多层统计分析模型 SAS与应用2025|PDF|Epub|mobi|kindle电子书版本百度云盘下载

多层统计分析模型 SAS与应用PDF格式电子书版下载

注意：本站所有压缩包均有解压码： 点击下载压缩包解压工具

Chapter 1 Introduction1

1.1 Conceptual framework of multilevel modeling1

1.2 Hierarchically structured data3

1.3 Variables in multilevel data4

1.4 Analytical problems with multilevel data6

1.5 Advantages and limitations of multilevel modeling9

1.6 Computer software for multilevel modeling11

Chapter 2 Basics of Linear Multilevel Models13

2.1 Intraclass correlation coefficient(ICC)13

2.2 Formulation of two-level multilevel models15

2.3 Model assumptions17

2.4 Fixed and random regression coefficients18

2.5 Cross-level interactions20

2.6 Measurement centering21

2.7 Model estimation23

2.8 Model fit,hypothesis testing,and model comparisons27

2.8.1 Model fit27

2.8.2 Hypothesis testing28

2.8.3 Model comparisons30

2.9 Explained level-1 and level-2 variances30

2.10 Steps for building multilevel models33

2.11 Higher-level multilevel models37

Chapter 3 Application of Two-level Linear Multilevel Models39

3.1 Data39

3.2 Empty model42

3.3 Predicting between-group variation48

3.4 Predicting within-group variation53

3.5 Testing random level-1 slopes57

3.6 Across-level interactions62

3.7 Other issues in model development66

Chapter 4 Application of Multilevel Modeling to Longitudinal Data73

4.1 Features of longitudinal data73

4.2 Limitations of traditional approaches for modeling longitudinal data74

4.3 Advantages of multilevel modeling for longitudinal data75

4.4 Formulation of growth models75

4.5 Data description and manipulation77

4.6 Linear growth models79

4.6.1 The shape of average outcome change over time80

4.6.2 Random intercept growth models80

4.6.3 Random intercept and slope growth models84

4.6.4 Intercept and slope as outcomes86

4.6.5 Controlling for individual background variables in models88

4.6.6 Coding time score89

4.6.7 Residual variance/covariance structures91

4.6.8 Time-varying covariates95

4.7 Curvilinear growth models98

4.7.1 Polynomial growth model98

4.7.2 Dealing with collinearity in higher order polynomial growth model100

4.7.3 Piecewise(linear spline)growth model106

Chapter 5 Multilevel Models for Discrete Outcome Measures113

5.1 Introduction to generalized linear mixed models113

5.1.1 Generalized linear models113

5.1.2 Generalized linear mixed models115

5.2 SAS Procedures for multilevel modeling with discrete outcomes116

5.3 Multilevel models for binary outcomes117

5.3.1 Logistic regression models117

5.3.2 Probit models118

5.3.3 Unobserved latent variables and observed binary outcome measures119

5.3.4 Multilevel logistic regression models119

5.3.5 Application of multilevel logistic regression models120

5.3.6 Application of multilevel logit models to longitudinal data136

5.4 Multilevel models for ordinal outcomes139

5.4.1 Cumulative logit models139

5.4.2 Multilevel cumulative logit models141

5.5 Multilevel models for nominal outcomes146

5.5.1 Multinomial logit models146

5.5.2 Multilevel multinomial logit models147

5.5.3 Application of multilevel multinomial logit models148

5.6 Multilevel models for count outcomes154

5.6.1 Poisson regression models155

5.6.2 Poisson regression with over-dispersion and a negative binomial model157

5.6.3 Multilevel Poisson and negative binomial models158

5.6.4 Application of multilevel Poisson and negative binomial models158

Chapter 6 Other Applications of Multilevel Modeling and Related Issues175

6.1 Multilevel zero-inflated models for count data with extra zeros175

6.1.1 Fixed-effect ZIP model176

6.1.2 Random effect zero-inflated Poisson (RE-ZIP)models177

6.1.3 Random effect zero-inflated negative binomial(RE-ZINB)models178

6.1.4 Application ofRE-ZIP and RE-ZINB models178

6.2 Mixed-effect mixed-distribution models for semi-continuous outcomes188

6.2.1 Mixed-effects mixed distribution model189

6.2.2 Application of the Mixed-Effect mixed distribution model190

6.3 Bootstrap multilevel modeling195

6.3.1 Nonparametric residual bootstrap multilevel modeling196

6.3.2 Parametric residual bootstrap multilevel modeling197

6.3.3 Application of nonparametric residual bootstrap multilevel modeling198

6.4 Group-based models for longitudinal data analysis210

6.4.1 Introduction to group-based model212

6.4.2 Group-based logit model214

6.4.3 Group-based zero-inflated Poisson(ZIP)model222

6.4.4 Group-based censored normal models230

6.5 Missing values issue237

6.5.1 Missing data mechanisms and their implications238

6.5.2 Handling missing data in longitudinal data analyses240

6.6 Statistical power and sample size for multilevel modeling241

6.6.1 Sample size estimation for two-level designs242

6.6.2 Sample size estimation for longitudinal data analysis242

Reference247

Index259