Analysis of Longitudinal Data by P. L. Diggle, K.-L. Liang, and S. L. Zeger (1994) is a comprehensive textbook on statistical models and methods for analyzing longitudinal data, primarily illustrated through biology and health sciences. Longitudinal data are defined as multiple short series, each corresponding to a subject, with measurements taken at various time points. The book focuses on modeling the observations of each subject, considering the intercorrelation among measurements. It presents regression problems where the response variable depends on explanatory variables, taking into account the type of response variable, number of experimental units, and study objectives. The book begins with the selection of study designs, focusing on sample size requirements for statistical power. It then covers exploratory methods such as graphical representation of data over time, curve fitting, and exploration of correlation structures. Linear models (GLM) are extensively discussed, contrasting them with repeated measures ANOVA. The book also addresses binary and frequency response variables, illustrating them in marginal, random effects, and transition models (Markov chains). It concludes with a discussion on missing data, a common issue in longitudinal studies. The authors use six examples from biology and health sciences to demonstrate the application of the theoretical models presented. The book is well-structured, with detailed theoretical explanations followed by concrete examples. The language is clear and accessible, requiring only basic knowledge of regression models and elementary matrix calculus. While the examples are mainly from biology and health sciences, the concepts can be applied to psychology. The book is a valuable resource for understanding longitudinal data analysis.Analysis of Longitudinal Data by P. L. Diggle, K.-L. Liang, and S. L. Zeger (1994) is a comprehensive textbook on statistical models and methods for analyzing longitudinal data, primarily illustrated through biology and health sciences. Longitudinal data are defined as multiple short series, each corresponding to a subject, with measurements taken at various time points. The book focuses on modeling the observations of each subject, considering the intercorrelation among measurements. It presents regression problems where the response variable depends on explanatory variables, taking into account the type of response variable, number of experimental units, and study objectives. The book begins with the selection of study designs, focusing on sample size requirements for statistical power. It then covers exploratory methods such as graphical representation of data over time, curve fitting, and exploration of correlation structures. Linear models (GLM) are extensively discussed, contrasting them with repeated measures ANOVA. The book also addresses binary and frequency response variables, illustrating them in marginal, random effects, and transition models (Markov chains). It concludes with a discussion on missing data, a common issue in longitudinal studies. The authors use six examples from biology and health sciences to demonstrate the application of the theoretical models presented. The book is well-structured, with detailed theoretical explanations followed by concrete examples. The language is clear and accessible, requiring only basic knowledge of regression models and elementary matrix calculus. While the examples are mainly from biology and health sciences, the concepts can be applied to psychology. The book is a valuable resource for understanding longitudinal data analysis.