um(tt))
Numerous caveats regarding using C-Alpha apply. And because you have the
factor loading you have the reliability of the factor. You don't need
C-Alpha.
Johannes Moser
Sent by: r-help-boun...@r-project.org
02/14/2014 05:24 PM
To
r-help@r-project.org,
cc
Subject
[R] ps
Many of the statistics reported don't make sense with only two
items--for example the alpha if an item is dropped makes no sense
because dropping an item leaves only one remaining.
Best,
Ista
On Fri, Feb 14, 2014 at 5:24 PM, Johannes Moser wrote:
> Dear R-help,
>
> I try to estimate alpha for a
Dear R-help,
I try to estimate alpha for a factor that loads onto two items, using
the psych-package (newest version).
The data is from the boston housing data set.
The problem I face can be reproduced by the following approximation of
the correlation matrix:
library("psych")
tt <- cbind(c(1,0
3 matches
Mail list logo
