A Monte Carlo study was conducted to compare the efficiency of Listwise deletion, Pairwise deletion, Allvalue, and Samemean methods in estimating the correlation matrix from data that had randomly occurring missing values. The four methods were compared in a 3x3x4 factorial design representing sample size, proportion of incomplete records in the sample, and the number of missing values per record. Each sample represented an N x 8 data matrix. The Pairwise method was found best in estimating the correlation matrix under all experimental conditions except when the incomplete records had 50% of values missing. In this condition, Listwise deletion was considered a better choice. Allvalue and Samemean methods performed exactly the same way under all experimental conditions, but were found less efficient than the Pairwise method. One table, three figures. (Contains 12 references.) (Author/SLD)