cbsem (version 1.0.0)

boottestgscm: Testing two segmentations of a GSC model

Description

boottestgscm computes a confidence interval for the difference of weighted average of averages of coefficients of determination for two segmentations of a GSC model For a one sided alternative hypothesis the error alpha has to be duplicated

Usage

boottestgscm(dat, B, indicatorx, indicatory, loadingx = FALSE,
  loadingy = FALSE, member1, member2, alpha, inner = FALSE)

Arguments

dat

(n,p)-matrix, the values of the manifest variables. The columns must be arranged in that way that the components of refl are (absolutely) increasing.

B

(q,q) lower triangular matrix describing the interrelations of the latent variables: b_ij = 1 regression coefficient of eta_j in the regression relation in which eta_i is the depend variable b_ij = 0 if eta_i does not depend on eta_j in a direct way (b_ii = 0 !)

indicatorx

vector describing with which exogenous composite the X-variables are connected

indicatory

vector describing with which endogenous composite the Y-variables are connected

loadingx

logical FALSE when there are no loadings for the X-variables in the model

loadingy

logical FALSE when there are no loadings for the Y-variables in the model

member1

vector of length n, indicating the cluster the observation belongs to for the first clustering

member2

vector of length n, indicating the cluster the observation belongs to for the second clustering

alpha

scalar, significance level ( = 1 - confidence level )

inner

Boolean, should a inner bootstrap loop be computed?

Value

KI vector with the confidence bounds; positive lower limit indicates significant superiority of first clustering, negative upper limit of second clustering.

Examples

# NOT RUN {
  data(twoclm)
  member1 <- c(rep(1,50),rep(2,50))
  member2 <- twoclm[,10]
  dat <- twoclm[,-10]
  B <- matrix(c( 0,0,0, 0,0,0, 1,1,0),3,3,byrow=TRUE)
  indicatorx <- c(1,1,1,2,2,2)
  indicatory <- c(1,1,1)   
  boottestgscm(dat,B,indicatorx,indicatory,loadingx=FALSE,loadingy=FALSE,
               member2,member1,0.1,inner=FALSE)
# }