# 106年第1學期-6192 類別資料分析 課程資訊

## 評分方式

Homework assignments 20
Midterm, Quizzes, or Projects 55
Final 25

## 教育目標

Introducing advanced statistical models and theories for categorical data used by statistical researchers and practitioners.1. Introduction: Distributions and Inference for Categorical Data 2. Describing Contingency Tables 3. Inference for Contingency Tables 4. Introduction to Generalized Linear Models 5. Logistic Regression 6. Building,Checking, and Applying Logistic Regression Models 7. Alternative Mideling of Binary Response Data 8. Models for Multinomial Responses 9. Loglinear Models for Contingency Tables 10. Building and Extending Loglinear Models 11. Models for Matched Pairs 12. Cluster Categorical Data: Marginal and Transitional Models 13. Cluster Categorical Data: Random Effect Models 14. Other Mixture Models for Discrete Data 15. Non-Model-Based Classification and Clustering 16. Large- and Small Sample Theory for Multinomial Models 17. Historical Tour of Categorical Data Analysis. In this semester, we may include some topics related to Data Mining such as Decision Trees, Bagging, Random Forests, and/or Boosting.

## 課程概述

Objective: Introducing statistical models for categorical data used by statistical researchers and practitioners. Prerequisites:(a) Elementary Statistics(b).At least one of the following packages(SAS, R/Splus, or SPSS). Contents : 1.Statistical inference for Two-way and Three-way Contigency tables under different assumptions. 2.Logit/Loglinear models and their extensions. 3.Generalized linear models with random effects for categorical responses. 4.Models checking and selection. 5.Asymptotic results and other advanced topics. Sofewares: 1.SAS: PPRC FREQ, GENMOD, LOGISTIC, CATMOD, and NLMIXED. 2.S-PLUS or R: chisq.test, glm, fisher. test, gee, and glmmPQL. 3.SPSS: crosstabs, logistic, and plum.

## 參考書目

“Categorical Data Analysis” by Alan Agresti