This book presents limit theorems in change-point analysis, focusing on statistical methods for detecting changes in data sequences. It is authored by Miklós Csörgő and Lajos Horváth, and covers three main areas: likelihood-based methods, nonparametric methods, and linear models. The book also includes a chapter on dependent observations, which is essential for analyzing time series data. The first chapter discusses the likelihood approach, including log likelihood ratio processes, maximum likelihood ratio tests, and estimators for the time of change. It also covers various applications such as Fisher-score change processes, maximally selected chi-square statistics, and epidemic alternatives. The second chapter presents nonparametric methods for detecting changes in data, including tests for changes in mean, location, and variance. It also discusses Wilcoxon-type statistics, U-statistics, and empirical distributions. The chapter includes various nonparametric methods for detecting changes, such as estimators for the time of change, tests based on M-estimators, and nonparametric tests for epidemic alternatives. The third chapter focuses on linear models, including maximum likelihood ratio methods, tests based on comparison of estimators, and consistency of tests. It also discusses estimators for the time of change and further results and remarks. The fourth chapter discusses dependent observations, including weakly dependent sequences, procedures based on residuals, and changes in the mean of strongly dependent sequences. It also includes further results and remarks. The book also includes appendices that provide approximations for partial sums of random variables, limit theorems for Ornstein-Uhlenbeck processes, and integral tests for some Gaussian processes. It concludes with references and indexes.This book presents limit theorems in change-point analysis, focusing on statistical methods for detecting changes in data sequences. It is authored by Miklós Csörgő and Lajos Horváth, and covers three main areas: likelihood-based methods, nonparametric methods, and linear models. The book also includes a chapter on dependent observations, which is essential for analyzing time series data. The first chapter discusses the likelihood approach, including log likelihood ratio processes, maximum likelihood ratio tests, and estimators for the time of change. It also covers various applications such as Fisher-score change processes, maximally selected chi-square statistics, and epidemic alternatives. The second chapter presents nonparametric methods for detecting changes in data, including tests for changes in mean, location, and variance. It also discusses Wilcoxon-type statistics, U-statistics, and empirical distributions. The chapter includes various nonparametric methods for detecting changes, such as estimators for the time of change, tests based on M-estimators, and nonparametric tests for epidemic alternatives. The third chapter focuses on linear models, including maximum likelihood ratio methods, tests based on comparison of estimators, and consistency of tests. It also discusses estimators for the time of change and further results and remarks. The fourth chapter discusses dependent observations, including weakly dependent sequences, procedures based on residuals, and changes in the mean of strongly dependent sequences. It also includes further results and remarks. The book also includes appendices that provide approximations for partial sums of random variables, limit theorems for Ornstein-Uhlenbeck processes, and integral tests for some Gaussian processes. It concludes with references and indexes.