MODIFICATION Indices in Mplus

Поділитися
Вставка
  • Опубліковано 4 вер 2022
  • QuantFish instructor Dr. Christian Geiser explains how to obtain and interpret modification indices when running structural equation or confirmatory factor models in the Mplus software.
    #Mplus #statistics #SPSS #mplusforbeginners #sem #cfa #geiser #quantfish
    FREE weekly stats tips: christiangeiser.com/newsletter
    Get Dr. Geiser's FREE POWER ANALYSIS MINI-COURSE: www.goquantfish.com/courses/s...
    FREE PATH ANALYSIS & MEDIATION MINI-COURSE
    www.goquantfish.com/courses/p...
    MPLUS FOR BEGINNERS COURSE: www.goquantfish.com/courses/m...
    Consulting inquiries: christiangeiser.com
    Dr. Geiser's BOOKS:
    ****Longitudinal Structural Equation Modeling with Mplus: amzn.to/3ekOLOW
    ****Data Analysis with Mplus: amzn.to/3eg9vY4
    ON-DEMAND MPLUS COURSES:
    ****MPlus from Scratch: www.goquantfish.com/courses/m...
    ****Multilevel Modeling with Mplus: www.goquantfish.com/courses/m...
    ****Latent Class Analysis with Mplus: www.goquantfish.com/courses/l...
    GET IN TOUCH with DR. GEISER:
    ****Facebook: / christiangeiserauthor
    ****Website: christiangeiser.com
    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. Sign up for his newsletter at christiangeiser.com.
    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.

КОМЕНТАРІ • 8

  • @justinbuckingham2226
    @justinbuckingham2226 Рік тому

    Thanks for the helpful videos! In this video you explain WITH statements. What are BY statements in the model modification indices section of MPlus output?

    • @QuantFish
      @QuantFish  Рік тому

      Hi Justin,
      The BY statements refer to factor loadings.
      Best, Christian Geiser

    • @justinbuckingham2226
      @justinbuckingham2226 Рік тому

      @@QuantFish Thanks for the quick reply!

  • @Paolo-tu2ft
    @Paolo-tu2ft Рік тому

    Thanks for This useful video Dr. Geiser. I would like to ask about one of your published books. I cannot the one titled "Advanced Multivariate Data Analysis with Mplus". Is there a way to obtain it and in English? Thanks in advance!

    • @QuantFish
      @QuantFish  Рік тому

      Hi Paolo, Thank you for asking. Unfortunately, this book never materialized. Best, Christian Geiser

  • @daisyo.6666
    @daisyo.6666 9 місяців тому

    How does one know based on the modification indices when to remove a factor? It seems that they always suggest adding parameters, not removing them. What if the misspecification occurs because we are loading an indicator to the wrong factor, how can the modification indices let us know that that is happening?

    • @QuantFish
      @QuantFish  9 місяців тому +1

      Hi Daisy,
      Modification indices (MIs) refer to underspecified models (models in which certain types of parameters are missing), not overspecified models. MIs are not going to show you when you have too many parameters (e.g., too many factors) because having too many parameters typically does not cause overall chi-square model misfit.
      Modification indices may suggest cross-loadings if those are the source of chi-square model misfit (model underspecification, missing parameters). Overall, you should not overestimate the value of MIs. MIs are completely atheoretical and often, suggested modifications do not make theoretical or substantive sense. Resulting modified models may be non-sensical or may capitalize on chance. I only use MIs as ONE diagnostic tool to help me understand why a model does not fit. I would never base model respecification solely on MIs.
      Best, Christian Geiser

    • @daisyo.6666
      @daisyo.6666 9 місяців тому

      @@QuantFish thank you!