To test it can be used the mtcars which have non-parametric distribution. I am developing a factor analysis. My data is non-parametric in nature. Therefore, according to the literature, it is recommended to apply the Spearman test. I'm using fuction:
root.fa2 <- principal(dt,
nfactors = 3,
rotate = 'varimax',
scores=T,
residuals =T,
oblique.scores=T,
method="regression",
spearman="cor",
use = "all.obs")
By default, she uses the option cor = "cor" applying the Person test. However, this is indicated for parametric data. The spearman = "cor" option is valid for the function. However, this error is returning -> Error in stats::varimax(loadings, ...): unused argument (spearman = "cor"). This only happens when I define a nfactors > 1.
The documentation is not a clear as it might be here, but looking at the documentation for MixedCor
the following works and gives you your scores:
root.fa2 <- principal(mtcars, nfactors = 3,
rotate = 'varimax', scores=TRUE, residuals=TRUE, oblique.scores=TRUE,
method="regression", use = "all.obs", cor="spearman")
Note. It is good practice to spell out TRUE
and FALSE
since they are reserved words. T
and F
will usually work, but they are not reserved so that you can accidentally assign T
or F
to a value in some other part of your code.
The technical post webpages of this site follow the CC BY-SA 4.0 protocol. If you need to reprint, please indicate the site URL or the original address.Any question please contact:yoyou2525@163.com.