INSEAD Library

Includes bibliographical references and index

Digitized

Fixed Effects Regression Methods
for Longitudinal Data Using SAS®
Contents
Acknowledgments...................................................................................... v
Chapter 1 Introduction to Fixed Effects Methods...................................1
1.1 The Promise of Fixed Effects for Nonexperimental Research................. 1
1.2 The Paired-Comparison t-Test as a Fixed Effects Method...................... 2
1.3 Costs and Benefits of Fixed Effects Methods.......................................... 3
1.4 Why Are These Methods Called "Fixed Effects"?.................................... 5
1.5 Fixed Effects Methods in SAS/STAT........................................................ 6
1.6 What You Need to Know.......................................................................... 6
1.7 Computing................................................................................................. 7
Chapter 2 Fixed Effects Methods for Linear Regression.......................9
2.1 Introduction............................................................................................... 9
2.2 Estimation with Two Observations Per Person...................................... 10
2.3 Extending the Model............................................................................... 15
2.4 Estimation with PROC GLM for More Than Two Observations
Per Person......................................................................................... 19
2.5 Fixed Effects versus Random Effects..................................................... 25
2.6 A Hybrid Method..................................................................................... 32
2.7 An Example with Unbalanced Data........................................................ 38
2.8 Summary................................................................................................. 46
Chapter 3 Fixed Effects Methods for Categorical
Response Variables.............................................................47
3.1 Introduction............................................................................................. 47
3.2 Logistic Models for Dichotomous Data with Two Observations
Per Person......................................................................................... 49
3.3 Estimation of Logistic Models for Two or More Observations
Per Person......................................................................................... 57
3.4 Fixed Effects versus Random Effects..................................................... 62
3.5 Subject-Specific versus Population-Averaged Coefficients.................... 64
3.6 A Hybrid Model....................................................................................... 66
3.7 Fixed Effects Methods for Multinomial Responses................................ 70
3.8 Summary................................................................................................. 77
Chapter 4 Fixed Effects Regression Methods for Count Data...........79
4.1 Introduction............................................................................................. 79
4.2 Poisson Models for Count Data with Two Observations Per
Individual............................................................................................... 80
4.3 Poisson Models for Data with More Than Two Observations
Per Individual........................................................................................ 86
4.4 Fixed Effects Negative Binomial Models for Count Data....................... 93
4.5 Comparison with Random Effects Models and GEE
Estimation............................................................................................. 97
4.6 A Hybrid Approach................................................................................ 101
4.7 Summary............................................................................................... 104
Chapter 5 Fixed Effects Methods for Event History Analysis......... 107
5.1 Introduction........................................................................................... 107
5.2 Cox Regression.................................................................................... 108
5.3 Cox Regression with Fixed Effects....................................................... 112
5.4 Some Caveats...................................................................................... 116
5.5 Cox Regression Using the Hybrid Method........................................... 116
5.6 Fixed Effects Event History Methods for
Nonrepeated Events........................................................................... 117
5.7 Summary............................................................................................... 123
Chapter 6 Linear Fixed Effects Models with PROC CALIS...............125
6.1 Introduction........................................................................................... 125
6.2 Random Effects as a Latent Variable Model........................................ 126
6.3 Fixed Effects as a Latent Variable Model............................................. 130
6.4 A Compromise between Fixed Effects and Random
Effects............................................................................................. 132
6.5 Reciprocal Effects with Lagged Predictors........................................... 134
6.6 Summary and Conclusion..................................................................... 137
References..............................................................................................139
Index........................................................................................................143