Displaying 1 result from an estimated 1 matches for "mypromax".
2003 May 13
0
bug in promax?
...809487
[2,] 0.90713821 -0.11197901
[3,] 0.79547453 0.06260245
[4,] 0.05020993 0.86729962
[5,] 0.11747045 0.72788738
[6,] -0.12182636 0.72904497
Although the values are quite close to the SAS solution, there is
nevertheless a small mismatch. The following slightly edited function
of promax
mypromax <- function (x, m = 3)
{
if (ncol(x) < 2)
return(x)
dn <- dimnames(x)
xx <- varimax(x)
x <- xx$loadings
x1 <- diag(1/sqrt(diag(x %*% t(x)))) %*% x
Q <- x1 * abs(x1)^(m - 1)
U <- lm.fit(x, Q)$coefficients
d <- diag(solve(t(U) %*% U...