Recovering preipsative information from additive ipsatized data - A factor score approach

Response bias has long been recognized as an issue in the behavioral and social sciences, especially in cross-cultural research. Transforming raw data into ipsatized data, individual scores subject to a constant sum constraint, is proposed to be an effective measure to minimize response bias. One major problem of applying ipsatized data is that scores are incomparable across individuals. By assuming that the ipsatized data are transformed from a preipsative confirmatory factor analytic model, factor scores based on the ipsatized data are proposed to serve as proxy variables for the preipsative information in this study. The ipsative factor scores can be used for further data analysis. Simulation results reveal that the proposed method works reasonably well. A real example is used to illustrate how this method can be applied to real data sets.