PENDUGAAN DATA HILANG DENGAN MENGGUNAKAN DATA AUGMENTATION

Abstract

Data augmentation is a method for estimating missing data. It is a special case of Gibbs sampling which has two important steps. The first step is imputation or I-step where the missing data is generated based on the conditional distributions for missing data if the observed data are known. The next step is posterior or P-step where the estimation process of parameter values from the complete data is conducted. Imputation and posterior steps on the data augmentation will continue to run until the convergence is reached. The estimate of missing data is obtained through the average of simulated values.