Why Your SEM or CFA Model DOESN'T FIT

When your confirmatory factor analysis or structural equation model doesn't fit, there are a few things you can do to investigate the matter further. QuantFish instructor Dr. Christian Geiser walks you through some tips about how to proceed when your model fit is poor.
#Mplus #Mplusforbeginners #statistics #SEM #CFA #modelfit #geiser #quantfish #statisticstutorials
FREE weekly stats tips: mailchi.mp/goq...
FREE statistics workshops: www.goquantfis...
Get Dr. Geiser's FREE MPLUS FOR BEGINNERS COURSE:
www.goquantfis...
FREE POWER ANALYSIS & SIMULATION MINI-COURSE: www.goquantfis...
MPLUS FACTOR ANALYSIS COURSE: www.goquantfis...
Dr. Geiser's BOOKS:
****Longitudinal Structural Equation Modeling with Mplus: amzn.to/3ekOLOW
****Data Analysis with Mplus: amzn.to/3eg9vY4
ON-DEMAND MPLUS COURSES:
****SEM with Mplus: www.goquantfis...
****Multilevel Modeling with Mplus: www.goquantfis...
****Latent Class Analysis with Mplus: www.goquantfis...
GET IN TOUCH with DR. GEISER:
****Facebook: / christiangeiserauthor
****Website: christiangeise...
ABOUT THIS INSTRUCTOR:
Dr. Christian Geiser is a quantitative psychologist, author of two books on Mplus, and a leader in the development of latent variable techniques for complex data. With his accessible books and sought-after workshops, he has helped thousands of researchers and students around the world to achieve their analytic goals.
ABOUT QUANTFISH:
We bring top-level stats training from the world's leading methodologists to researchers and students all over the world. Learn more at goquantfish.com.
Some affiliate links may be included at no additional cost to purchasers.

[@nianalavallee3165]

Great video! Do you have any resource recommendations for someone new to latent growth curve modelling using MPlus?

[@QuantFish]

Have you seen my playlist on latent growth curve models in Mplus?
th-cam.com/play/PL-kVjeOVYChrpQMBEAp926r8S83cfZp4V.html
Best, Christian Geiser

[@VK2024X]

Hi Christian,
Do you have any references that we can use in a paper to support the idea that a model can't be too restrictive? Thank you!

[@QuantFish]

Hi Kai,
I'm not sure I understand. A model CAN BE too restrictive. This is typically indicated by a significant chi-square test of model fit.
Best, Christian Geiser

[@anav3565]

My Model doesnt fit. How can I fix convergence? Its is a Model with second level endogeneous and exogeneous latent variables

[@QuantFish]

Convergence problems are often due to (theoretical or empirical) model non-identification (underidentified models) or a model that is too complex (e.g., too many factors). In other (more benign) cases, non-convergence can be due to bad starting values (e.g., when observed variables on the same factor have very different variances), in which case it can be fixed by providing user-defined starting values for loadings etc. A separate video on convergence problems will be coming soon, so stay tuned! CG

[@anav3565]

@@QuantFish ThankU! I have a week working on that. I will be waiting.