CEE 3030 ● Uncertainty in Engineering Analysis ● ● ● ● ● Instructor Lectures Classroom Textbook Notes Gilberto E. Urroz MW 3:30-4:20 pm ENGR ... Spiegel et. al. “PROBABILITY AND STATISTICS, Schaum, McGraw-Hill” See course web site ABET Outcomes for CEE 3030 (1) Upon successful completion of undergraduate program for CE at USU, students will have: ● ● http://www.engineering.usu.edu/cee/faculty/gurro Click on Classes, then on CEE 3030 ABET Outcomes for CEE 3030 (2) Upon successful completion of undergraduate program for CE at USU, students will have: ● Outcome 3 – Shown a capacity for investigation and experimentation into physical (engineering) phenomena along with the ability to analyze and interpret engineering data ... Outcome 1 – Proven themselves proficient in mathematics, the sciences, ... Outcome 2 – Demonstrated the ability to solve engineering problems, utilizing fundamental engineering principles as well as the latest technologies and engineering tools, in the process of engineering analysis and design. .... Class Contents (1) 1 – Introduction 2 – Probability 3 – Random variables 4 – Probability distributions 5 – Samples, frequency distributions, graphs 6 – Sampling distributions 7 – Interval estimation 8 – Regression techniques Assignments, exams, grading Tools ● ● Assignments: 60% of grade ● Exams: 40% of grade MAPLE 10 – – – ● – Two tests (50 minutes, each): 10% of grade, each – Final exam (110 minutes): 20% of grade Calculators – – ● Mathematics software with statistics package Point-and-click mathematics Relatively easy to use Hp 49g+ TI 89 Titanium Spreadsheets – – Excel (MS Office) Calc (Open Office) Uncertainty in Engineering Analysis – An Introduction (1) ● Probability and statistics for engineers ● Knowledge needed: – – – Algebra Univariate calculus Multivariate calculus Types of systems ● Systems – e.g., pipe flow Well-defined input and well-known system response →DETERMINISTIC p 8 LQ 2 4Q ⋅f , = g D5 D D Examples from Civil Engineering 1 ● – – ● If uncertainty exists in input or response →STOCASTIC Examples from Civil Engineering 2 ● Water engineering – Transportation engineering – – Statistics of transportation systems Modeling of transportation systems Examples from Environmental Engineering ● Turbulence – time uncertainty ● Hydrology ● ● ● – Statistics of soil samples Earthquakes (probability of liquefaction) Uncertainties in water quality in rivers and lakes Hydraulics and fluid mechanics ● – Earthquakes (accelerations, structural responses) Samples of concrete quality Geotechnical engineering – – ● ● Structural engineering Statistics of weather quantities (precipitation) Prediction of runoff Probability of flooding/period of return Groundwater ● ● ● Uncertainties in groundwater supply Variations in aquifer properties Statistics of groundwater contamination Uncertainties in location of contamination sources (non-point source pollution) ● Statistical analysis of water and air quality ● Modeling of environmental contamination ● Statistics of animal and fish habitat Random variables Statistics ● Variables associated with uncertainties ● ● Examples: ● – Precipitation in a basin – Number of cars per unit time in highway ramp – Strength of concrete cylinders Science and technology of data analysis (rough definition) Statistical techniques: – – – ● Processing large amounts of data Reducing data to measures and graphs Reduced data can be used for decision making Statistical techniques originated from – City government needs ● ● – Probability ● What is probability? – – ● ● – Intensity of earthquakes Number between 0 and 1 Provides estimate of how likely an event is to occur Probability theory: science of prediction of random systems (rough definition) Probability theory originated to understand the outcome of games of chance Population, samples, inference Taxation Health Services Napoleonic wars ● Casualties Statistical inference (1) ● ● ● ● Population: all possible values of measurement or collection of all individuals of interest in a study Sample: sub-set of a population used to obtain statistical measures Statistical inference: use samples to make inferences on population Techniques of statistical inference: – – – Estimation Hypothesis testing Regression Random samples ● Each element selected with the same probability or likelihood ● Is representative of a population ● Biased sample: not representative of population Sample space and events ● ● ● Sample space (Ω): set of all possible outcomes of an experiment Events (A, B, ...): subsets of the sample space. Example: casting a die Ω = {1, 2, 3, 4, 5, 6}, A = {2, 4, 6}, B = {1, 3, 5} Events are also sets: ● ● Venn diagrams 2 ∈ A, 3 ∉ A A ⊂ Ω, B ⊂ Ω, A ⊄ B Sets and set operations Ω = universal set , ∅ = empty set = {} A ⊂ Ω, B ⊂ Ω, ... ∅ ⊂ A, ∅ ⊂ A, ... Operations: – Complement: A' = {elements not in A} – Union: A ∪ B = {elements in A or B} Intersection: A ∩ B = {elements in A and B} A∪Ω=Ω, A∩Ω= A, A∪∅ = A A∩∅=∅, A∪A'= Ω, A∩A'=∅ By definition: ∅ ' = Ω, Ω' = ∅ – (A∪ B)' = A' ∩ B'