Martingales and Brownian motion Applications in financial modeling Assessment: Midterm Exams, Final Exam, Assignments, Quizzes. References 1- An Introduction to Stochastic Modeling. H. M. Taylor and S. Karlin, 3rd Edition, 2003, Academic Press. 2- Introduction to Stochastic Processes Gregory F. Lawler, 2nd edition, 2006, CRC Press. 3- Introduction to Probability Models. S. M. Ross, 9th Edition, 2006, Academic Press. 4- Essential of Stochastic Processes. R. Durrett, 2nd Edition, 1999, Springer Verlag. 51 COLLEGE OF ARTS AND SCIENCES DEPARTMENT of MATHEMATICS, STATISTICS AND PHYSICS STAT 322 Mathematical Statistics II Course Information Course Title: Mathematical Statistics II Course Number: STAT 322 Credit Hours: 3 (2+2) Course Status: Major Compulsive Course Prerequisite: STAT 221 Course Description Consistency, Sufficiency, the exponential family of distributions. Completeness of a family of distributions. Theory of Point Estimation, Criteria for judging point estimators. The mean squared error and the variance. Unbiasedness, Rao-Blackwell Theorem. Uniformly minimum variance unbiased estimation. Lower bounds of the variance of unbiased estimators. Information. Efficiency of an estimator. Maximum likelihood method. Moments method. Least squares method. Comparisons between the different methods. Interval estimation, Pivotal quantities. A General method for confidence intervals. Large sample confidence interval. Test of hypotheses, most powerful test. Neyman-Pearson lemma. Uniformly most powerful test. Uniformly most powerful unbiased test. Likelihood ratio test. Sequential tests. Large sample tests. Course Objectives The course aims are: 1- To acquaint students with some basic statistical concepts needed to develop some statistical estimation and testing theorems and applications. 2- To familiarize students with methods of statistical inference under various probability models and how to apply them. 3- To develop the optimality criteria used for estimation and testing. 4- To introduce sequential and large sample tests Learning Outcomes By the end of this course, students will be able to: 52 1- Classify distributions belonging to the exponential family of distributions 2- Use effectively the properties of the exponential family of distributions to derive statistical inference procedures 3- Use the optimality criteria to compare the competing inference procedures 4- Derive point estimators like the maximum likelihood, the least squares, the moments and the minimum variance unbiased estimators 5- Derive most powerful and likelihood ratio tests 6- Construct confidence intervals and study their properties 7- Derive large sample test 8- Apply sequential tests Content Distribution Week 1 2 3 4 5 6 7 8 9 10 11 12 13 14 Topics Consistency of an estimator. Sufficiency of a statistic Exponential family of distributions. Completeness of a family of distributions Criteria for judging point estimators. The mean squared error and the variance. Unbiasedness Rao-Blackwell Theorem. Uniformly minimum variance unbiased estimation Lower bounds of the variance of unbiased estimators. Information. Efficiency of an estimator Maximum likelihood method Moments and Least squares method, Comparisons Pivotal quantities A General method for confidence intervals Large sample confidence interval Basic concepts. Most powerful test. Neyman-Pearson lemma Uniformly most powerful test. Uniformly most powerful unbiased test Likelihood ratio test Sequential tests. Large sample tests Assessment: Midterm Exams, Final Exam, Assignments, Quizzes. References 1- John E. Freund's Mathematical Statistics. Miller & Miller, 7th Edition, 2003, Prentice Hall. 2- Probability and Mathematical Inference. Hogg and Tanis, 8th Edition, 2009, Prentice Hall. 3- Introduction to Mathematical Statistics. Hogg, Craig and McKean, 6th Edition, 2004, Prentice Hall. 53 COLLEGE OF ARTS AND SCIENCES DEPARTMENT OF MATHEMATICS, STATISTICS AND PHYSICS STAT 341 Actuarial Statistics I Course Information Course Title: Actuarial Statistics I Course Number: STAT 442 Credit Hours: 3 (2+2) Course Status: Program Elective Course Prerequisite: STAT 102 and STAT 211 Course Description Actuarial models, classifying and creating distributions.Frequency and severity with coverage models, deductibles, policy limits and coinsuranse. Aggregrate loss models, compoubd models, computing aggregate claims distributions, comparison beteen the various computing methods. Discrete and Continuous time ruin models. Course Objectives The course aims at: 1- Acquainting the student with actuarial models and the related quantities 2- Familiarize the student with methods of calculating deductibles and studying their effect on claim frequency and the effect of inflation on them 3- Gain knowledge on aggregate loss distributions and the related calculations 4- Acquainting the student with stochastic processes associated with insurance including discrete and continuous ruin probabilities Learning Outcomes By the end of this course, students will be able to: 1- Derive and work with actuarial probability models and the related functions 54 2- Calculate deductibles and study their effects on claim frequency and how they are affected by inflation 3- Compute aggregate claim distributions with recursive methods and approximate methods 4- Develop and use stochastic models for insurance 5- Derive continuous and discrete ruin probabilities Content Distribution Week 1 2 3 4 5 6 7 8 9 10 11 12 13 14 Topics Introduction to Actuarial Science, Examples Actuarial probability models Functions associated with probability distributions Creating new distributions, Mixture distribution Deductibles, the loss elimination ratio, the effect of inflation for ordinary deductibles Coinsurance, the impact of deductibles on claim frequency Aggregate loss models, model choices The compound model for aggregate claims, computing the aggregatre claims distribution Recursive methods calculations with approximate distributions Exact calculaions of the aggregate distribution, Compound Poisson approximation Process models for insurance, Discrete ruin probabilities Continuous time ruin models Examples and Applications Assessment: Midterm Exams, Final Exam, Assignments, Mini Projects. References 1- Loss Models: From Data to Dicisions Stuart A. Klugman, Harry, H. Panjer and Gordon E. Willmot, 3rd edition, Wiley InterScience. 