Abstract

Random variables generated from five distributions were used to represent the common and specific factors in factor analysis in order to determine the robustness of the maximum likelihood estimation procedure. Five response variables were chosen for this study each with two factors. The chosen variables were transformed into linear combinations of an underlying set of hypothesized or unobserved components (factors). The result revealed that the estimates of the variance for the first factor were found to be almost the same and closely related to each other in all the distributions considered. The Chi-Square test conducted concluded that maximum likelihood method of estimation is robust in factor analysis.

Key words: Maximum likelihood, factor analysis, robustness, distributions, Random variables,Chi-Square test.