Computes projected training data X for given dimension 'k'.
Returns B'X. That is, it computes the projection of the n x p design matrix X on the column space of B of dimension k.
## S3 method for class 'cve' directions(object, k, ...)
the n x k dimensional matrix X B where B is the cve-estimate for dimension k.
# create B for simulation (k = 1) B <- rep(1, 5) / sqrt(5) set.seed(21) # creat predictor data x ~ N(0, I_p) x <- matrix(rnorm(500), 100, 5) # simulate response variable # y = f(B'x) + err # with f(x1) = x1 and err ~ N(0, 0.25^2) y <- x %*% B + 0.25 * rnorm(100) # calculate cve with method 'mean' for k = 1 set.seed(21) cve.obj.mean <- cve(y ~ x, k = 1, method = 'mean') # get projected data for k = 1 x.proj <- directions(cve.obj.mean, k = 1) # plot y against projected data plot(x.proj, y)
Please choose more modern alternatives, such as Google Chrome or Mozilla Firefox.