2- Modern Actuarial Risk Theory Rob Kaas, Marc Goovaerts, Jan Dhaene and Michel Denoit, 2nd edition, Springer. 3- Modern Actuarial Theory and Practice Philip Booth, Robert Chadburn, Steve Haberman and Dewi James, 2nd edition, Chapman and Hall/CRC 55 COLLEGE OF ARTS AND SCIENCES DEPARTMENT OF MATHEMATICS, STATISTICS AND PHYSICS STAT 332 Design of Experiments Course Information Course Title: Design of Experiments Course Number: STAT 332 Credit Hours: 3(2+2) Course Status: Major Compulsory Course Prerequisite: STAT 231 Course Description Principles of Experimental Design; Completely Randomized designs; Randomized Complete Block designs; Latin Square designs; Incomplete Block Designs; Factorial Experiments; Split Plot; Analysis of Covariance. Statistical software like Minitab and R will be used. Course Objectives The course aims at: 1234- Acquainting students with single factor experiments. Familiarizing the student with multiple comparisons procedures Introducing some special designs that have a wide variety of applications. Acquainting students with factorial experiments and higher designs that have a wide variety of applications. 5- Acquainting the student with the distribution theory of statistics used in analysis of variance techniques. Learning Outcomes By the end of this course, students will be able to: 1- Design statistical experiments which conforms to the basic statistical principles of experimental design 2- Write down the statistical model for the single factor, block, factorial and related designs and estimate their parameters 3- Construct the relevant ANOVA table for the given design and interpret the results 4- Perform various types of multiple comparisons procedures when needed 56 5- Use statistical software to obtain the results of the analysis of a designed experiment and interpret their values. 6- Derive and prove some basic distributional properties related to F tests. Content Distribution Week 1 2 3 4 5 6 7 8 9 10 11 12 13 14 Topics Experiments with Single factor studies The Completely randomized design Multiple Comparisons Randomized block Latin squares, related designs Applications Factorial designs 2 k factorial designs 3 k factorial designs Applications Random factors and Mixed models Rules for the expected mean squared error Nested and Split Plot designs Analysis of Covariance Assessment: Midterm Exams, Final Exam, Assignments, Mini Projects, Lab assignments. References 1- Design and Analysis of Experiments. D. C. Montgomery, 7th Edition, 2007, John Wiley and sons, Inc. 2- Statistical Design and Analysis of Experiments. Mason, Gunst and Hess, 2nd Edition, 2003, John Wiley and sons, Inc. 3- Fundamental Concepts in the Design of Experiments. Charles Hicks, 5th Edition, 1999, Oxford University Press. 57 COLLEGE OF ARTS AND SCIENCES DEPARTMENT OF MATHEMATICS, STATISTICS AND PHYSICS STAT 333 Time Series Course Information Course Title: Time Series Course Number: STAT 333 Credit Hours: 3 (2+2) Course Status: Major Compulsory Course Prerequisite: STAT 231 Course Description This course discusses the analysis of time series data and their use in prediction and forecasting. The course presents various methods including time series regression, smoothing techniques and the BoxJenkins methodology. The emphasize is on the applied side of the subject utilizing statistical packages like R, SPSS and Minitab. Course Objectives The course aims at: Introducing the concept of a time series and the nature of time series data. 12345- Giving a firm knowledge on how and when to apply the time series methodology. Introducing smoothing techniques and their use in time series data Developing the Box-Jenkinz methodology for time series data Giving practice in analyzing real world problems and interpret the results. Building a solid theoretical background for the subject. Learning Outcomes By the end of this course, students will be able to: 1234567- Analyze various types of time series regression models. Use decomposition and smoothing techniques Apply the Box-Jenkins methodology for time series data. Use packages to implement decomposition and Box-Jenkinz methods Conduct real life studies involving time series Produce and interpret the computer output of various packages for the time series analysis. Explain the theoretical basis of the methods of time series analysis 58 Content Distribution Week 1 2 3 4 5 6 8 9 10 11 12 13 14 Topics Introduction and general ideas The nature of time series data and forecasting Time series regression Model checks, autocorrelation, transformation, dummy variables Decomposition methods Applications Single Exponential smoothing Double exponential smoothing Holt-Winter’s methods Nonseasonal Box-Jenkinz methods Diagnostics and forecasting Box-Jenkinz seasonal modeling Applications Assessment: Midterm Exams, Final Exam, Assignments, Mini Projects, Lab assignments. References 1- Forecasting, Time series and Regression: an applied approach. B. Bowerman, R. O'Connell and Anne. Koehler, 4th edition, 2004, South Western College Publications. 2- Time Series Models. Harvey, A.C., 2nd Edition, 1993, Harvester Wheatsheaf. 3- Time Series Analysis, Forecasting and Control. G. Box, G Jenkins and G. Reinsel, 4th Edition, 2008, Wiley. 59 COLLEGE OF ARTS AND SCIENCES DEPARTMENT of MATHEMATICS, STATISTICS AND PHYSICS STAT 343 Applied Survival Analysis Course Information Course Title: Applied Survival Analysis Course Number: STAT 343 Credit Hours: 3 (2+2) Course Status: Major Elective Course Prerequisite: STAT 102 Course Description Censored data, types of censoring, examples of survival data analysis, the survival function, the hazard function, Nonparametric Methods, Life tables, the Product-Limit Estimator of the survival function, comparing two survival distributions (Mantel-Haenszel test), Parametric Survival Distributions and Inference, Goodness of Fit for Survival, Parametric Regression Models, Cox’s Proportional Hazards Model. Statistical software like Minitab, SPSS and R are used Course Objectives The course aims at: 1- Introducing censored data and presenting the special features associated with them 2- Acquainting the student with the statistical models used in survival analysis and their properties. 