Available:*
Library | Item Barcode | Call Number | Material Type | Item Category 1 | Status |
---|---|---|---|---|---|
Searching... | 30000010063510 | QA278 F57 2004 | Open Access Book | Book | Searching... |
Searching... | 30000010070395 | QA278 F57 2004 | Open Access Book | Book | Searching... |
On Order
Summary
Summary
A rigorous, systematic presentation of modern longitudinal analysis
Longitudinal studies, employing repeated measurement of subjects over time, play a prominent role in the health and medical sciences as well as in pharmaceutical studies. An important strategy in modern clinical research, they provide valuable insights into both the development and persistence of disease and those factors that can alter the course of disease development.
Written at a technical level suitable for researchers and graduate students, Applied Longitudinal Analysis provides a rigorous and comprehensive description of modern methods for analyzing longitudinal data. Focusing on General Linear and Mixed Effects Models for continuous responses, and extensions of Generalized Linear Models for discrete responses, the authors discuss in detail the relationships among these different models, including their underlying assumptions and relative merits. The book features:
* A focus on practical applications, utilizing a wide range of examples drawn from real-world studies
* Coverage of modern methods of regression analysis for correlated data
* Analyses utilizing SAS(r)
* Multiple exercises and "homework" problems for review
An accompanying Web site features twenty-five real data sets used throughout the text, in addition to programming statements and selected computer output for the examples.
Author Notes
GARRETT M. FITZMAURICE, ScD , is Associate Professor of Biostatistics at the Harvard School of Public Health.
NAN M. LAIRD, PhD, is Professor of Biostatistics at the Harvard School of Public Health.
JAMES H. WARE, PhD , is Frederick Mosteller Professor of Biostatistics and Dean for Academic Affairs at the Harvard School of Public Health.
All three authors are Fellows of the American Statistical Association and members of the International Statistical Institute.
Reviews 1
Choice Review
Written to address the paucity of graduate-level works on longitudinal and clustered data in the health and medical sciences, Fitzmaurice and colleagues (all, Harvard Univ.) provide solid coverage of both technique and the conceptual underpinnings of the material at hand. The 17 chapters rely on real data from the field to illustrate the applications and include well-founded, practical descriptions. (These data sets can be downloaded from the book's Web site.) Issues regarding missing data are addressed along with linear, covariance pattern, linear mixed effects, and marginal models. Naturally, residual analysis and related diagnostic concerns are also explored. Most chapters include problem sets, generally requiring statistical software for their completion (with SAS recommended by the authors). Of special value are case studies throughout the book, effectively illustrating the presented techniques and concepts. Appendixes include a brief review of essential matrix techniques, properties of expectations and variances, and critical points for a 50:50 mixture of chi-squared distributions. The authors' decision to include introductory comments at the start of each chapter and descriptive comments of sources for additional readings for each chapter lends additional solidity to the presentation. ^BSumming Up: Recommended. Graduate students through professionals. N. W. Schillow Lehigh Carbon Community College
