進階統計模式與資料分析
Applied Multivariate and Longitudinal Data Analysis
| 節 | 週四 |
|---|---|
7 15:30–16:20 | 進階統計模式與資料分析 YS415 2 節連堂 |
8 16:30–17:20 |
* 根據陽明交大上課時間表所列
This course focus on multivariate extensions of linear, logistic, and Poisson regression models. Topics include design issues with more complex data structure, generalized estimating equation (GEE), random effect models, principal component analysis, and Factor analyses. Model building and development will be covered through real data analysis projects.
This course focus on multivariate extensions of linear, logistic, and Poisson regression models. Topics include design issues with more complex data structure, generalized estimating equation (GEE), random effect models, principal component analysis, and Factor analyses. Model building and development will be covered through real data analysis projects.Course Description: This course focuses on applied multivariate extensions of linear, logistic, and Poisson regression models with more complex data structure such as longitudinal repeated measures, matching, and hierarchical samples. Topics include design issues, generalized estimating equation (GEE), random effect models, principal component analysis, and Factor analyses. Model building and development will be covered through real data analysis projects. Computing: Students are required to use a statistical software package to do the data analysis projects. SPSS and/or SAS will be demonstrated in class.
| 週次 | 主題 |
|---|---|
| 第 1 週 | Course Introduction / Designs with correlated data |
| 第 2 週 | Introduction to generalized linear models (1) - Linear regression, Logistic regression - Issues of model building: a case study |
| 第 3 週 | Introduction to generalized linear models (2) - Poisson log-linear models - Quasi-likelihood approach for robust variance estimates |
| 第 4 週 | Exploratory analysis for longitudinal data - Mean profiles, covariance structure |
| 第 5 週 | Linear models with correlated data - I - Marginal models |
| 第 6 週 | Linear models with correlated data - II - Random coefficient models - “Multi-level models” and “Mixed models” |
| 第 7 週 | Case studies (1) |
| 第 8 週 | Generalized linear model with longitudinal data I - Logistic model with GEE |
| 第 9 週 | Generalized linear model with longitudinal data II - Poisson log-linear model with GEE |
| 第 10 週 | Case studies (2) |
| 第 11 週 | Principal Component analysis |
| 第 12 週 | Factor Analysis |
| 第 13 週 | Selected multivariate methods |
| 第 14 週 | Case studies (3) |
| 第 15 週 | Student presentation /Cases studies |
| 第 16 週 | Final exam (take home) |
| 第 17 週 | Online learning activities (1) |
| 第 18 週 | Online learning activities (2) |
References: Kutner, Nachtsheim, Neter, and Li. Applied linear statistical models. 5th ed. Hosmer & Lemoshew “Applied logistic regression” (2000) McCullagh and Nelder. Generalized linear models. 2nd ed, 1989, Chapman and Hall. Diggle, Heagerty, Liang, & Zeger. Analysis of longitudinal data 2nd ed. 2002 Oxford science publications. Liang and Zeger. Regression analysis for correlated data. Annual Review of Public Health 1993. 14:43-68. Rencher & Christensen. Methods of multivariate analysis. 3rd ed. (2012)