3- Introducing the concept of covariate and how to study their effects on survival times 4- Developing the skills, including using statistical software, needed to handle practical situations with survival analysis. 5- Stimulating interest to go for advanced studies in survival analysis. Learning Outcomes By the end of this course, students will be able to: 1- Derive the survival function, the hazard function and other related quantities in survival analysis 60 234567- Identify suitable distributions for the given data using probability and hazard plotting Compute nonparametric estimators like the product-limit estimator Construct life tables Compare survival experience of two or more groups of individuals Study the effect of covariates on survival time using regression models Use statistical software for the analysis of survival data Content Distribution Week 1 2 3 4 5 6 8 9 10 11 12 13 14 Topics Censored data, types of censoring, examples of survival data analysis the survival function, the hazard function Life tables, the Product-Limit Estimator of the survival function Comparing two survival distributions (Mantel-Haenszel test) The Exponential and Weibull distributions The Lognormal, Gamma and Log-logistic distributions Other survival distributions Inference in survival models with covariates Probability plotting, hazard plotting Cox- Snell residuals, goodness of fit based on likelihood asymptotics Exponential regression, Weibull regression Lognormal regression, Model selection Estimation and testing in the proportional hazards model Assessment: Midterm Exams, Final Exam, Assignments, Mini Projects, Lab assignments. References 1- Analysis of Survival Data D.R. Cox and D. Oakes, Chapman & Hall, 1984. L. Prentice, Wiley, 2002. 2- Statistical Models and Methods for Lifetime Data, 2nd Ed. J.F. Lawless, Wiley,2003. 3- Modeling Survival Data, Extending the Cox Model T.M. Therneau and P.M. Grambsch, Springer, 2000. 61 COLLEGE OF ARTS AND SCIENCES DEPARTMENT OF MATHEMATICS, STATISTICS AND PHYSICS STAT 344 Quality Control Course Information Course Title: Quality Control Course Number: STAT 344 Credit Hours: 3(2+2) Course Status: Major Elective Course Prerequisite: STAT 102 and STAT 211 Course Description Analysis of Control Charts for Variables and Attributes; Histogram Analysis; Process Capability; Standard Acceptance Sampling Plans; Process Reliability. Statistical software like Minitab, SPSS and R are used Course Objectives The course aims are: 1- To acquaint students with control charts of variables and attributes. 2- To introduce process capability and its assessments. 3- To learn various sampling plans and their properties. Learning Outcomes By the end of this course the student will be able to: 12345- Construct, use and interpret control charts for the mean Construct, use and interpret control charts for attributes Calculate measures of process capability and interpret the results Design and analyze acceptance sampling plans Use statistical software to construct control charts and analyze acceptance sampling plans 62 Content Distribution Week 1 2 3 4 5 6 7 8 9 10 11 12 13 14 Topics Statistical basics for control charts. Rational sub grouping Analysis of patterns of control charts. Uses of control charts Construction and use of sample mean and sample range charts. Sample mean and sample standard deviation charts The operating characteristic function. The average run length for the charts. Individuals charts. Binomial count charts. Construction and use of the p chart for constant and variable subgroup sizes The np charts. Area of opportunity charts. c and u charts Applications and examples Process capability ratios (PCR). Confidence intervals on PCR The relationships between control limits. Natural limits and specification limits. Acceptance sampling by attributes. The operating characteristic curves The single-, double-, and sequential-sampling plans Rectifying inspection. The Average outing quality Acceptance Sampling by Variables. Applications and examples Assessment: Midterm Exams, Final Exam, Assignments, Mini Projects, Lab assignments. References 1- Introduction to Statistical Quality Control. Montgomery, D.C., 6th Edition, 2008, John Wiley and sons, Inc. 2- Quality Control. D. H. Besterfield, 8th edition, 2008, Prentice Hall. 3- Statistical Quality Control. Chandra, M. J, 2001, CRC Press. 63 COLLEGE OF ARTS AND SCIENCES DEPARTMENT OF MATHEMATICS, STATISTICS AND PHYSICS STAT 361 Sampling Methods Course Information Course Title: Sampling Methods Course Number: STAT 361 Credit Hours: 3(2+2) Course Status: Major Compulsory Course Prerequisite: STAT 102 and STAT 211 Course Description Principles of sampling; questionnaire Design; Simple random sampling; Stratified and Cluster Sampling; Ratio and Regression estimation; Systematic Sampling; Multistage and Multiphase Sampling; Determination of the sample Size; Non-response and Non-sampling Errors Adjustment. Course Objectives The course aims are: 1- To familiarize students with the concepts of a finite population, sample, sampling design, estimator and advantages of a sample survey over complete enumeration. 2- To acquaint students with the concepts of simple random sampling, with and without replacement for estimation of population mean, total and proportion. 3- To introduce students to the concepts of stratified, systematic and cluster random sampling for estimation of population total, proportion and mean. 4- To introduce the concept of ratio estimation and regression estimation for estimation of a population total and population mean. 5- To introduce the concept of probability proportional to size with replacement (PPSWR) sampling. 6- To introduce the concepts of multistage sampling, multiphase sampling, non-sampling error and methods for non-response. 