Table of Contents
Preface | p. xv |
Acknowledgments | p. xix |
Part I Introduction to Longitudinal and Clustered Data | |
1 Longitudinal and Clustered Data | p. 1 |
1.1 Introduction | p. 1 |
1.2 Longitudinal and Clustered Data | p. 2 |
1.3 Examples | p. 5 |
1.4 Regression Models for Correlated Responses | p. 13 |
1.5 Organization of This Book | p. 16 |
1.6 Further Reading | p. 18 |
2 Longitudinal Data: Basic Concepts | p. 19 |
2.1 Introduction | p. 19 |
2.2 Objectives of Longitudinal Analysis | p. 19 |
2.3 Defining Features of Longitudinal Data | p. 22 |
2.4 Example: Treatment of Lead-Exposed Children Trial | p. 31 |
2.5 Sources of Correlation in Longitudinal Data | p. 36 |
2.6 Further Reading | p. 44 |
Problems | p. 44 |
Part II Linear Models for Longitudinal Continuous Data | |
3 Overview of Linear Models for Longitudinal Data | p. 49 |
3.1 Introduction | p. 49 |
3.2 Notation and Distributional Assumptions | p. 50 |
3.3 Simple Descriptive Methods of Analysis | p. 62 |
3.4 Modelling the Mean | p. 71 |
3.5 Modelling the Covariance | p. 73 |
3.6 Historical Approaches | p. 76 |
3.7 Further Reading | p. 86 |
4 Estimation and Statistical Inference | p. 87 |
4.1 Introduction | p. 87 |
4.2 Estimation: Maximum Likelihood | p. 88 |
4.3 Missing Data Issues | p. 92 |
4.4 Statistical Inference | p. 94 |
4.5 Restricted Maximum Likelihood (REML) Estimation | p. 99 |
4.6 Further Reading | p. 102 |
5 Modelling the Mean: Analyzing Response Profiles | p. 103 |
5.1 Introduction | p. 103 |
5.2 Hypotheses Concerning Response Profiles | p. 105 |
5.3 General Linear Model Formulation | p. 110 |
5.4 Case Study | p. 115 |
5.5 One-Degree-of-Freedom Tests for Group by Time Interaction | p. 118 |
5.6 Adjustment for Baseline Response | p. 122 |
5.7 Alternative Methods of Adjusting for Baseline Response | p. 126 |
5.8 Strengths and Weaknesses of Analyzing Response Profiles | p. 132 |
5.9 Computing: Analyzing Response Profiles Using PROC MIXED in SAS | p. 134 |
5.10 Further Reading | p. 138 |
Problems | p. 138 |
6 Modelling the Mean: Parametric Curves | p. 141 |
6.1 Introduction | p. 141 |
6.2 Polynomial Trends in Time | p. 142 |
6.3 Linear Splines | p. 147 |
6.4 General Linear Model Formulation | p. 150 |
6.5 Case Studies | p. 152 |
6.6 Computing: Fitting Parametric Curves Using PROC MIXED in SAS | p. 159 |
6.7 Further Reading | p. 160 |
Problems | p. 161 |
7 Modelling the Covariance | p. 163 |
7.1 Introduction | p. 163 |
7.2 Implications of Correlation among Longitudinal Data | p. 164 |
7.3 Unstructured Covariance | p. 166 |
7.4 Covariance Pattern Models | p. 167 |
7.5 Choice among Covariance Pattern Models | p. 173 |
7.6 Case Study | p. 178 |
7.7 Discussion: Strengths and Weaknesses of Covariance Pattern Models | p. 181 |
7.8 Computing: Fitting Covariance Pattern Models Using PROC MIXED in SAS | p. 182 |
7.9 Further Reading | p. 184 |
Problems | p. 184 |
8 Linear Mixed Effects Models | p. 187 |
8.1 Introduction | p. 187 |
8.2 Linear Mixed Effects Models | p. 192 |
8.3 Random Effects Covariance Structure | p. 198 |
8.4 Two-Stage Random Effects Formulation | p. 200 |
8.5 Choice among Random Effects Covariance Models | p. 205 |
8.6 Prediction of Random Effects | p. 206 |
8.7 Prediction and Shrinkage | p. 208 |
8.8 Case Studies | p. 210 |
8.9 Computing: Fitting Linear Mixed Effects Models Using PROC MIXED in SAS | p. 231 |
