A Monte Carlo Study Investigating the Impact of Item Parceling Strategies on Parameter Estimates and Their Standard Errors in CFA

Abstract A simulation study was conducted to examine the effect of item parceling on confirmatory factor analysis parameter estimates and their standard errors at different levels of sample size, number of indicators per factor, size of factor structure/pattern coefficients, magnitude of interfactor correlations, and variations in item-level data distribution. Results suggest that the use of item parceling had negligible effects on parameter bias and on the standard errors of the estimated factor correlations. Including more items per parcel did reduce the standard errors of estimated factor structure/pattern coefficients although this effect was attenuated with larger samples and higher pattern/structure coefficients that generally led to smaller standard errors.