Rdimtools (version 0.1.2)

do.fa: Exploratory Factor Analysis

Description

do.fa is an optimization-based implementation of a popular technique, Exploratory Factor Analysis. This link explains similarities and intrinsic differences between a closely-related method of Principal Component Analysis (PCA).

Usage

do.fa(X, ndim = 2, preprocess = "center", maxiter = 1000,
  tolerance = 1e-10)

Arguments

X

an (n-by-p) matrix or data frame whose rows are observations and columns represent independent variables.

ndim

an integer-valued number of loading variables, or target dimension.

preprocess

an additional option for preprocessing the data. Default is ``center'' and other methods of ``decorrelate'', or ``whiten'' are supported. See also aux.preprocess for more details.

maxiter

maximum number of iterations for updating.

tolerance

stopping criterion in a Frobenius norm.

Value

a named list containing

Y

an (n-by-ndim) matrix whose rows are embedded observations.

trfinfo

a list containing information for out-of-sample prediction.

projection

a (p-by-ndim) whose columns are basis for projection.

loadings

a (p-by-ndim) matrix whose rows are extracted loading factors.

noise

a length-p vector of estimated noise.

References

spearman_general_1904Rdimtools

Examples

# NOT RUN {
## generate data
X = aux.gensamples()

## 1. use centered data
output1 <- do.fa(X,ndim=2)

## 2. use decorrelated data
output2 <- do.fa(X,ndim=2,preprocess="decorrelate")

## 3. use whitened data
output3 <- do.fa(X,ndim=2,preprocess="whiten")

## Visualize three different projections
par(mfrow=c(1,3))
plot(output1$Y[,1],output1$Y[,2],main="centered")
plot(output2$Y[,1],output2$Y[,2],main="decorrelated")
plot(output3$Y[,1],output3$Y[,2],main="whitened")

# }