HU Credits:
6
Degree/Cycle:
1st degree (Bachelor)
Responsible Department:
Statistics
Semester:
2nd Semester
Teaching Languages:
Hebrew
Campus:
Mt. Scopus
Course/Module Coordinator:
Dr. Asaf Weinstein
Coordinator Office Hours:
Tuesdays 17:00-18:00
Teaching Staff:
Dr. Asaf Weinstein, Mr.
Course/Module description:
1. Simple and multiple linear regression
2. Analysis of variance
3. Logistic regression
4.Poisson regression
Course/Module aims:
To build foundations for statistical inference in some basic linear models
Learning outcomes - On successful completion of this module, students should be able to:
1. Understand the theory behind the methods studied
2. Apply the methods studied in the lectures
3. Understand analyses that use the methods studied in the lectures
Attendance requirements(%):
None
Teaching arrangement and method of instruction:
The instructor will make parallel use of slides and writing on the blackboard. There will be many examples of computer outputs (data sets, results of statistical analyses, etc.) which will be also available through the course's website.
Course/Module Content:
1. Introduction and simple linear regression for a single predictor
2. Multiple linear regression. The Least Squares estimator, its mathematical properties and geometric interpretation. Projections.
3. Probabilistic background. Expectation and covariance matrix of a random vector, the multivariate normal distribution, multivariate Central Limit theorems.
4. Statistical inference in multivariate linear regression. Expectation and covariance matrix for the Least Squares estimator, estimating the covariance of errors, the Gauss-Markov theorem, inference for a single coefficient and for a linear combination under normality assumptions.
5. Practical aspects and model diagnostics. Examination of residuals, multicollinearity, evaluating the influence of points.
6. Model building in multiple linear regression. Preliminary examination, dummy variables, interactions, transformations, variable selection, goodness-of-fit metrics
7. F tests for comparing between models
8. One-way and two-way analysis of variance (ANOVA)
9. Generalized linear models. Regression with a continuous response and a nonlinear link function, logistic regression for binary response, Poisson regression for count data.
10. Random-effects models.
11. Selected topics (if time permits): controlled variable selection, post-selection inference.
Required Reading:
Required reading material will be posted on the course website over the course of the semester
Additional Reading Material:
Additional recommended reading material will be posted on the course website over the course of the semester
Course/Module evaluation:
End of year written/oral examination 65 %
Presentation 0 %
Participation in Tutorials 0 %
Project work 0 %
Assignments 15 %
Reports 0 %
Research project 0 %
Quizzes 20 %
Other 0 %
Additional information:
**Passing the final exam is a requirement for passing the course**
Course requirements:
1. Final exam (standard format). If only remote learning is practiced at the time of the exam, the exam will be taken from home.
2. Homework. Exercises for submission will be assigned weekly. Submitting in pairs is allowed (even encouraged). Homework will be graded acceptable/unacceptable, where “acceptable” means work that has been handed in on time, presented neatly, and demonstrates a serious effort to solve the problems. The overall grade for homework will be the percentage of acceptable assignments among all assignments. It should be emphasized that homework is an integral---and perhaps the most important---part of the course, and that problem solving is essential for assimilation of the material.
3. Quizzes. Two at-home quizzes will be held during the semester. The quizzes will be graded in full and graded in the standard way. Submitting in pairs is allowed here as well.
|