matrixpls (version 1.0.4)

predict.matrixpls: Predict method for matrixpls results

Description

The matrixpls method for the generic function predict predict. Predicts the reflective indicators of endogenous latent variables using estimated model and data for the indicators of exogenous latent variables

Usage

"predict"(object, newData, predictionType = "exogenous", means = NULL, ...)

Arguments

object

matrixpls estimation result object produced by the matrixpls function.

newData

A data frame or a matrix containing data used for prediction.

predictionType

"exogenous" (default) predicts indicators from exogenous composites. "redundancy" and "communality" are alternative strategies described by Chin (2010).

means

A vector of means of the original data used to calculate intercepts for the linear prediciton equations. If not provided, calculated from the new data or assumed zero.

...

All other arguments are ignored.

Value

a matrix of predicted values for reflective indicators of endogenous latent variables.

References

Wold, H. (1974). Causal flows with latent variables: Partings of the ways in the light of NIPALS modelling. European Economic Review, 5(1), 67–86. doi:10.1016/0014-2921(74)90008-7

Chin, W. W. (2010). How to write up and report PLS analyses. In V. Esposito Vinzi, W. W. Chin, J. Henseler, & H. Wang (Eds.), Handbook of partial least squares (pp. 655–690). Berlin Heidelberg: Springer.

See Also

Other post-estimation functions: ave, cr, effects.matrixpls, fitSummary, fitted.matrixpls, gof, htmt, loadings, r2, residuals.matrixpls