Hot deck imputation is a method used to handle missing data in surveys by replacing missing values with observed responses from similar units. Despite its widespread use, the theoretical foundation of hot deck imputation is less developed compared to other imputation methods. This review discusses various forms of hot deck imputation, including random and deterministic methods, and their applications in real surveys such as the U.S. Census Bureau's Current Population Survey (CPS). It also highlights the importance of creating donor pools based on auxiliary variables and the role of sampling weights in improving imputation accuracy. The paper explores methods for incorporating sampling weights, handling multivariate missing data, and estimating variance from imputed data. Additionally, it compares hot deck imputation with parametric methods and discusses potential areas for future research, emphasizing the need for more rigorous theoretical and empirical evaluations of hot deck imputation's properties.Hot deck imputation is a method used to handle missing data in surveys by replacing missing values with observed responses from similar units. Despite its widespread use, the theoretical foundation of hot deck imputation is less developed compared to other imputation methods. This review discusses various forms of hot deck imputation, including random and deterministic methods, and their applications in real surveys such as the U.S. Census Bureau's Current Population Survey (CPS). It also highlights the importance of creating donor pools based on auxiliary variables and the role of sampling weights in improving imputation accuracy. The paper explores methods for incorporating sampling weights, handling multivariate missing data, and estimating variance from imputed data. Additionally, it compares hot deck imputation with parametric methods and discusses potential areas for future research, emphasizing the need for more rigorous theoretical and empirical evaluations of hot deck imputation's properties.