I'm looking at the psych package and the VSS tutorial, do I simply replace VSS with MAP? Like this:
MAP(x, n = 8, rotate = "varimax", diagonal = FALSE, fm = "pa", n.obs=NULL,plot=TRUE,title="Very Simple Structure",...)
or is there another way to do this? I've doing factor analysis right now and I'm using the elbow method on a scree plot. I'm trying to see if I can try to use Velicer's MAP criterion also
Check out the documentation for that function using ?MAP.
If there is nothing there, probably send an email to the author, listed at the package's CRAN page: CRAN Page for Psych
That package is made by the folks at this site. They probably have a mailing list: PersonalityProject.org
@Ryan Rosario
I finally figured it out:
install.packages("psych")
library("psych")
I ran the sample steps
my.VSS <- VSS(test.data,title="VSS of 24 mental tests")
and
VSS(sim.circ(nvar=24),fm="mle", title="VSS of 24 circumplex variables")
and
VSS(sim.item(nvar=24),fm="mle", title="VSS of 24 circumplex variables")
you get something like this as output (for the last input):
Very Simple Structure of VSS of 24 circumplex variables Call: VSS(x = sim.item(nvar = 24), fm = "mle", title = "VSS of 24 circumplex variables") VSS complexity 1 achieves a maximimum of 0.84 with 3 factors VSS complexity 2 achieves a maximimum of 0.87 with 8 factors
The Velicer MAP criterion achieves a minimum of 0.05 with 2 factors
Velicer MAP [1] 0.05 0.01 0.01 0.01 0.01 0.02 0.02 0.02
Very Simple Structure Complexity 1 [1] 0.44 0.84 0.84 0.80 0.75 0.76 0.80 0.80
Very Simple Structure Complexity 2 [1] 0.00 0.85 0.85 0.85 0.86 0.86 0.86 0.87
as the documentation says (highlighting above is mine):
"Wayne Velicer's MAP criterion has been added as an additional test for the optimal number of components to extract. Note that VSS and MAP will not always agree as to the optimal number."
In this case VSS with complexity of 1 and 2 gives an answer of 3 and 8 factors respectively while Velicer's MAP criterion gives 2.