STAT4102 Schedule
Part 1: Basic Ideas
The goal of statistics is to make some claim about an entire population using the data from some representative part of that population, or sample. There are three major ways of making this sort of claim: likelihood, asymptotics, and Bayesian ideas. In the first part of this course, we'll learn the basic concepts of each and use them to find a single point estimate of a given population parameter. We'll also study ways of evaluating and comparing these different kinds of estimates.Date | Topic | |
Wed. Jan 17 | Overview of Course
Random Sampling (8.1) | |
Fri. Jan 19 | Likelihood (8.2) | |
Mon. Jan 22 | Sufficiency (8.3) | |
Wed. Jan 24 | Sampling Distribution (8.4) Moments of Sample Means (8.7, 9.2) | |
Fri. Jan 26 | Central Limit Theorem (8.8) | |
Mon. Jan 29 | Central Limit Theorem (8.9) Normal Population Results (8.10) | |
Wed. Jan 31 | The Bayesian Approach (8.11-8.12) | |
Fri. Feb 2 | Estimation (9.10-9.11) | |
Mon. Feb 5 | Mean Squared Error (9.1) | |
Wed. Feb 7 | Consistency (9.3) | |
Fri. Feb 9 | Efficiency (9.12 through Example 9.12b) | |
Mon. Feb 12 | Review | |
Wed. Feb 14 | Exam |
Part 2: Inference
Having a single point estimate of a population parameter is nice, but because it's random, it's useless unless we have a way of measuring the uncertainty in our estimation. Also, how can we best make a decision based on that estimate? This part of the course studies how to measure that uncertainty and use it to make decisions.Fri. Feb 16 | Confidence Intervals (9.4) | |
Mon. Feb 19 | Confidence Intervals, small samples (9.5-9.6) | |
Wed. Feb 21 | Pivots (9.7) CI's for Mean Difference and Variance (9.8-9.9) | |
Fri. Feb 23 | Exam Review | |
Mon. Feb 26 | Exam Review | |
Wed. Feb 28 | Confidence Intervals for Binomials | |
Fri. Mar 2 | No class - Snowed in! | |
Mon. Mar 5 | Hypothesis Testing and p-values (10.1-10.2) | |
Wed. Mar 7 | One Sample Z and T tests (10.3-10.4) | |
Fri. Mar 9 | Nonparametric Tests (10.5) |
Mon. Mar 19 | Type I and Type II Errors, Power (11.1) | |
Wed. Mar 21 | Power and Sample Size (11.2-11.3) | |
Fri. Mar 23 | Most Powerful Tests (11.5) | |
Mon. Mar 26 | Most Powerful Tests, continued (11.6-11.7) | |
Wed. Mar 28 | Likelihood Ratio Test (11.8) | |
Fri. Mar 30 | Bayesian Decisions (11.9) | |
Mon. April 2 | Review, Take-home exam passed out | |
Wed. April 4 | No class
Office hour for any exam questions | |
Fri. Apr 6 | Exam due by start of class
Two kinds of two populations (12.1, 12.6) |
Part 3: Application
The final part of the course applies these concepts to situations with two or more populations (discrete predictors, continuous response), categorical data (discrete predictors and response), and regression (continuous predictors and response).Mon. Apr 9 | Two population tests (12.2-12.4) | |
Wed. Apr 11 | Nonparametric two population tests (12.5) | |
Fri. Apr 13 | F and Variance tests (12.7-12.8) | |
Mon. Apr. 16 | Categorical tests, Chi-squared test (13.1-13.2) | |
Wed. Apr 18 | As a likelihood ratio test (13.6) | |
Fri. Apr. 20 | Testing Independence and Homogeneity (13.5, 13.7) | |
Mon. Apr. 23 | ANOVA in practice (14.1) | |
Wed. Apr. 25 | ANOVA in theory (14.2) | |
Fri. Apr. 27 | Multiple comparisons (14.3) | |
Mon. Apr. 30 | Regression (15.1-15.2) | |
Wed. May 2 | Inference for Regression (15.3-15.4) | |
Fri. May 4 | Regression Effect (15.8) |
Final
Wed. May 9 | Final Exam, 1:30-3:30pm |