64 Learning Outcomes By the end of the course the student will be able to: 1- Design and conduct sample surveys 2- Calculate and interpret estimators obtained from simple random samples, stratified, systematic, cluster and other related samples 3- Calculate and interpret ratio and regression estimators 4- Use the pps sampling design and interpret the results 5- Distinguish nonsampling errors and make necessary adjustments Content Distribution Week 1 2 3 4 5 6 7 8 9 10 11 12 13 14 Topics Finite population. Population parameters. Sample. Sampling design. Estimators. Advantages of sampling. Conducting large scale sample surveys. Sampling with and without replacement Estimation of population total, mean and proportion with their variance estimators Estimation of domain total. Stratified sample Systematic sample and cluster sample Ratio and regression estimators of the population total. MSE of ratio estimators. Bias of estimators. Efficiency. Selection of sample. Estimation of population total and variance. Simple random sampling at both stages. PPSWR-sampling at first stage. Stratified multi-stage sampling. Adjustment for non-response in surveys. Sampling with probability proportional to size Estimation of parameters with PPS sampling Assessment: Midterm Exams, Final Exam, Assignments, Mini Projects. References 1- Sampling Methodologies and Applications. P. Rao, 2000, Chapman and Hall/CRC, Inc. 2- Theory and Methods of Survey Sampling. Parimal Mukhopadhay, 1998, Prentice-Hall of India. 3- Elementary Survey Sampling. R. Scheaffer, W. Mendenhall III and R. Ott, 6th Edition, 2005, Duxbury Press. 65 COLLEGE OF ARTS AND SCIENCES DEPARTMENT of MATHEMATICS, STATISTICS & PHYSICS STAT 371 Statistical Packages Course Information Course Title: Statistical Packages Course Number: STAT 371 Credit Hours: 3 (2+2) Course Status: Major Compulsory Course Prerequisites: STAT 231 Course Description Detailed use and full exploitation of Statistical Packages such as SPSS, MINITAB, R and SAS in working with Data; Topics include Data Entry, checking, manipulation and Analysis. Comparison between the different packages, their advantages and disadvantages. Weeknesses and strengths are discussed. Effective use of Statistical packages in solving real life problems. Advanced features of statistical packages like programming. Course Objectives The course aims are: 1- To study, in detail, the standard statistical packages to students and how to effectively use them. 2- To get knowledge on how to obtain and manipulate the various types of plots and descriptive measures. 3- To familiarize the students with the computations of statistical tables, critical values and other related quantities. 4- To get practice in solving real world problems and interpretation of the results. 5- To get knowledge on how to apply the advanced statistical techniques and how to build models that can be used for statistical inference. 6- To compare between different statistical packages, their advantages, strengths and special features Learning Outcomes By the end of this course, students will be able to: 1- Use effectively some of the most important statistical packages. 2- Manipulate data effectively with various computer packages 66 34567- Produce and manipulate descriptive measures, graphs and other related quantities Obtain certain characteristics of probability distributions Analyze various types of real life data using statistical packages Interpret the output of the data analysis and write reports Perform simulation techniques on some standard distributions Content Distribution Week 1 2 3 4 5 6 7 8 9 10 11 12 13 14 Topics Introduction to Packages, getting started Manipulating data and variables in R, SPSS and SAS Manipulating data and variables in R, SPSS and SAS Producing summary Statistics and graphs Working with Statistical Distributions, plotting their densities and distribution functions Working with Statistical Distributions, calculating probabilities, finding quantiles and critical values Applications Linear Regression and Correlation T – test procedures, one sample, paired samples and independent samples ANOVA techniques and Chi-Square tests Applications Simulation from discrete and continuous distributions Programming in statistical packages, R Programming in statistical packages, SAS Assessment: Midterm Exams, Final Exam, Assignments, Mini Projects, Lab assignments. References 1- SPSS Survival manual J. Pallant, 2nd edition, 2005, Open University Press. 2- Doing data analysis with MINITAB 14 M. Carver, 2nd edition, 2003,Duxbury Press. 3- Using SPSS for Windows Green, Salkind and Akey, 5TH edition, 2007, Prentice Hall. 67 COLLEGE OF ARTS AND SCIENCES DEPARTMENT OF MATHEMATICS, STATISTICS AND PHYSICS STAT 372 Statistical Simulation Course Information Course Title: Statistical Simulation Course Number: STAT 372 Credit Hours: 3(2+2) Course Status: Major Elective Course Prerequisite: STAT 211 Course Description This course covers the basic ideas of statistical simulation including: Generating of Discrete and Continuous Random Variables; Bootstrapping; Variance Reduction Techniques; Model Design and Simulation with Applications Including Queuing and other Applications; Verification and Validation of the Model. Using Statistical software like Minitab, SPSS and R. Course Objectives The course aims are: 1- To acquaint students with methods of generating uniform random numbers. 2- To equip the student with general and special techniques for generating variates from discrete and continuous distributions. 3- To give an introduction to the principles of variance reduction. 4- To introduce the students to some applications of simulation including the simulation of Poisson processes and queuing systems. 5- To acquaint the students with the techniques of Jackknife and Bootstrap for calculating variance estimates and confidence intervals. Learning Outcomes By the end of this course, students will be able to: 1- Generate uniform random numbers manually as well as using the computer. 2- Write and run a variety of computer programs using R-project packages. 3- Recognize and apply different techniques for generating random numbers from discrete and continuous distributions. 4- Identify and use principles of variance reduction techniques. 68 5- Analyze and apply statistical simulation methods in interdisciplinary issues within political, social, economic and statistical modeling. 6- Use different simulation techniques for statistical computations including Jackknife and Bootstrap. 