predict.glmmadmb: Prediction for glmmADMB models

In bbolker/glmmadmb: Generalized Linear Mixed Models using 'AD Model Builder'

Description

Generates predicted values, standard errors and confidence intervals for glmmADMB fits

Usage

## S3 method for class 'glmmadmb'
predict(object,
 newdata = NULL, type = c("link", "response"),
  se.fit = FALSE, interval = c("none", "confidence"),
  random = ~0, level = 0.95, ...)

Arguments

object	A fitted model from glmmadmb
newdata	An optional data frame in which to look for variables with which to predict. If omitted, the fitted values are used.
type	Whether to return predictions on the scale of the linear predictor ("link") or the scale of the data ("response").
se.fit	A switch indicating if standard errors are required.
interval	What type of confidence intervals to return
random	Specification of random effects to use (STUB)
level	Tolerance/confidence level
...	further arguments passed to or from other methods.

Details

Produces predicted values from the model, based on evaluating the model with 'newdata' (if specified). If the logical 'se.fit' is 'TRUE', standard errors are calculated (this is only available on the link scale). It

Value

predict.lm produces a vector of predictions or a data frame of predictions and bounds with column names fit, lwr, and upr if interval is set. If se.fit is TRUE, a list with the components fit (vector or matrix as above) and se.fit (standard error of predicted means) is returned.

Note

• Prediction is currently available only at the population level (i.e. with all random effects terms set to zero).

• Confidence intervals and standard errors neglect uncertainty due to random effects, as well as the uncertainty of random effects. For more accurate confidence intervals, use MCMC-sampling methods.

Author(s)

Ben Bolker (partially copied from predict.lm)

Examples

getdata("OwlModel")
pp <- predict(OwlModel,interval="confidence",type="response")
pframe <- data.frame(obs=Owls$NegPerChick,pp)
with(pframe,plot(obs,fit,ylim=c(0,8)))
with(pframe,arrows(obs,lwr,obs,upr,length=0))
abline(a=0,b=1,col=2,lty=2) ## 1-to-1 line

bbolker/glmmadmb documentation built on May 11, 2019, 9:29 p.m.