textir (version 1.8-8)

predict.pls: pls predict

Description

Predict function for Partial Least Squares

Usage

## S3 method for class 'pls':
predict( object, newdata, type="response", ... )

Arguments

object

An output object from the pls function.

newdata

An nrow(object$loadings)-column matrix of multinomial phrase/category counts for new documents/observations. Can be either a simple matrix or a simple_triplet_matrix.

type

If "response", predictions scaled to the original response. If "reduction", fitted partial least squares directions.

...

Additional unused arguments.

Value

• Output is either a vector of predicted resonse or an nrow(newcounts) by ncol(object$loadings) matrix of pls directions for each new observation.

Details

This function returns the pls projection $X\Phi$ for new covariates, or $\alpha + \beta*X\phi$ if type="response" with regression coefficients taken from object$fwdmod.

References

Taddy (2012), Multinomial Inverse Regression for Text Analysis. http://arxiv.org/abs/1012.2098

See Also

pls, congress109