Event History Analysis with Stata, by Hans-Peter Blossfeld, Katrin Golsch, and Götz Rohwer, presents survival analysis from a social science perspective. Introducing the mathematics and statistics of survival analysis, along with substantive discussions of social science data issues, the authors give examples throughout using Stata (version 15) and data from the German Life History Study. The text covers both basic and advanced topics, from an introduction to life tables to fitting parametric models with unobserved heterogeneity. The authors aptly illustrate the entire research path required in applying event history analysis, from the initial problems of recording event-oriented data to data organization, software applications, and interpreting results.
After a substantive discussion of event history data, the authors explain, throughout the book, the theory and application of nonparametric methods, parametric regression, and finally the Cox model. The chapters on parametric analysis contain an instructive and detailed discussion on time-dependent covariates and practical situations where these might be present.
The book provides a link to the authors’ site, where readers can find the dataset and the code used in the examples. New in this edition is an Appendix that will allow readers to consolidate the concepts just learned by applying them in practical exercises using data from the German National Educational Panel Study.
Event History Analysis with Stata is aimed at the professional social scientist but could also serve as a graduate-level text.
Preface
1. INTRODUCTION
Causal Modeling and Observation Plans
Cross-Sectional Data
Panel Data
Event History Data
Event History Analysis and Causal Modeling
Causal explanations
Transition rate models
2. EVENT HISTORY DATA STRUCTURES
Basic Terminology
Event History Data Organization
Using event history data files with Stata
Executing Stata with a do-file
Single episode data
Multiepisode data
3. NONPARAMETRIC DESCRIPTIVE METHODS
Life Table Method
Product-Limit Estimation
Comparing Survivor Functions
4. EXPONENTIAL TRANSITION RATE MODELS
The Basic Exponential Model
Maximum Likelihood Estimation
Models without Covariates
Time-Constant Covariates
Models with Multiple Decisions
Models with Multiple Episodes
5. PIECEWISE CONSTANT EXPONENTIAL MODELS
The Basic Model
Models without Covariates
Models with Proportional Covariate Effects
Models with Period-Specific Effects
6. EXPONENTIAL MODELS WITH TIME-DEPENDENT COVARIATES
Parallel and Interdependent Processes
Interdependent Processes: The System Approach
Interdependent Processes: The Causal Approach
Episode Splitting with Qualitative Covariates
Episode Splitting with Quantitative Covariates
Application Examples
7. PARAMETRIC MODELS OF TIME-DEPENDENCE
Interpretation of Time-Dependence
Gompertz Models
Weibull Models
Log-Logistic Models
Log-Normal Models
Conclusion: Estimating time-dependent models with Stata
8. METHODS TO CHECK PARAMETRIC ASSUMPTIONS
Simple Graphical Methods
Pseudoresiduals
9. SEMIPARAMETRIC TRANSITION RATE MODELS
Partial Likelihood Estimation
Time-Dependent Covariates
The Proportionality Assumption
Stratification with covariates and for multiepisode data
Baseline Results and Survivor Functions
Application Example
10. PROBLEMS OF MODEL SPECIFICATION
Unobserved Heterogeneity
Models with a Mixture Distribution
Models with a Gamma Mixture
Exponential Models with a Gamma Mixture
Weibull Models with a Gamma Mixture
Random effects for multiepisode data
Discussion
11. INTRODUCTION TO SEQUENCE ANALYSIS BY BRENDAN HALPIN
Defining distances
Doing sequence analysis in Stata
Unary summaries
Intersequence distance
What to do with sequence distances?
Optimal matching distance
Special topics
Conclusion