7- Use statistical software for simulation studies. Content Distribution Week 1 2 4 5 6 7 8 9 10 11 12 13 14 Topics Introduction & Motivation Introduction to R Uniform Random Numbers: Linear and multiplicative linear congruential generators. Tests for random numbers. Empirical tests. Shuffling General Methods for Generating Random Variates Inversion of cumulative distribution function Generation of Variates From Some Standard Distributions: Standard normal distribution and the Box-Muller method. Lognormal, Beta, t, Gamma, binomial, negative binomial and Poisson distributions Variance Reduction methods 1: Importance sampling Stratified sampling Variance Reduction methods 2: Control variates index numbers Rejection methods. Adaptive rejection methods Discrete Event Simulation: Poisson processes, Time-Dependent Poisson distributions, Markov chains. Queuing systems. The Jackknife and the Bootstrap. Assessment: Midterm Exams, Final Exam, Assignments, Mini Projects, Lab assignments. References 1. Simulation and the Monte Carlo Method R. Rubinstein and D. Kroese, Second edition, 2008, Wiley 2. Simulation and Monte Carlo J.S. Dagpunar, 2007, Wiley. 3. A Course in Simulation Sheldon Ross, 2002, 3rdedition, Academic Press. 69 COLLEGE OF ARTS AND SCIENCES DEPARTMENT OF MATHEMATICS, STATISTICS AND PHYSICS STAT 381 Categorical Data Analysis Course Information Course Title: Categorical Data Analysis Course Number: STAT 381 Credit Hours: 3(2+2) Course Status: Major Elective Course Prerequisite: STAT 231 Course Description Contingency Tables; Measures of Association; Exact and Asymptotic methods for 2x2 and rxc Contingency Tables; Probit and Logistic Regression Models for Binary Data; Loglinear Models for Multiway Contingency Tables. Statistical software like Minitab, SPSS and R are used. Course Objectives The course aims are: 1- To introduce the most important methods for analyzing categorical data. 2- To familiarize the student with high dimensional contingency tables and the relevant statistical models. 3- To acquaint students with the methods of analyzing logistic and Poisson models. 4- To familiarize the students with the methods of checking the fit of models and how to build suitable models for a given categorical data. Learning Outcomes By the end of this course, students will be able to: 12345- Test hypotheses associated with contingency tables and interpret the results. Calculate certain descriptive measures from contingency tables. Apply logistic regression and log linear models for categorical data and interpret the results Check model adequacy and build relevant models. Use effectively statistical software to analyze and interpret the results. 70 Content Distribution Week 1 2 3 4 5 6 7 8 9 10 11 12 13 14 Topics Basic concepts. Categorical data. Cross-classification tables. Structure of contingency tables Comparing proportions in two way tables. Odds ratio Relative risk, Tests of independence, Exact tests Partial associations. Cochran-Mantel Haneszel methods. Exact inferences for conditional associations Interpreting logistic regression model. Inference for logistic regression. Model checking Logit models, multiple logistic regression and exact inference Log linear models for two way tables. Inferences for Log linear models. Modeling ordinal associations. Testing conditional independence Model fitting and checking Applications and examples Assessment: Midterm Exams, Final Exam, Assignments, Mini Projects, Lab assignments. References 1- An Introduction to Categorical Data Analysis. Alan Agresti, 1st Edition, 1996, John Wiley and sons, Inc. 2- Applied linear regression models. Wasserman, Netter and Kutner, 3rd Edition, 1996, McGraw-Hill. 3- Analysis of Ordinal Categorical Data. Alan Agresti, 1984, John Wiley and sons, Inc. 71 COLLEGE OF ARTS AND SCIENCES DEPARTMENT OF MATHEMATICS, STATISTICS AND PHYSICS STAT 382 Nonparametric Statistics Course Information Course Title: Nonparametric Statistics Course Number: STAT 382 Credit Hours: 3(2+2) Course Status: Major Elective Course Prerequisite: STAT 221 Course Description Basic Concepts of Non-Parametric Methods; Testing and Estimation for one, Two, and Several sample Problems; Independent and Paired; Location and Dispersion Problems; Goodness of Fit Tests; Tests for Trends and Association; Analysis of variance of Ranked Data; Pittman Efficiency of Non-Parametric Methods. Statistical software like Minitab, SPSS and R are used. Course Objectives The course aims are: 123456- To introduce the basic concepts of nonparametric methods. To present students with problems of estimation. To familiarize students with testing of hypotheses for a single sample problem. To acquaint students with testing of hypotheses for a two-sample problem. To acquaint students with testing of hypothesis for c-sample problems. To familiarize students with different tests and measures of association from contingency tables. Learning Outcomes By the end of this course, students will be able to: 123456- Conduct nonparametric tests for single sample problems Conduct nonparametric tests for the two sample problems Conduct nonparametric tests for the multi- sample problems Calculate and interpret several measures of correlation and contingency Calculate nonparametric estimators and confidence intervals for population parameters Use statistical software for nonparametric data analysis 72 Content Distribution Weeks 1 2 3 4 5 6 7 8 9 10 11 12 13 14 Topics Scope of nonparametric methods with respect to parametric methods. Single-sample problem: test of randomness. Test of goodness of fit Tests of location. Sign test. Wilcoxon signed-rank test Hodges-Lehmann estimators, confidence intervals Wald-Wolfwitz Run test. Mann-Whitney-Wilcoxon test Median test. Kolmogorov-Smirnov two-sample test Tests of independence, runs tests Tests for Dispersion Kruskal-Wallis test. Friedman’s test Other multi-sample tests Test of independence. Test for homogeneity Yule’s coefficient of correlation. Pearson’s coefficient of contingency Spearman’s correlation coefficient, Kendall’s tao Efficiency and properties of nonparametric tests Assessment: Midterm Exams, Final Exam, Assignments, Mini Projects, Lab assignments. References 1- Nonparametric Statistical Methods. Myles Hollander and Douglas A. Wolfe, 2nd Edition, 1999, John Wiley and sons, Inc. 2- Applied Nonparametric Statistical Methods. Peter Sprent and Nigel Charles Smelton, 3rd Edition, 2000, CRC Press. 3- Practical Nonparametric Statistics. W. G. Connover, 1999, 3rd Edition, Wiley Europe. 