Comparison of EM and Multiple Imputation Methods with Traditional Methods in Monotone Missing Pattern

  • Kang, Shin-Soo (Department of Information Statistics, Kwandong University)
  • Published : 2005.02.28

Abstract

Complete-case analysis is easy to carry out and it may be fine with small amount of missing data. However, this method is not recommended in general because the estimates are usually biased and not efficient. There are numerous alternatives to complete-case analysis. A natural alternative procedure is available-case analysis. Available-case analysis uses all cases that contain the variables required for a specific task. The EM algorithm is a general approach for computing maximum likelihood estimates of parameters from incomplete data. These methods and multiple imputation(MI) are reviewed and the performances are compared by simulation studies in monotone missing pattern.