The paper discusses the use of fully conditional specification (FCS) in multivariate imputation, a method that involves iteratively imputing missing values using conditional models. While FCS has theoretical weaknesses, such as potential incompatibility of conditional densities, the study shows that it performs well in practice. Simulations were conducted under various missing data mechanisms, including MAR, to evaluate the effectiveness of FCS. Results indicate that multiple imputation using FCS produces unbiased estimates with appropriate coverage, even for incompatible models. The study also highlights that FCS is computationally feasible and robust against incompatibility, making it a valuable tool for multivariate imputation. The paper concludes that FCS is a practical and effective approach for handling missing data, despite its theoretical limitations.The paper discusses the use of fully conditional specification (FCS) in multivariate imputation, a method that involves iteratively imputing missing values using conditional models. While FCS has theoretical weaknesses, such as potential incompatibility of conditional densities, the study shows that it performs well in practice. Simulations were conducted under various missing data mechanisms, including MAR, to evaluate the effectiveness of FCS. Results indicate that multiple imputation using FCS produces unbiased estimates with appropriate coverage, even for incompatible models. The study also highlights that FCS is computationally feasible and robust against incompatibility, making it a valuable tool for multivariate imputation. The paper concludes that FCS is a practical and effective approach for handling missing data, despite its theoretical limitations.