73 COLLEGE OF ARTS AND SCIENCES DEPARTMENT of MATHEMATICS, STATISTICS AND PHYSICS STAT 434 Generalized Linear Models Course Information Course Title: Generalized Linear Models Course Number: STAT 434 Credit Hours: 3 (2+2) Course Status: Major Elective Course Prerequisite: STAT 322 Course Description The Exponential family of distributions, Properties of distributions in the Exponential family, Generalized linear models, Examples, Inference in Generalized Linear Models, Model Adequacy and Diagnostics, The deviance statistic, The residuals, modifications of the residuals and model checks based on the residuals. Special Cases of Generalized Linear Models, Normal theory linear models, Binary logistic regression, Nominal and ordinal logistic regression, Poisson regression and Loglinear models. Statistical software like Minitab, SPSS and R are used. Course Objectives The course aims at: 1- Introducing generalized linear models as a generalization of the normal theory linear models in certain directions 2- Recognizing that many other commonly used models are special cases of generalized linear models 3- Familiarizing the student with the basic theory involved in inference from generalized linear models 4- Introducing model checking techniques suitable to geberalized linear models 5- Developing the skills needed to handle practical situations with generalized linear models.. 6- Stimulating interest to go for advanced studies in generalized linear models. 74 Learning Outcomes By the end of this course, students will be able to: 12345- Identify models that belong to generalized linear models Prove and derive some of the basic results in generalized linear models Perform statistical analysis for various types of data Use computer packages effectively to analyze data from generalized linear models Analyze data using logistic, poisson ordinal logistic and survival regression models and interpret the results 6- Perform model checks and select the suitable model for a given data Content Distribution Week Topics 1 The Exponential family of distributions, Properties of distributions in the Exponential family 2 Generalized linear models 3 Examples 4 Maximum likelihood estimation 5 The score vector and the information matrix 6 Large sample theory of the MLE 7 Large sample tests and intervals in Generalized Linear Models 8 The deviance statistic, The residuals, modifications of the residuals 9 Model checks based on the residuals 10 Normal theory linear models 11 Binary logistic regression 12 Nominal and ordinal logistic regression 13 Poisson regression and Loglinear models 14 Survival regression models Assessment: Midterm Exams, Final Exam, Assignments, Mini Projects, Lab assignments. References 1- Generalized Linear Models Mc Cullagh, P., and Nelder, J., 2nd edition, 1989, Chapman & Hall 2- An Introduction to Generalized Linear Models. Anette Dobson, 3rd edition, 2008, Chapman & Hall 3- An Introduction to Generalized Linear Models. Dunteman and Ho, 1st edition, 2005, Sage Publications 75 COLLEGE OF ARTS AND SCIENCES DEPARTMENT OF MATHEMATICS, STATISTICS AND PHYSICS STAT 442 Actuarial Statistics II Course Information Course Title: Actuarial Statistics II Course Number: STAT 442 Credit Hours: 3 (2+2) Course Status: Program Elective Course Prerequisite: STAT 341 Course Description Construction of Empirical Models, estimation for grouped and modified data, kernel density estimators. Parametric Statistical methods, estimation and confidence intervals in actuarial models. Model Selection, graphical methods, goodness of fit techniques. Credibility theory, Simulation of actuarial models, Case study examples Course Objectives The course aims at: 1- Acquainting the student with methods of inference from complete and grouped data arising from actuarial studies 2- Familiarising the student with likelihood and Bayesian methods in actuarial models 3- Introducing the student to model selection problems 4- Familiarising the student with the credibility theory applied to problems in actuarial statistics 5- Acquainting the student with the techniques of simulating actuarial models Learning Outcomes By the end of this course, students will be able to: 76 1- Conduct statistical inference based on complete, grouped, censored and modified data in the actuarial studies 2- Work with actuarial bivariate models, copulas and models with covariates 3- Check the fit of models used in actuarial science using graphical methods and formal statistical tests 4- Apply the concepts of credibility theory in actuarial problems 5- Simulate actuarial models Content Distribution Week 1 2 3 4 5 6 7 8 9 10 11 12 13 14 Topics Construction of empirical models Point estimation and confidence interval based on complete and grouped data Inference based on modified data Kernel density estimator, approximation for large data sets Likelihood inference based on complete, grouped and censored samples Bayesian inference in actuarial models Estimation in bivariate models, Copulas Models with covariates Graphical methods for model selection Goodness of fit tests, Kolmogorov-Smirnov test, Anderson Darling test, chi-square test and Likelihood ratio test Credibility theory, limited fluctuation credibility theory Greatest accuracy credibility theory, empirical Bayes estimation in actuarial models Simulation of actuarial models Examples and Applications Assessment: Midterm Exams, Final Exam, Assignments, Mini Projects. References 1- Loss Models: From Data to Dicisions Stuart A. Klugman, Harry, H. Panjer and Gordon E. Willmot, 3rd edition, Wiley InterScience. 2- Modern Actuarial Risk Theory Rob Kaas, Marc Goovaerts, Jan Dhaene and Michel Denoit, 2nd edition, Springer. 