Compositional (version 1.0)

glm.pcr: Principal component generalised linear models

Description

Principal component generalised linear models.

Usage

glm.pcr(y, x, k, oiko = "binomial", xnew = NULL)

Arguments

y

A numerical vector, either 0 and 1 (binary) or discrete (count) data.

x

The predictor variable(s), they have to be continuous.

k

A number at least equal to 1. How many principal components to use.

oiko

The type of regression to be used, "binomial" for binary response or "poisson" for count response.

xnew

If you have new data use it, otherwise leave it NULL.

Value

• A list including:
• model
  The summary of the glm model
• per
  The percentage of variance of the predictor variables retained by the k principal components.
• est
  The fitted or the predicted values (if xnew is not NULL).

Details

Principal component regression is performed with binary logistic or Poisson regression.

References

Jolliffe I.T. (2002). Principal Component Analysis.

See Also

pcr, alfa.pcr, alfapcr.tune, glm

Examples

library(MASS)
x<- iris[, 1:4]
y<- rbinom(150, 1, 0.6)
mod<- glm.pcr(y, x, k = 1, oiko = binomial)