LFMM generative data sampler

Sample data with the latent factor model.

lfmm_sampler(n, p, K, outlier.prop, cs, sigma = 0.2, B.sd = 1, B.mean = 0,
  U.sd = 1, V.sd = 1)

Arguments

n	number of observations.
p	number of output variables.
K	number of latent variables.
outlier.prop	proportion of outlier.
cs	correlation with between X and U.
sigma	standard deviation of the error.
B.sd	standard deviation of B.
B.mean	mean of B.
U.sd	standard deviation of U.
V.sd	standard deviation of V.

Value

A list with sampled data.

Details

lfmm_sample() sample an output matrix Y and primary matrix X such that

Y = U t(V) + X t(B) + Epsilon.

U,V, B and Epsilon are sampled with normal multivariate distribution. Moreover U and X are such that cor(U[,i], X) = cs[i].

Examples

dat <- lfmm_sampler(n = 100, p = 1000, K = 3,
                    outlier.prop = 0.1,
                    cs = c(0.8),
                    sigma = 0.2,
                    B.sd = 1.0, B.mean = 0.0,
                    U.sd = 1.0, V.sd = 1.0)
#> length(cs) < K. Filling cs with zero