[R] Difference between cor_auto (qgraph package) and lavCor (lavaan package)

Enjalbert Line |@enj@|bert @end|ng |rom y@hoo@|r
Fri Apr 19 09:17:18 CEST 2019

I would like to know the diffrence between 2 commands : cor_auto (from qgraph package) and lavCor (from lavaan package) to compute a polychoric correlation matrix in order to do a network analysis.
I have the responses to the SF-36 questionnaire (36 items with ordered responses) and I would like to have a polychoric correlation matrix by following the Sacha Epskamp's method. But I have a warning if using cor_auto :  "Correlation matrix is not positive definite. Finding nearest positive definite matrix". I can ignore this warning or not ? Because I try to do a polychoric matrix in STATA software and I do not have a warning message.
And I don't understand the difference between lavCor command, because When I use lavCor, I do not have the warning message either.
//cor.auto1 <- cor_auto(Data_1it)
//cor.lav1<-lavCor(Data_1it, ordered=names(Data_1it))
Thank you in advance for your answer. 

	[[alternative HTML version deleted]]

More information about the R-help mailing list