|
|
|
||
This course extends the foundations of linear regression. It covers regression models for non-normal data and
discrete responses. The practice sessions combine theoretical and practical exercises with main focus on
analyses of various types of econometric, financial and technical data. The course includes a final project.
Last update: Branda Martin, doc. RNDr., Ph.D. (11.12.2020)
|
|
||
To explain regression models for non-normal data. Last update: Kulich Michal, doc. Mgr., Ph.D. (11.12.2020)
|
|
||
Tutorial credit requirements:
Three homework assignments will be given during the semester. Each homework solution will be assessed as one of the following: Satisfactory (worth 2 points), Borderline satisfactory (worth 1 point), Unsatisfactory (0 points). Only students who get in total at least 5 points will get the course credit. It is possible to correct one borderline satisfactory report. An unsatisfactory report cannot be corrected.
The nature of these requirements precludes any possibility of additional attempts to obtain the tutorial credit. The tutorial credit is necessary to sign up for the exam. Last update: Kulich Michal, doc. Mgr., Ph.D. (10.02.2025)
|
|
||
J.W. Hardin and J.M. Hilbe: Generalized Linear Model and Extensions. StataPress, 2007. A. Agresti: Categorical Data Analysis. Wiley, 1990. Last update: Kulich Michal, doc. Mgr., Ph.D. (11.12.2020)
|
|
||
Lecture + exercises. Last update: Zichová Jitka, RNDr., Dr. (20.05.2022)
|
|
||
The exam has two parts: (1) Evaluation of applied project report and (2) Theoretical oral part. To pass the exam, both parts need to be passed.
Requirements for the exam comprise the entire contents of the lectures and exercise sessions. Last update: Kulich Michal, doc. Mgr., Ph.D. (11.12.2020)
|
|
||
1. Generalized linear model 2. Binary response regression 3. Loglinear model 4. Extensions of generalized linear model, quasilikelihood, sandwich estimator of variance Last update: Kulich Michal, doc. Mgr., Ph.D. (11.12.2020)
|
|
||
This course assumes mid-level knowledge of linear regression (both theory and applications) and good understanding of maximum likelihood theory. Last update: Kulich Michal, doc. Mgr., Ph.D. (11.12.2020)
|