Comparison of Two Approaches to Detecting Switched Class Labels in LCA Simulations: Class Assignment vs. Class Similarity

Abstract

The detection of switched class labels is required in latent class analysis (LCA) simulations involving parameter estimation. The present study proposed a class similarity (CS) algorithm to detect switched class labels based on the similarity of conditional probabilities between true and estimated classes, in contrast to Tueller et al.’s class assignment (CA) algorithm considering the number of participants in each true class assigned to every estimated class. The performances of CS and CA were compared by examining the average class assignment accuracy and the bias of parameter estimates in a numerical experiment. CS and CA were shown to perform similarly that either method can be used to detect switched class labels in future LCA simulations. The performance of the two algorithms warrants further investigation under a wider simulation condition.

Keywords:

• Class assignment algorithm
• class similarity algorithm
• latent class analysis
• parameter estimation
• simulation
• switched class labels

Acknowledgement

We thank Chao-Ying Joanne Peng for comments on earlier versions of this manuscript.

Additional information

Funding

The research was supported in part by Ministry of Science and Technology in Taiwan under Grants MOST106-2410-H002-097 and MOST107-2410-H002-116-MY3.