binGroup (version 2.2-1)

predict.gt: Predict Method for Group Testing Model Fits

Description

Obtains predictions for individual observations and optionally estimates standard errors of those predictions from objects of class "gt" or "gt.mp" returned by gtreg and gtreg.mp, respectively.

Usage

# S3 method for gt
predict(object, newdata, type = c("link", "response"),
 se.fit = FALSE, conf.level = NULL, na.action = na.pass, ...)

Arguments

object

a fitted object of class "gt" or "gt.mp".

newdata

optionally, a data frame in which to look for variables with which to predict. If omitted, the fitted linear predictors are used.

type

the type of prediction required. The option "link" is on the scale of the linear predictors; the alternative "response" is on the scale of the response variable. Thus for the binomial model the "link" predictions are of log-odds (probabilities on logit scale) and type = "response" gives the predicted probabilities.

se.fit

logical switch indicating if standard errors are required.

conf.level

confidence level of the interval of the predicted values.

na.action

function determining what should be done with missing values in newdata. The default is to predict NA.

…

currently not used

Value

If se = FALSE, a vector or matrix of predictions. If se = TRUE, a list with components

fit

Predictions

se.fit

Estimated standard errors

lower

Lower bound of the confidence interval if calculated

upper

Upper bound of the confidence interval if calculated

Details

If newdata is omitted the predictions are based on the data used for the fit. When newdata is present and contains missing values, how the missing values will be dealt with is determined by the na.action argument. In this case, if na.action = na.omit omitted cases will not appear, whereas if na.action = na.exclude they will appear (in predictions and standard errors), with value NA. See also napredict.

Examples

# NOT RUN {
data(hivsurv)

fit1 <- gtreg(formula = groupres ~ AGE + EDUC., data = hivsurv,  
  groupn = gnum, sens = 0.9, spec = 0.9, linkf = "logit", method = "V")
pred.data <- data.frame(AGE = c(15, 25, 30), EDUC. = c(1, 3, 2))
predict(object = fit1, newdata = pred.data, type = "link", se.fit = TRUE)
predict(object = fit1, newdata = pred.data, type = "response", 
  se.fit = TRUE, conf.level = 0.9)
predict(object = fit1, type = "response", se.fit = TRUE, conf.level = 0.9)


# }