"Could not compute standard errors" and "The variance-covariance matrix of the estimated parameters does not appear to be positive definite!"

Question

I've been stuck on this assignment for days. Can someone please help me understand what I'm doing wrong? I've included a picture of the path diagram and labels for each step to make my thought process clear. I'm new to SEM and the model would be the presented here.

First, I conducted the multiple group assessment:

mod.mg1a = "

#Variances

crit ~~ crit
warm ~~ warm

trust ~~ trust

never ~~ never
moral ~~ moral
han ~~ han
good ~~ good

#Regression/Causal Path

trust ~ warm
trust ~ crit

#Factor Loadings

trust =~ never + moral + han + good

"
fit.mg1a = lavaan(mod.mg1a,data=mach,group="gen")
summary(fit.mg1a)

mod.mg1b = "
#Variances

crit ~~ crit
warm ~~ warm

trust ~~ trust

never ~~ never
moral ~~ moral
han ~~ han
good ~~ good

#Regression/Causal Path

trust ~ warm
trust ~ crit

#Factor Loadings

trust =~ never + moral + han + good

"
fit.mg1b = lavaan(mod.mg1b,data=mach,group="gen")
summary(fit.mg1b)

anova(fit.mg1a, fit.mg1b)

This return the following warnings:

***Warning in lav_partable_check(lavpartable, categorical = lavoptions$categorical,  :
  lavaan WARNING: automatically added intercepts are set to zero:
    [warm crit warm crit]
Warning in lav_model_vcov(lavmodel = lavmodel, lavsamplestats = lavsamplestats,  :
  lavaan WARNING:
    Could not compute standard errors! The information matrix could
    not be inverted. This may be a symptom that the model is not
    identified.***

----------

***Warning in lavTestLRT(object = object, ..., model.names = NAMES) :
  lavaan WARNING: some models have the same degrees of freedom***

The following assess the comparison with the model with all parameters constrained to be equal:

    fit.con = lavaan(mod.mg1a,data=mach, group="gen", group.equal=c(
      "loadings","lv.covariances","intercepts","means","residuals",
      "lv.variances","regressions"))

which returns:

***Warning in lav_partable_check(lavpartable, categorical = lavoptions$categorical,  :
  lavaan WARNING: automatically added intercepts are set to zero:
    [warm crit warm crit]
Warning in lav_model_vcov(lavmodel = lavmodel, lavsamplestats = lavsamplestats,  :
  lavaan WARNING:
    The variance-covariance matrix of the estimated parameters (vcov)
    does not appear to be positive definite! The smallest eigenvalue
    (= 7.438519e-15) is close to zero. This may be a symptom that the
    model is not identified.***

Grateful for any guidance.

"Could not compute standard errors" and "The variance-covariance matrix of the estimated parameters does not appear to be positive definite!"

0 Answers0