Latent Class Analysis in Mplus Version 3.ppt

Latent Class Analysis in Mplus Version 3 Karen Nylund Social Research Methods Graduate School of Education Information Studies knylund@ Overview of Session General description of Latent Class Analysis (LCA) within a hypothetical example Two examples of LCA analysis using Mplus Version 3 Anti-Social Behavior Diabetes Diagnosis Extensions of the LCA models Resources and References Hypothetical Example: Identifying effective teachers Setting: Unsure how to identify an effective teacher Possible Indicators: Credential or Not? Promotes critical thinking Reflective Professional Development (P.D.) What would the data look like? Possible research questions: Are there specific characteristics that identify an effective teacher? Given known ideas of what an effective teacher is, what characteristics are important indicators? Are there background characteristics of the teachers that help classify them as effective? What could LCA tell us? To find groups of teacher that are similar based on observed characteristics Identify and accurately enumerate the number of groups of teachers Identify characteristics that indicate groups well Estimate the prevalence of the groups Classify teachers into classes The LCA Model Observed Continuous (y’s) or Categorical Items (u’s) Categorical Latent Class Variable (c) Continuous or Categorical Covariates (x) How is this modelingprocess conducted? Run through models imposing different numbers of classes Estimation via the EM algorithm Start with random split of people into classes. Reclassify based on a improvement criterion Reclassify until the best classification of people is found. Evaluating the Model Model Fit BIC and AIC X2 Statistic Lo-Mendell-Rubin Test (Tech 11) Standardized Residuals (Tech 10) Model Usefulness Substantive Interpretation Classification Quality Classification Tables Entropy 1st Data Example: Anti-Social Behavior Damaged property Fighting Shoplifting Stole $50 Stole $50 Use of force Seriously t