On the two-dimensional nature of the Marlowe-Crowne Social Desirability Scale

Ramanaiah, Schill, and Leung (1977) reported empirical evidence supporting Millham's (1974) hypothesis that attribution and denial are two separate components of the MC-SD scale. This paper presents the results of two studies conducted to test the hypothesis that the results obtained by Ramanaiah et al. (1977) may be attributed to method variance caused by the keying direction in the MC-SD attribution and denial subscales. The first study was concerned with the development of balanced attribution and denial scales, while the second study investigated whether the results from Ramanaiah et al., which used the original unbalanced attribution and denial scales, could be replicated with the balanced scales developed in Study I. The results strongly supported the tested hypothesis, indicating that the two subscales are measuring essentially the same construct.