|
Abstract:
|
MLE is obtained from the partial log-likelihood function for the cell probabilities of two-way incomplete contingency tables proposed by Chen and Fienberg (1974). Constraints can be incorporated with the lagrangian multiplier. Variances of MLE estimators of population proportions are derived from the matrix of second derivatives of the log-likelihood with respect to cell probabilities, and Wald and likelihood ratio tests of independence are examined. Simulation results, when data are missing at random, reveal that MLE provides more efficient estimates of population proportions than either multiple imputation (MI), based on data augmentation, or complete case analysis, but neither MLE nor MI provides an improvement over complete-case analysis with respect to power of tests for independence.
|
