GPArotation (version 2022.10-2)

Random.Start: Generate a Random Orthogonal Rotation

Description

Random orthogonal rotation to use as Tmat matrix to start GPForth or GPFoblq.

Usage

Random.Start(k)

Value

An orthogonal matrix.

Arguments

k

An integer indicating the dimension of the square matrix.

Author

Coen A. Bernaards and Robert I. Jennrich with some R modifications by Paul Gilbert

Details

The random start function produces an orthogonal matrix with columns of length one based on the QR decompostion.

See Also

GPForth, GPFoblq, oblimin

Examples

   Global.min <- function(A,method,B=10){
      fv <- rep(0,B)
      seeds <- sample(1e+7, B)
      for(i in 1:B){
    	cat(i," ")
    	set.seed(seeds[i])
    	gpout <- GPFoblq(A=A, Random.Start(ncol(A)), method=method)
    	dtab <- dim(gpout$Table)
    	fv[i] <- gpout$Table[dtab[1],2]
    	cat(fv[i], "\n")
      }
      cat("Min is ",min(fv),"\n")
      set.seed(seeds[order(fv)[1]])
      ans <- GPFoblq(A=A, Random.Start(ncol(A)), method=method)
      ans
      }

   data("Thurstone", package="GPArotation")

   Global.min(box26,"simplimax",10)