Stata 15 help for estat mindices

[SEM] estat mindices -- Modification indices


estat mindices [, options]

options Description ------------------------------------------------------------------------- showpclass(pclassname) restrict output to parameters in specified parameter classes minchi2(#) display only tests with modification index (MI) > # -------------------------------------------------------------------------

pclassname Description ------------------------------------------------------------------------- scoef structural coefficients scons structural intercepts

mcoef measurement coefficients mcons measurement intercepts

serrvar covariances of structural errors merrvar covariances of measurement errors smerrcov covariances between structural and measurement errors

meanex means of exogenous variables covex covariances of exogenous variables ------------------------------------------------------------------------- all all the above none none of the above -------------------------------------------------------------------------


Statistics > SEM (structural equation modeling) > Testing and CIs > Modification indices


estat mindices is for use after sem but not gsem.

estat mindices reports modification indices for path coefficients and covariances that were constrained or omitted in the fitted model. Modification indices are score tests (Lagrange multiplier tests) for the statistical significance of the constrained parameters. See Sörbom (1989) and Wooldridge (2010, 421-428).


showpclass(pclassname) specifies that results be limited to parameters that belong to the specified parameter classes. The default is showpclass(all).

minchi2(#) suppresses listing paths with modification indices (MIs) less than #. By default, estat mindices lists values significant at the 0.05 level, corresponding to chi2(1) value minchi2(3.8414588). Specify minchi2(0) if you wish to see all tests.


See [SEM] example 5.


Setup . webuse sem_2fmm . sem (Affective -> a1 a2 a3 a4 a5) (Cognitive -> c1 c2 c3 c4 c5), cov(Affective*Cognitive@0)

Compute modification indices . estat mindices

Show all modification indices . estat mindices, minchi2(0)

Only show modification indices for covariances of measurement errors . estat mindices, showpclass(merrvar)

Stored results

estat mindices stores the following in r():

Scalars r(N_groups) number of groups

Matrices r(nobs) sample size for each group r(mindices_pclass) parameter class of modification indices r(mindices) matrix containing the displayed table values


Sörbom, D. 1989. Model modification. Psychometrika 54: 371-384.

Wooldridge, J. M. 2010. Econometric Analysis of Cross Section and Panel Data. 2nd ed. Cambridge, MA: MIT Press.

© Copyright 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index