3- Modern Actuarial Theory and Practice Philip Booth, Robert Chadburn, Steve Haberman and Dewi James, 2nd edition, Chapman and Hall/CRC 77 COLLEGE OF ARTS AND SCIENCES DEPARTMENT OF MATHEMATICS, STATISTICS AND PHYSICS STAT 445 Reliability and Life Testing Course Information Course Title: Reliability and Life Testing Course Number: STAT 445 Credit Hours: 3(2+2) Course Status: Major Elective Course Prerequisite: STAT 322 Course Description Reliability Concepts; Component and System Reliability; Notions of Aging; Lifetime Distributions and Hazard Functions; Types of Censoring; Nonparametric Estimation of Reliability Function; Kaplan-Meier and Nelson Estimators; Parametric Inference Procedures for Exponential, Weibull and Extreme Value Distributions; Proportional Hazards Regression Model; Accelerated Life Testing; Stress-Strength Models. Statistical software like Minitab, SPSS and R are used. Course Objectives The course aims at: 1- Introducing censoring types and situations where censored data occur 2- Acquainting the student with lifetime distribution and the related functions like the reliability function, the hazard function and the mean residual lifetime 3- Describing nonparametric inference with censored data 4- Acquainting the student with Parametric life distributions and the associated inference procedures 5- Describing regression with life data 6- Introducing the proportional hazards model Learning Outcomes By the end of this course, students will be able to: 12345- Analyze data from parametric life time distributions Calculate and plot several characteristics of lifetime distributions Check the goodness of fit based on possibly censored data Conduct nonparametric tests and calculate confidence intervals and estimates Analyze data from parametric regression models 78 6- Conduct nonparametric regression methods and interpret the results 7- Analyze data from accelerated life tests 8- Use statistical software for reliability data analysis Content Distribution Week 1 2 3 4 5 6 7 8 9 10 11 12 13 14 Topics Introduction, types of censoring, examples The reliability function and the related functions Classes of life distributions, system lifetime Parametric families of life distributions Hazard functions, reliability functions and quantiles of specific lifetime distributions Parametric analysis of survival data Applications Nonparametric inference with censored data Goodness of fit tests with censored data Two sample problems Applications Regression with life data The proportional hazards model Accelerated life tests and related topics Assessment: Midterm Exams, Final Exam, Assignments, Mini Projects, Lab assignments. References 1- Lifetime Data: Statistical Models and Methods, Deshpande and Purohit.2006, world scientific publishing company 2- Statistical models and methods for lifetime data analysis J. F. Lawless. 2nd edition, 2002, Wiley. 3- Statistical Methods for Reliability Data W. Meeker and L. Escobar. Wiley, 1998 79 COLLEGE OF ARTS AND SCIENCES DEPARTMENT of MATHEMATICS, STATISTICS AND PHYSICS STAT 464 Environmental Statistics Course Information Course Title: Environmental Statistics Course Number: STAT 464 Credit Hours: 3 (2+2) Course Status: Major Elective Course Prerequisite: STAT 312 and STAT 361 Course Description Stochastic processes in the Environment. Fitting probability models to Environmental data. Tail Exponential Method. Poisson Processes and its application. Negative binomial model (Contagion and True Models). Capture-Recapture Method, Distance Sampling, Composite sampling, Introduction of Rank Set sampling methods, adaptive cluster sampling and adaptive allocation methods. Course Objectives The course aims are: 1- To learn some statistical methods in Environmental Sciences. 2- To see the application of Statistics in Environmental and Ecological Sciences. 3- To train students who are familiar with some environmental statistics methods and have potential to collaborate with Environmentalists. Learning Outcomes By the end of this course, students will be able to: 1- Fit statistical models to data from the environmental science. 2- Use some statistical techniques and models like the tail exponential method, the Poisson process, the negative binomial model. 3- Calculate and apply certain types of distance measures 4- Apply and analyze the results from line transect sampling 5- Apply and analyze the results from ranked set sampling 6- Use adaptive cluster samples and adaptive allocation methods 80 Content Distribution Week 1 2 3 4 5 6 7 8 9 10 11 12 13 14 Topics Introduction to remote senses and Stochastic processes in the Environment. Fitting probability models to Environmental data. Tail Exponential method Poisson Processes and its application. Negative binomial models (Contagion and True Models). Capture-Recapture: Peterson Method and sample size estimation. Schnabel method Confidence interval. Jolly-Seber Method. A catchability test Distance sampling: Methods for spatial Maps. Nearest-Neighbor distance Method Distances to second to the nth Nearest Neighbors Indices of dispersion for Quadrat counts and distance measures Line transect sampling and detection function. Composite sampling: Classification, Extreme values Estimating of prevalence. Cost functions Rank set Sampling: Introduction of Rank Set sampling methods and its application in Ecological problems, Adaptive sampling: adaptive cluster sampling Adaptive allocation methods. Assessment: Midterm Exams, Final Exam, Assignments, Mini Projects. References 1- Environmental Statistics and Data Analysis Wayne R. Ott, 1995, CRC Press. 2- Ecological Methodology. Krebs, C.J. 1999, 2nd edition, Benjamin Cummings. 3- Estimation of Animal Abundance. Seber GAF, 2002, 2nd. Edward Arnold: London. 81 COLLEGE OF ARTS AND SCIENCES DEPARTMENT OF MATHEMATICS, STATISTICS AND PHYSICS STAT 481 Multivariate Analysis Course Information Course Title: Multivariate Analysis Course Number: STAT 481 Credit Hours: 3 (2+2) Course Status: Program Compulsory Course Prerequisite: STAT 322 and MATH 231 Course Description The course discusses the analysis of multivariate data. Multivariate distributions and inference about means are considered. Techniques like principal components, factor, cluster and discriminant analyses were studied with examples. The use of computer packages is emphasized in this course. Real life data are often used to illustrate the power and applicability of multivariate methods. Statistical software like Minitab, SPSS and R are used. Course Objectives The course aims at: 12345- Enabling the students to organize multivariate data into an array and calculate its mean vector, covariance matrix, and generalized variance. Introducing the students to Multivariate Normal (MN) distribution and distribution of sample mean and covariance from an MN distribution and the associated inferences. Helping students acquire knowledge of principal components analysis (PCA) and Factor Analysis (FA). Introducing the elements of discriminant anlaysis and canonical correlation. Familiarizing the students with the concepts of cluster analysis and multidimensional scaling. Learning Outcomes By the end of this course, students will be able to: 1- Calculate statistical quantities like the multivariate mean, covariance matrix and the generalized variance. 