廣義線性模型

This is an introductory course on the generalized linear model (GLM). In this course, some previous background in maximum likelihood estimation for linear regression is first covered in sufficient detail. Secondly, we give a thorough treatment of logistic and Poisson regression. Thirdly, we provide an introduction to generalized estimating equations (GEEs), which is a topic closely related to GLM. Finally, we provide an introduction to the generalized linear mixed model (GLMM). Both GEEs and GLMMs are of increasing importance to many practitioners. Important application areas include biology, to analyze longitudinal data, and the physical sciences and engineering, to analyze correlated observations.

None

Please download the textbook pdf file from the NCTU library. The projector and the blackboard will be used for this course.

作業部份: None 考試部份: It is required for every student to present a published paper from the References of the textbook by the Friday of the 18th week. The presentation time should be between 30 minutes and 1 hour for each master student, and between 1 hour and 2 hours for each Ph.D. student. Q&A (Questions and Answers) will be about 15 minutes for each master student and about 30 minutes for each Ph.D. student. 評量部份: 1. Attendance at the class. 2. Presentation of a published paper from the References of the textbook by the Friday of the 18th week.

• 1. Introduction to Generalized Linear Models
• 2. Linear Regression Models
• 4. Logistic and Poisson Regression Models
• 5. The Generalized Linear Model
• 6. Generalized Estimating Equations
• 7. Random Effects in Generalized Linear Models

Myers, R. H., Montgomery, D. C., Vining, G. G., and Robinson, T. J. (2010). Generalized Linear Models with Applications in Engineering and the Sciences, 2nd Edition. John Wiley & Sons, Inc., Hoboken, New Jersey.

地點

A416

時間

Every Tuesday from 1:20 p.m. to 4:20 p.m.

聯絡方式

E-mail address: cchen@stat.nctu.edu.tw Office phone number: (03) 571-2121 Ext. 31794 or (03) 573-1794