Become an expert in R — Interactive courses, Cheat Sheets, certificates and more!
Get Started for Free

coefvlm

Extract Model Coefficients

Description

Extracts the estimated coefficients from VLM objects such as VGLMs.

Usage

coefvlm(object, matrix.out = FALSE, label = TRUE, colon = FALSE)

Arguments

object

An object for which the extraction of coefficients is meaningful. This will usually be a vglm object.

matrix.out

Logical. If TRUE then a matrix is returned. The explanatory variables are the rows. The linear/additive predictors are the columns. The constraint matrices are used to compute this matrix.

label

Logical. If FALSE then the names of the vector of coefficients are set to NULL.

colon

Logical. Explanatory variables which appear in more than one linear/additive predictor are labelled with a colon, e.g., age:1, age:2. However, if it only appears in one linear/additive predictor then the :1 is omitted by default. Then setting colon = TRUE will add the :1.

Details

This function works in a similar way to applying coef() to a lm or glm object. However, for VGLMs, there are more options available.

Value

A vector usually. A matrix if matrix.out = TRUE.

Author(s)

Thomas W. Yee

References

Yee, T. W. and Hastie, T. J. (2003). Reduced-rank vector generalized linear models. Statistical Modelling, 3, 15–41.

See Also

Examples

zdata <- data.frame(x2 = runif(nn <- 200))
zdata <- transform(zdata, pstr0  = logitlink(-0.5 + 1*x2, inverse = TRUE),
                          lambda =   loglink( 0.5 + 2*x2, inverse = TRUE))
zdata <- transform(zdata, y2 = rzipois(nn, lambda, pstr0 = pstr0))

fit2 <- vglm(y2 ~ x2, zipoisson(zero = 1), data = zdata, trace = TRUE)
coef(fit2, matrix = TRUE)  # Always a good idea
coef(fit2)
coef(fit2, colon = TRUE)
VGAM

Vector Generalized Linear and Additive Models

v1.1-5
GPL-3
Authors
Thomas Yee [aut, cre], Cleve Moler [ctb] (author of several LINPACK routines)
Initial release
2021-01-13

We don't support your browser anymore

Please choose more modern alternatives, such as Google Chrome or Mozilla Firefox.