Venue: Online

First Meeting: 10th January at 11:00 AM

Class Timings: Tuesday and Thursday 7:00 PM -  9:00 PM

Course Description: 

Week 1: Review of Estimation, Hypothesis Testing
Week 2:  Review of working with R-package
Week 3:  Least square estimation, estimable linear functions
Week 4:  Normal equations
Week 5:  Best Linear Unbiased Estimates (BLUEs).
Week 6:  Gauss-Markov Theorem
Week 7:  Degrees of freedom. Fundamental Theorems of Least Square.
Week 8:  Testing of linear hypotheses.
Week 9: One-way and two-way classification models
Week 10: ANOVA and ANCOVA.
Week 11: Nested models. Multiple comparisons
Week 12: Introduction to random effect models


1. Plane Answers to Complex Questions The Theory of Linear Models, Springer by R. Christensen.

2. Linear Statistical Inference by C. R. Rao.

Evaluation: Weekly Worksheets, Homework Assignments and Quizzes will be given. Students must install R, Rstudio. It would be ideal (but not necessary) if students install latex, pandoc and be prepared to work with RNW files, RMD files.

Prerequisites: Basic Probability Theory, R-Programming (good to have).

Outcome: To introduce linear statistical models and their applications in estimation and testing. The course will illustrate concepts with specific examples, data sets and numerical exercises using statistical package R.

Credit Score: 4