effects (version 4.2-1)

summary.eff: Summarizing and Printing Effects

Description

summary, print, and as.data.frame methods for objects created using the effects package.

Usage

# S3 method for eff
print(x, type=c("response", "link"), ...)
# S3 method for effpoly
print(x, type=c("probability", "logits"), ...)
# S3 method for efflatent
print(x, ...)
# S3 method for efflist
print(x, ...)
# S3 method for mlm.efflist
print(x, ...)
# S3 method for summary.eff
print(x, ...)
# S3 method for eff
summary(object, type=c("response", "link"), ...)
# S3 method for effpoly
summary(object, type=c("probability", "logits"), ...)
# S3 method for efflatent
summary(object, ...)
# S3 method for efflist
summary(object, ...)
# S3 method for mlm.efflist
summary(object, ...)
# S3 method for eff
as.data.frame(x, row.names=NULL, optional=TRUE, 
        type=c("response", "link"), ...)
# S3 method for efflist
as.data.frame(x, row.names=NULL, optional=TRUE, type, ...)
# S3 method for effpoly
as.data.frame(x, row.names=NULL, optional=TRUE, ...)
# S3 method for efflatent
as.data.frame(x, row.names=NULL, optional=TRUE, ...)
# S3 method for eff
vcov(object, ...)

Value

The print methods return the fitted values in tables. The summary methods return the fitted values and 95 percent condifence intervals, also in tables. The as.data.frame method returns fitted values, standard errors, and 95 percent confidence intervals as a data frame, or as a list of data frames for the efflist method. The vcov method returns the covariance matrix of the fitted values.

Arguments

x, object

an object consisting of fitted values and other information needed to draw effects plots that is produced by functions in the effects package.

type

fitted values are by default printed by these functions in the "response" scale. For models with a link function like a GLM, fitted values in the linear predictor scale are obtained by setting type="link". For polytomous response models setting type="logits" returns fitted values in the logit scale.

row.names, optional

arguments to as.data.frame not used by these methods.

...

other arguments passed on

Author

John Fox and Jangman Hong.

Examples

mod.cowles <- glm(volunteer ~ sex + neuroticism*extraversion,
                  data=Cowles, family=binomial)
eff.cowles <- predictorEffects(mod.cowles)
print(eff.cowles)
print(eff.cowles[["neuroticism"]], type="link")
summary(eff.cowles[["neuroticism"]], type="link")
as.data.frame(eff.cowles)
# covariance matrix of fitted values in linear predictor scale
vcov(eff.cowles[[1]])