Linear Mixed Models for Longitudinal DataSpringer Science & Business Media, 27 janv. 2008 - 568 pages This book provides a comprehensive treatment of linear mixed models for continuous longitudinal data. Next to model formulation, this edition puts major emphasis on exploratory data analysis for all aspects of the model, such as the marginal model, subject-specific profiles, and residual covariance structure. Further, model diagnostics and missing data receive extensive treatment. Sensitivity analysis for incomplete data is given a prominent place. Most analyses were done with the MIXED procedure of the SAS software package, but the data analyses are presented in a software-independent fashion. |
Table des matières
| 6 | |
A Model for Longitudinal Data | 19 |
Exploratory Data Analysis | 31 |
Estimation of the Marginal Model | 41 |
Inference for the Marginal Model | 55 |
Inference for the Random Effects | 77 |
Fitting Linear Mixed Models with SAS | 93 |
General Guidelines for Model Building | 121 |
Sensitivity Analysis for Selection Models 295 | 294 |
Sensitivity Analysis for PatternMixture Models | 331 |
201 | 354 |
1 | 375 |
The ExpectationMaximization Algorithm | 387 |
Case Studies | 405 |
209 | 409 |
Appendix | 485 |
10 | 135 |
Local Influence for the Linear Mixed Model | 151 |
The Heterogeneity Model 169 | 168 |
Conditional Linear Mixed Models | 189 |
The Vorozole Study | 201 |
Growth Data | 221 |
Selection Models 231 | 230 |
PatternMixture Models | 275 |
B Technical Details for Sensitivity Analysis | 515 |
| 522 | |
| 534 | |
| 551 | |
| 554 | |
| 557 | |
Autres éditions - Tout afficher
Expressions et termes fréquents
ACMV algorithm assumed assumption baseline cancer CCMV complete data corresponding covariance matrix covariance structure data set degrees of freedom density Diggle and Kenward dropout model dropout pattern dropout process endpoint equal example F-test Figure fitted fixed effects fixed-effects Growth Data incomplete inference influence Lesaffre likelihood function likelihood ratio likelihood ratio test linear mixed model log-likelihood marginal model mastitis maximal MCAR mean structure measurement error measurement model method missing data missing value missingness MNAR Molenberghs nonrandom dropout normally distributed null hypothesis obtained p-value parameter estimates pattern-mixture models plots procedure prostate cancer Prostate Data random effects random intercepts random-effects model Rat Data regression REML estimates residual restrictions sample selection model serial correlation specified standard errors statement statistic strategies subject-specific surrogate endpoint Table time2 tion treatment effect variability variance components vector Verbeke Vorozole Study Wald test