The changepoint package in R provides multiple methods for detecting changes in time series data. It includes the PELT algorithm, which is efficient and accurate for identifying multiple changepoints. The package offers various search methods, including Binary Segmentation, Segment Neighbourhoods, and PELT, along with different test statistics for analyzing changes in mean, variance, or both. The package also includes an S4 class, 'cpt', to store results of changepoint analysis, and functions for accessing and manipulating these results. The package allows users to choose between different penalty types and test statistics, and it supports both distributional and distribution-free methods. The paper describes the implementation of these methods, provides examples of their application, and discusses the differences between exact and approximate methods. The package is useful for both practitioners and researchers, enabling them to compare existing methods with new approaches. The package is available on CRAN and can be used for a wide range of applications, including climate data, bioinformatics, and financial analysis.The changepoint package in R provides multiple methods for detecting changes in time series data. It includes the PELT algorithm, which is efficient and accurate for identifying multiple changepoints. The package offers various search methods, including Binary Segmentation, Segment Neighbourhoods, and PELT, along with different test statistics for analyzing changes in mean, variance, or both. The package also includes an S4 class, 'cpt', to store results of changepoint analysis, and functions for accessing and manipulating these results. The package allows users to choose between different penalty types and test statistics, and it supports both distributional and distribution-free methods. The paper describes the implementation of these methods, provides examples of their application, and discusses the differences between exact and approximate methods. The package is useful for both practitioners and researchers, enabling them to compare existing methods with new approaches. The package is available on CRAN and can be used for a wide range of applications, including climate data, bioinformatics, and financial analysis.