Home  /  Resources & support  /  Training  /  Organizational training  /  Structural equation modeling using Stata

Organizational training

Structural equation modeling using Stata


Description

This course introduces structural equation modeling and its implementation in Stata. Stata allows for fitting structural equation models in two ways—by using the command syntax or using the SEM Builder to draw path diagrams. Examples will demonstrate both approaches, starting with linear regression up to confirmatory factor analysis and growth curve modeling. Model identification and evaluation will also be extensively discussed. The course concludes with a brief introduction to multilevel models and generalized linear models within the SEM framework.

Request this course

Course topics

  • Overview of linear structural equation modeling
    • Model description
    • Process of fitting and evaluating structural equation models
    • Description of path diagrams
  • Stata’s tools for SEM
    • Fitting models with the sem command
    • Fitting models with the SEM Builder by drawing path diagrams
    • Using the ssd commands to work with summary statistics
  • Details on specific types of structural equation models
    • Models with observed variables
      • Linear regression
      • Path analysis
      • Mediation analysis
    • Models with latent and observed variables
      • Confirmatory factor analysis
      • Full structural equation models
      • Latent growth curves
    • Models with multiple groups
  • Testing and interpreting linear SEM results
    • Standardized results
    • Direct, indirect, and total effects
    • Goodness-of-fit statistics
    • Modification indices
    • Model comparison
  • Overview of generalized structural equation modeling and the gsem command
    • Fitting multilevel models
    • Fitting models with binary, ordered, count, and categorical outcomes
  • Report results from a structural equation modeling analysis

Prerequisite

Knowledge of basic statistical techniques such as correlation and linear regression.

Notes

This course is available in-person or virtually. In-person training courses generally run for eight hours per day and include morning and afternoon breaks and a lunch break. Virtual training courses are typically divided into three- to four-hour daily sessions. You can arrange a convenient schedule with your instructor.

Request this course