pred_matrix: Build the prediction design matrix based on new data and...

In LaMa: Fast Numerical Maximum Likelihood Estimation for Latent Markov Models

Build the prediction design matrix based on new data and model_matrices object created by make_matrices

Description

Build the prediction design matrix based on new data and model_matrices object created by make_matrices

Usage

pred_matrix(model_matrices, newdata, exclude = NULL)

Arguments

model_matrices	model_matrices object as returned from make_matrices
newdata	data frame containing the variables in the formula and new data for which to evaluate the basis
exclude	optional vector of terms to set to zero in the predicted design matrix. Useful for predicting main effects only when e.g. sd(..., bs = "re") terms are present. See mgcv::predict.gam for more details.

Value

prediction design matrix for newdata with the same basis as used for model_matrices

Examples

modmat = make_matrices(~ s(x), data.frame(x = 1:10))
Z_predict = pred_matrix(modmat, data.frame(x = 1:10 - 0.5))

LaMa documentation built on June 8, 2025, 1:53 p.m.