Item Parceling Strategies in SEM: Investigating the Subtle Effects of Unmodeled Secondary Constructs

TLDR

Researchers combine item responses into parcels for SEM, but the impact of different parceling strategies on parameter estimation and model fit remains unclear. The study proposes that parceling items sharing an unmodeled secondary influence (shared uniqueness strategy) will improve parameter estimate accuracy. They applied the shared uniqueness parceling strategy to item sets in two studies—an empirical organizational dataset and a simulated dataset—to evaluate its effect on parameter estimates. Study 1 found that parceling choices markedly altered parameter estimates and fit in two organizational datasets, while Study 2 demonstrated that the shared uniqueness strategy yielded more accurate estimates when the secondary influence affected only one construct, and when both constructs were contaminated, bias was present but signaled by worsened fit statistics.

Abstract

For theoretical and empirical reasons, researchers may combine item-level responses into aggregate item parcels to use as indicators in a structural equation modeling context. Yet the effects of specific parceling strategies on parameter estimation and model fit are not known. In Study 1, different parceling combinations meaningfully affected parameter estimates and fit indicators in two organizational data sets. Based on the concept of external consistency, the authors proposed that combining items that shared an unmodeled secondary influence into the same parcel (shared uniqueness strategy) would enhance the accuracy of parameter estimates. This proposal was supported in Study 2, using simulated data generated from a known model. When the unmodeled secondary influence was related to indicators of only one latent construct, the shared uniqueness parceling strategy resulted in more accurate parameter estimates. When indicators of both target latent constructs were contaminated, bias was present but appropriately signaled by worsened fit statistics.