基本説明
Provides a systematic exposition of a group-based statistical method for analyzing logitudinal data in the social and behavioral sciences and in medicine.
Full Description
This book provides a systematic exposition of a group-based statistical method for analyzing longitudinal data in the social and behavioral sciences and in medicine. The methods can be applied to a wide range of data, such as that describing the progression of delinquency and criminality over the life course, changes in income over time, the course of a disease or physiological condition, or the evolution of the socioeconomic status of communities. Using real-world research data from longitudinal studies, the book explains and applies this method for identifying distinctive time-based progressions called developmental trajectories. Rather than assuming the existence of developmental trajectories of a specific form before statistical data analysis begins, the method allows the trajectories to emerge from the data itself. Thus, in an analysis of data on Montreal school children, it teases apart four distinct trajectories of physical aggression over the ages 6 to 15, examines predictors of these trajectories, and identifies events that may alter the trajectories.
Aimed at consumers of statistical methodology, including social scientists, criminologists, psychologists, and medical researchers, the book presents the statistical theory underlying the method with a mixture of intuition and technical development.
Contents
Acknowledgments 1. Introduction and Rationale PART I. LAYING OUT THE BASIC MODEL 2. The Basic Model 3. Groups as an Approximation 4. Model Selection 5. Posterior Group-Membership Probabilities PART II. GENERALIZING THE BASIC MODEL 6. Statistically Linking Group Membership to Covariates 7. Adding Covariates to the Trajectories Themselves 8. Dual Trajectory Analysis 9. Concluding Observations References Index
