Structural Equation Modeling A Multidisciplinary Journal· 2013Q1
Statistical Power to Detect the Correct Number of Classes in Latent Profile Analysis
- 1,836citations
- Q1SCImago
- 2013year
Short summary
Latent profile analysis (LPA) often struggles to detect the correct number of classes, especially with small interclass distances. This simulation found that only very large interclass distances (Cohen's d = 1.5) allowed methods like the LMR test, adjusted LMR, bootstrap likelihood ratio test, BIC, and sample-size-adjusted BIC to reliably select the correct number of classes.
AI-generated from the title and abstract; the full text is not read.
Key points
- Statistical power to detect the correct number of classes in LPA is significantly influenced by the interclass distance (degree of separation).
- Methods like LMR tests, adjusted LMR, bootstrap likelihood ratio test, BIC, and sample-size-adjusted BIC showed good power only with a very large interclass distance (Cohen's d = 1.5).
- With smaller interclass distances (d = 0.2, 0.5, 0.8), power was inadequate or dependent on sample size and number of indicators.
- Akaike's Information Criterion (AIC) and entropy consistently performed poorly in selecting the correct number of classes.
AI-generated from the title and abstract; the full text is not read.
Abstract
Little research has examined factors influencing statistical power to detect the correct number of latent classes using latent profile analysis (LPA). This simulation study examined power related to interclass distance between latent classes given true number of classes, sample size, and number of indicators. Seven model selection methods were evaluated. None had adequate power to select the correct number of classes with a small (Cohen's d = .2) or medium (d = .5) degree of separation. With a very large degree of separation (d = 1.5), the Lo–Mendell–Rubin test (LMR), adjusted LMR, bootstrap likelihood ratio test, Bayesian Information Criterion (BIC), and sample-size-adjusted BIC were good at selecting the correct number of classes. However, with a large degree of separation (d = .8), power depended on number of indicators and sample size. Akaike's Information Criterion and entropy poorly selected the correct number of classes, regardless of degree of separation, number of indicators, or sample size.
The authors' abstract, as published at the source. Structural Equation Modeling A Multidisciplinary Journal, 2013 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: Statistics and Probability
Statistics and ProbabilityMathematics