8.10 Further Reading | p. 233 |
Problems | p. 234 |
9 Residual Analyses and Diagnostics | p. 237 |
9.1 Introduction | p. 237 |
9.2 Residuals | p. 237 |
9.3 Transformed Residuals | p. 238 |
9.4 Semi-Variogram | p. 241 |
9.5 Case Study | p. 242 |
9.6 Summary | p. 251 |
9.7 Further Reading | p. 252 |
Problems | p. 253 |
Part III Generalized Linear Models for Longitudinal Data | |
10 Review of Generalized Linear Models | p. 257 |
10.1 Introduction | p. 257 |
10.2 Salient Features of Generalized Linear Models | p. 258 |
10.3 Illustrative Examples | p. 263 |
10.4 Computing: Fitting Generalized Linear Models Using PROC GENMOD in SAS | p. 276 |
10.5 Overview of Generalized Linear Models | p. 279 |
10.6 Further Reading | p. 287 |
Problems | p. 287 |
11 Marginal Models: Generalized Estimating Equations (GEE) | p. 291 |
11.1 Introduction | p. 291 |
11.2 Marginal Models for Longitudinal Data | p. 292 |
11.3 Estimation for Marginal Models: Generalized Estimating Equations | p. 299 |
11.4 Case Studies | p. 305 |
11.5 Computing: Generalized Estimating Equations Using PROC GENMOD in SAS | p. 316 |
11.6 Distributional Assumptions for Marginal Models | p. 319 |
11.7 Further Reading | p. 321 |
Problems | p. 321 |
12 Generalized Linear Mixed Effects Models | p. 325 |
12.1 Introduction | p. 325 |
12.2 Incorporating Random Effects in Generalized Linear Models | p. 326 |
12.3 Interpretation of Regression Parameters | p. 331 |
12.4 Estimation and Inference | p. 338 |
12.5 Case Studies | p. 340 |
12.6 Computing: Fitting Generalized Linear Mixed Models Using PROC NLNIXED in SAS | p. 351 |
12.7 Further Reading | p. 354 |
Problems | p. 355 |
13 Contrasting Marginal and Mixed Effects Models | p. 359 |
13.1 Introduction | p. 359 |
13.2 Linear Models: A Special Case | p. 359 |
13.3 Generalized Linear Models | p. 360 |
13.4 Simple Numerical Illustration | p. 364 |
13.5 Case Study | p. 365 |
13.6 Conclusion | p. 369 |
13.7 Further Reading | p. 371 |
Part IV Advanced Topics for Longitudinal and Clustered Data | |
14 Missing Data and Dropout | p. 375 |
14.1 Introduction | p. 375 |
14.2 Hierarchy of Missing Data Mechanisms | p. 377 |
14.3 Implications for Longitudinal Analysis | p. 384 |
14.4 Dropout | p. 386 |
14.5 Common Approaches for Handling Dropout | p. 391 |
14.6 Case Study | p. 397 |
14.7 Further Reading | p. 400 |
15 Some Aspects of the Design of Longitudinal Studies | p. 401 |
15.1 Introduction | p. 401 |
15.2 Sample Size and Power | p. 401 |
15.3 Interpretation of Stochastic Time-Varying Covariates | p. 414 |
15.4 Longitudinal and Cross-Sectional Information | p. 418 |
15.5 Further Reading | p. 422 |
16 Repeated Measures and Related Designs | p. 425 |
16.1 Introduction | p. 425 |
16.2 Repeated Measures Designs | p. 426 |
16.3 Multiple Source Data | p. 430 |
16.4 Case Study 1: Repeated Measures Experiment | p. 431 |
16.5 Case Study 2: Multiple Source Data | p. 434 |
16.6 Summary | p. 439 |
16.7 Further Reading | p. 440 |
17 Multilevel Models | p. 441 |
17.1 Introduction | p. 441 |
17.2 Multilevel Data | p. 442 |
17.3 Multilevel Linear Models | p. 444 |
17.4 Multilevel Generalized Linear Models | p. 455 |
17.5 Summary | p. 465 |
17.6 Further Reading | p. 466 |
Appendix A Gentle Introduction to Vectors and Matrices | p. 469 |
Appendix B Properties of Expectations and Variances | p. 479 |
Appendix C Critical Points for a 50:50 Mixture of Chi-Squared Distributions | p. 483 |
References | p. 485 |
Index | p. 501 |