predict.TML: Predict method for "TML" objects

Description

Obtains predictions from a fitted Truncated Maximum Likelihood (TML) object.

Usage

# S3 method for TML
predict(object, newdata = NULL, ...)

Value

Returns a vector of predictions.

Arguments

object: An object of class "TML", usually, a result of a call to TML.noncensored or TML.censored.
newdata: Optionally, a vector, a matrix or a data frame containing the variables with which to predict. If omitted, the fitted values of object are returned.
...: Additional arguments affecting the predictions produced.

Details

newdata must have the same number of variables (that is of columns) as the model. If object is a model with an intercept, newdata must have a first column of 1.

Examples

Run this code

if (FALSE) {
     data(D243)
     Cost <- D243$Cost                             # Cost (Swiss francs)
     LOS  <- D243$LOS                              # Length of stay (days)
     Adm  <- D243$Typadm; Adm <- (Adm==" Urg")*1   # Type of admission 
                                                   # (0=on notification, 1=Emergency)

     # Fitting the model
     z    <- TML.noncensored(log(Cost)~log(LOS)+Adm, errors="logWeibull")

     # With a vector of data
     vec  <- c(1, 2.4, 1)
     predict(object = z, newdata = vec)
     # With a matrix of data
     mat  <- matrix(c(1,1,2.4,2.7,1,0), ncol=3)
     predict(z, mat)
     # With a data frame
     dat  <- as.data.frame(cbind("intercept"=c(1,1,1), "log(LOS)"=c(2.4,2.7,2.2), 
             "Adm"=c(1,0,1)))
     predict(z, dat)
}