Latent profile analysis with nonnormal mixtures: A Monte Carlo examination of model selection using fit indices

2016 ◽  
Vol 93 ◽  
pp. 146-161 ◽  
Author(s):  
Grant B. Morgan ◽  
Kari J. Hodge ◽  
Aaron R. Baggett
Keyword(s):  
Monte Carlo ◽  
Model Selection ◽  
Latent Profile Analysis ◽  
Profile Analysis ◽  
Fit Indices ◽  
Latent Profile

scholarly journals Latent profile analysis of human values: What is the optimal number of clusters?

Methodology ◽  
2021 ◽  
Vol 17 (2) ◽  
pp. 127-148
Author(s):  
Mikkel N. Schmidt ◽  
Daniel Seddig ◽  
Eldad Davidov ◽  
Morten Mørup ◽  
Kristoffer Jon Albers ◽  
...  
Keyword(s):  
Model Selection ◽  
Selection Criteria ◽  
Latent Profile Analysis ◽  
Profile Analysis ◽  
Information Criterion ◽  
Optimal Number ◽  
Number Of Clusters ◽  
Model Selection Criteria ◽  
Optimal Number Of Clusters ◽  
Latent Profile

Latent Profile Analysis (LPA) is a method to extract homogeneous clusters characterized by a common response profile. Previous works employing LPA to human value segmentation tend to select a small number of moderately homogeneous clusters based on model selection criteria such as Akaike information criterion, Bayesian information criterion and Entropy. The question is whether a small number of clusters is all that can be gleaned from the data. While some studies have carefully compared different statistical model selection criteria, there is currently no established criteria to assess if an increased number of clusters generates meaningful theoretical insights. This article examines the content and meaningfulness of the clusters extracted using two algorithms: Variational Bayesian LPA and Maximum Likelihood LPA. For both methods, our results point towards eight as the optimal number of clusters for characterizing distinctive Schwartz value typologies that generate meaningful insights and predict several external variables.

A Latent Profile Analysis of Student Restudy Decisions - under review

2019 ◽  
Author(s):  
Alison Robey
Keyword(s):  
Cluster Model ◽  
Latent Profile Analysis ◽  
Cross Validation ◽  
Current Knowledge ◽  
Profile Analysis ◽  
Auxiliary Variable ◽  
The Other ◽  
Fit Indices ◽  
Almost All ◽  
Latent Profile

Do all learners make the same restudy decisions, or is there heterogeneity within the population? The present study combines three previously published datasets and uses latent profile analysis to determine if subpopulations of learners can be identified that make different restudy decisions. Based on multiple fit indices, cross-validation, and theoretical consideration, a 4-cluster model was selected. Two clusters of learners differentiate items based on their current knowledge focusing on either known or unknown items for restudy, whereas two clusters do not distinguish between known and unknown items and instead choose to restudy almost all or almost known of the items, regardless of whether they were retrieved correctly. Additional auxiliary variable analyses revealed that learners who chose to focus their restudy on unknown information make more accurate restudy decisions than the other clusters. Implications for future exploration of student restudy decisions and the need to explore heterogeneity are discussed.

Sign in / Sign up

Export Citation Format

Share Document