Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

From |
Guillermo Montes <gmontes@childrensinstitute.net> |

To |
"statalist@hsphsun2.harvard.edu" <statalist@hsphsun2.harvard.edu> |

Subject |
st: Difference between factor score and linear prediction of latent variables after sem |

Date |
Mon, 14 Oct 2013 18:05:41 +0000 |

I estimated a sem model that regresses many observable predictors on two latent variables (SOC1 SOC2), each measured by 4 observable indicators. Then, I used the post estimation commands to calculate both the factor scores and the linear predictions of the latent variables using the commands below. Predict Lat*, xblatent(SOC1 SOC2) Predict Fac*, latent(SOC1 SOC2) http://www.stata.com/manuals13/sempredictaftersem.pdf The manual says factor scores are predicted values of latent variables. What is the difference between a factor score and a linear prediction of a latent variable? The numbers are only correlated .7 or so in my case. Thanks Guillermo Montes Ph.D. * * For searches and help try: * http://www.stata.com/help.cgi?search * http://www.stata.com/support/faqs/resources/statalist-faq/ * http://www.ats.ucla.edu/stat/stata/

**Follow-Ups**:**Re: st: Difference between factor score and linear prediction of latent variables after sem***From:*Maarten Buis <maartenlbuis@gmail.com>

- Prev by Date:
**RE: RE: RE: st: Tests of overidentifying restrictions with -ivregress-** - Next by Date:
**Re: st: RE: updated package -binscatter- in SSC** - Previous by thread:
**st: ROC-curves** - Next by thread:
**Re: st: Difference between factor score and linear prediction of latent variables after sem** - Index(es):