2- Test hypotheses about the parameters of the multivariate normal distribution. 3- Compare several multivariate normal mean. 82 4567- Perform principal component analyses and factor analyses. Apply the techniques of canonical correlation and discriminant analysis. Apply the techniques of cluster analysis and multidimensional scaling. Use statistical software for multivariate data analysis Content Distribution Week 1 2 3 4 5 6 7 8 9 10 11 12 13 14 Topics Multivariate Data: Summary Statistics Multivariate Data: Plots The Multivariate Normal Distribution Inference about Single multivariate means Inference about paired and independent multivariate means One way Multivariate analysis of variance Two way Multivariate analysis of variance Examples and Discussion Principal Components Analysis Factor Analysis Discriminant analysis Canonical Correlation Cluster Analysis Examples Assessment: Midterm Exams, Final Exam, Assignments, Mini Projects, Lab assignments. References 4- Applied Multivariate Statistical Analysis Richard A. Johnson and Dean W. Wichern, 6th edition, 2007, Prentice Hall. 5- Multivariate Statistical Methods: A Primer Bryan Manly, 3rd edition, 2004, Chapman & Hall/CRC. 3- Methods of Multivariate Analysis A. C. Rencher, 2nd edition, 2002, John Wiley and sons, Inc. 83 COLLEGE OF ARTS AND SCIENCES DEPARTMENT of MATHEMATICS, STATISTICS AND PHYSICS STAT 482 Bayesian Statistics Course Information Course Title: Bayesian Statistics Course Number: STAT 482 Credit Hours: 3 (2+2) Course Status: Major Elective Course Prerequisite: STAT 322 Course Description Nature of Bayesian Statistics, Prior and posterior distributions. Noninformative priors. Jeffereys rule. Conjugate priors. Bayesian Inference, Quadratic loss function and Bayes estimators, Highest posterior density intervals, Bayesian tests of hypothesis. Bayesian methods in the normal and some other distributions. Approximate Bayesian Methods, Asymptotic approximations of the Bayes estimator, The Lindley and Tierney-Kadane methods, Markov chain Monte Carlo methods and the Gibbs sampler. Course Objectives The course aims are: 1- To introduce the basic concepts and principles of Bayesian inference. 2- To give the students some standard normal theory results from a Bayesian perspective and to contrast them with the classical approach to inference. 3- To Acquaint students with methods of developing Bayesian inference procedures. 4- To introduce the students to the approximations usually used in Bayesian inference to solve the high dimensional integrations usually faced in Bayesian methodology. Learning Outcomes By the end of this course, students will be able to: 1- Construct and find suitable non informative and conjugate prior distributions 2- Calculate Bayes estimator and Bayes intervals, in particular, the highest posterior density intervals 3- Apply Bayesian methodology to some standards problems like the one and two sample normal theory situations 84 4- Use asymptotic approximations to Bayesian Estimators like Tierney Kadane and Laplace methods 5- Apply Markov chain Monte Carlo methods and Gibbs sampler techniques of computer intensive Bayesian calculations Content Distribution Week 1 2 Topics Probability and Bayes theorem, Examples on Bayes theorem. Parameters as random variables. Prior distributions 3 4 5 Noninformative priors. Jeffereys rule. Conjugate priors Posterior distributions Quadratic loss function and Bayes estimators 6 7 Highest posterior density intervals Bayesian tests of hypothesis 8 9 10 11 12 The normal one and two-sample location problems The Behrens-Fisher problem. The variance and ratio of variances Asymptotic approximations of the Bayes estimator The Lindley and Tierney-Kadane methods Markov chain Monte Carlo methods 13 14 Gibbs sampler Applications Assessment: Midterm Exams, Final Exam, Assignments, Quizzes. References 1- Bayesian Statistics: An Introduction. Peter M. Lee, 3rd Edition, 2004, Arnold. 2- Introduction to Bayesian Statistics. Bolstad, 2nd Edition, 2007, Wiley 3- Bayesian Data Analysis. Carlin, Stern and Rubin, 2nd edition, 2003, Chapman and Hall/CRC 85 COLLEGE OF ARTS AND SCIENCES DEPARTMENT OF MATHEMATICS, STATISTICS AND PHYSICS STAT 499 Graduation Project Course Information Course Title: Graduation Project Course Number: STAT 499 Credit Hours: 3 Course Status: Major Compulsory Course Prerequisite: Approval of the Department Head Course Description This project is a final project in which graduating students demonstrate their ability to design questionnaires, conduct surveys and/or retrieve information from the internet, analyze the collected data using various techniques, interpret the results, present what they have accomplished to an audience in a concise manner and reflect on their experience. The Graduation Project provides students the opportunity to relate content knowledge and acquired skills to real world situations and issues. Course Objectives The course aims at: 1- Introducing the student to the field of working with real data 2- Familiarizing the student with the methods of collecting real data and the difficulties associated with them 3- Acquainting the student with the methodology of model building and data analysis 4- Training the student on how to interpret the results of real life studies 5- Familiarizing the student with the general methodology of research and the reporting of results 6- Training the student on oral presentation of his findings Learning Outcomes By the end of this course, students will be able to: 1- Formulate a data analysis problem in a statistical framework. 2- Use perfectly at least one statistical software package to analyze data. 86 3- Use a variety of methods for exploring, summarizing and presenting data. 4- Apply statistical models and methods to solve practical problems. 5- Interpret the results of a statistical analysis. 6- Comment critically on choices of model and method of analysis. 7- Communicate the results of statistical investigations and data analyses, using a form, structure and style that suit the purpose. 87