All geek questions in one place

CFA in R (Lavaan) with ordinal data - is polychoric correlation included?

I would like to calculate confirmatory factor analysis (CFA) with ordinal data in R, using lavaan. The data is taken from a questionnaire containing 16 elements structured on the Likert scale.

I believe that a 4-factor model works best for my data. To calculate CFA, I looked for information and found a useful recommendation in this one.

The recommendation is to use DWLS estimation and polychoric correlation. I was able to calculate CFA with DWLS in Rusing a package lavaan. I found out that in Mplus the evaluation of DWLS or WLSMV, which is the same, uses polychoric correlation , unfortunately, I never used Mplus and would like to work with R, so I was wondering if lavaanthis is the same.

So far, I have calculated CFA as follows:

I indicated a model (model 4) with 4 factors (AV, AW, AB, AA), (each factor has 4 elements)

model.4='
AV =~ AVf1_+AVf2+AVf3+AVf4 
AW =~ AWf1+AW2+AWf3+AWf4 
AB =~ ABf1+ABf2+ABf3+ABf4 
AA =~ AAf1+AAf2+AAf3+AAf4'

Then I used a function "ordered"due to my ordered data, which is recommended in the packagelavaan

model.ord = cfa(model.4,data=Data,ordered=c(
"AVf1","AVf2","AVf3","AVf4",
"AWf1","AWf2","AWf3","AWf4",
"ABf1","ABf2","ABf3","ABf4",
"AAf1","AAf2","AAf3","AAf4"))

. (CFI, RMSEA ..). : , Mplus? - ? lavaan , lavCor, , , , , .

:

model.ord1 <- lavCor(cfa(model.4,data=Data,ordered=c(
 "AVf1","AVf2","AVf3","AVf4",
"AWf1","AWf2","AWf3","AWf4",
"ABf1","ABf2","ABf3","ABf4",
"AAf1","AAf2","AAf3","AAf4"))

))

> summary(model.ord1, fit=T) . .

: CFA ? , ?

+4
2

, lavaan, "" DWLS ,

,

inspect(fit, "sampstat")$cov

fit - cfa() ,

lavCor(fit, ordered = TRUE, group = NULL, output = "cor")

+2

Source: https://habr.com/ru/post/1665317/

More articles:


All Articles