Biostatistics 310 – Biostatistics for the Health Sciences
Winter 2014
Prerequisites: College algebra (MATH 111) or higher
Credits: 4, graded
Structure: 3 lectures/week (50 min); 1 discussion section/week (50 min)
Time slot:
Lecture: 2:30 – 3:20 MWF, T639
Discussion: W 3:30 – 4:20, E216
Th 10:30 – 11:20, T531
Th 2:30 – 3:20, T663
Fr 1:30 – 2:20, T635
Instructor:
Jim Hughes, Professor of Biostatistics
H655F, Health Sciences Building
206-616-2721
jphughes@uw.edu
Office Hours:
8:30 – 10:30 F
or by appt.
TAs:
Joo Yoon Han
Office Hours:
Erika Thommes
Office Hours:
H655F, HSB
jooyoon@uw.edu
9:00 – 10:00 M
3:30 – 4:30 M
ethommes@uw.edu
8:30 – 10:30 T
TA office hours will be held in the Health Sciences library, near the computer classrooms
Course Description: The objective of this biostatistics course is to provide students with an
understanding of basic concepts of data analysis and statistical inference in the medical and health
sciences. The major areas covered are:





Data Description and Exploratory Data Analysis used in health-related journals
Design of Medical and Health Studies
Screening Tests for Disease
Role of statistical inference in public health and medical studies
Statistical methods for evaluating the association of factors with health outcomes
The course will make extensive use of case studies and examples drawn from the biomedical and
health sciences literature; many of these examples will have been covered in the popular press and
may be familiar to students. Each case study will be used to motivate learning basic statistical ideas
in the areas outlined above. Presentation of concepts will be emphasized and students will not be
expected to do extensive analyses of data themselves.
Learning Objectives: Upon completion of the course, students should be able to …
 Interpret graphical displays and numerical summaries for both quantitative and
categorical data that are relevant to medical and health sciences studies
 Interpret key measures of bivariate association (e.g. correlation, relative risk, odds
ratio, risk difference) for relating factors to health outcomes
 Explain the difference between observational and experimental studies such as clinical
trials
 Explain the difference between random and opportunistic sampling for health surveys












Identify and describe study designs that are commonly used in medical and health
studies, including designed experiments, surveys, cohort studies, and case-control
studies
Identify potential sources of bias and variability associated with a given study design
Explain the difference between a sample and a population
Recognize and explain the concepts of confounding and effect modification and how
they effect our ability to determine causes of disease and measure the effectiveness of
interventions to improve health
Define sensitivity, specificity and predictive values in the context of a screening test for
a disease
Explain the logic of hypothesis testing and interpret p-values
Translate medical/health questions into appropriate null and alternative hypotheses
Explain and interpret confidence intervals
Be able to choose an appropriate statistical test (e.g. z-test, t-test, chi-square test) to
compare two samples and describe the assumptions underlying the use of these tests
Describe the assumptions underlying simple linear regression and be able to interpret a
regression model in the context of health outcomes.
Use simple linear regression model to make predictions
Critique the use of statistical methods in medical and health studies
Textbook: Sullivan, L. Essentials of biostatistics for the health sciences.
On Reserve (HSL):
Machin, Campbell and Walters (2007) Medical Statistics, 4th ed., Wiley.
 This was the primary text last year
Motulsky, H. Intuitive Biostatistics: A nonmathematical guide to statistical thinking.
 Good nonmathematical/noncompeting text on statistics but doesn’t cover all
the topics we need for biostatistics
Utts, J and Heckard, R. Mind on statistics.
 Another good introductory text, but a bit too much computing.
Web site: Homework assignments and other course materials will be posted on the course website
on Canvas (canvas.uw.edu).
Lecture Notes: Copies of the lecture notes (“coursepak”) may be purchased at the South Campus
Center Bookstore. The notes are also posted on the website.
Handouts: Extra copies of course handouts can be found on the website.
Discussion Board: A discussion board is available through the Canvas website. Any student in the
class may post to this board. The TAs and Prof. Hughes will monitor the discussions.
Online Quizzes: Students will be required to complete an online (catalyst) quiz each week (see the
modules section of the course webpage). These will be primarily computational in nature with
multiple choice answers. The goal of these quizzes is to increase your understanding of and comfort
with statistics and data by doing simple hand calculations. These quizzes will be graded
credit/nocredit. To receive credit you must complete all problems correctly but you can repeat the
quiz if you don’t get all the questions right the first time.
Homework: Homework assignments will (typically) be posted on the Canvas website on Wed. and
due the following Wed. by 2:30pm. In contrast to the quizzes, the homework problems will involve
more critical thinking and short answer responses. The homework assignments should be completed
in a Word or .pdf format document and submitted electronically to the Canvas website by the due
date. The TA’s will grade these and provide feedback. Late homework will not be accepted.
You may discuss the homework problems with fellow students (I encourage it) but the final version
you hand in should reflect your own interpretation and understanding. Copied assignments will
not receive credit.
Homeworks will be graded on the following scale: 0 = assignment not handed in; 2 = assignment
incomplete or showing little effort; 4 = reasonable effort on all questions; 5 = reasonable effort on
all questions and superior effort/ insight on at least some questions. I will discard your lowest
homework score in computing grades.
Exams: There will be two 50 minute mid-terms and a final exam (see schedule for dates). Exams
will be open book and you can bring one page (2-sides) of notes to each midterm and three pages to
the final. The exams will require no more than basic arithmetic that you can do in your head or on
scratch paper. If you are not comfortable with that, then it is okay to bring a calculator but it can’t
be a cell-phone or wireless device. Use of any electronic device with communication ability is not
allowed during exams.
Discussion Section: Discussion sections will consist of activities, problem sets or discussion of
articles. For each discussion class you will be required to hand in a brief assignment at the end of
class. Your participation grade will be based on completion of these assignments.
Disability: If you would like to request academic accommodations due to a disability,
please contact Disability Resources for Students, 448 Schmitz, 543-8924 (V/TDD). If you
have a letter from Disability Resources for Students indicating you have a disability that
requires academic accommodations, please present the letter to me so we can discuss the
accommodations you might need for class.
Grading: Numerical grades will be based on the following:
Midterm I:
Midterm II:
Final:
Online Quizzes:
Homework
Discussion section participation
20%
20%
20%
15%
15%
10%
Final course grades will be based on a curve approximately following the guidelines at
http://depts.washington.edu/grading/practices/guidelines.html
If you have questions or concerns regarding the content or structure of the class, please feel
free to talk (or write) to us at any time during the quarter. To the extent that you are not
satisfied with our response, you may contact the Biostatistics Department Chair
(bsweir@uw.edu). If concerns are still not satisfactorily resolved, you may also contact the
Graduate School at G1 Communications Building by phone at (206) 543-5139 or by
email at raan@uw.edu.
Date
Jan 6
Jan 8
Jan 10
Topic
Intro
Descriptive Stats for Quant. Data
Descriptive Stats for Quant. Data
Reading*
1.1 – 1.2
4.0,4.3
4.0,4.3
Discussion
Jan 13
Jan 15
Jan 17
Incidence, RR, RD
Sampling
Tables, prevalence, RR, RD, OR
3.1 – 3.4
5.1
4.1 – 4.2
Graphs &
Tables
Jan 20
Jan 22
Jan 24
HOLIDAY
Study Design
Study Design
2.1 – 2.5
2.1 – 2.5
Critiquing
a
Study
Jan 27
Jan 29
Jan 31
Probability & Screening
Probability & Screening
MIDTERM
5.2 – 5.5
5.2 – 5.5
Q&A
Feb 3
Feb 5
Feb 7
Binomial
Normal
Sampling distributions
5.6.1
5.6.2
5.6.3
Feb 10
Feb 12
Feb 14
CI
Hypothesis Test Intro
Chisquare Test
6.1 – 6.3
7.1
7.9
Randomization
Test
Feb 17
Feb 19
Feb 21
HOLIDAY
T-test
Hypothesis Test Issues
7.2,7.5 – 7.6
CMW 15.6
Q&A
Feb 24
Feb 26
Feb 28
MIDTERM
Hypothesis Test Issues
Correlation
8.1 – 8.2
9.3
Foods &
Cancer Risk
Mar 3
Mar 5
Mar 7
Regression
Multiple Regression
Regression to the Mean
9.3
9.4
CMW 15.3
ROC curves
Mar 10
Mar 12
Mar 14
Logistic Regression
9.5
Life tables and Survival Analysis
11.1 – 11.2
Why Most Published Research Findings are False
Mar 18
Final Exam, 2:30 – 4:20, location tba
Sampling
Variability
Calculations/
Z-scores
Q&A
* Readings from Sullivan, except CMW = Campbell, Machin, Walters (on reserve)