model: Describing Sampling Model for Imprecise Inferential Framework

In ipeglim: Imprecise Inferential Framework on Statistical Reasoning

Description

The function model is used to describe sampling models, specified by a symbolic description of the linear predictor in formula.

Usage

  model(formula, data,
    dist = c("poisson", "binom", "geom"), ztrunc = FALSE,
    verbose = FALSE)

Arguments

formula	an object of class formula; A symbolic description of the model to be fitted; The details of model specification are given under ‘Details’.
data	an optional data frame, list or environment containing variables used for a description of the model in formula. If not found in data, variables are taken from environment(formula), where the model is called.
dist	a sampling distribution of a response variable; Defaults to poisson. See ‘Details’.
ztrunc	a logical value; Is the zero truncated?; Defaults to FALSE.
verbose	a logical value; Be more verbose about the process by displaying messages; Defaults to FALSE.

Details

The function model is the first task on performing an imprecise inferential framework. To tag this stage, stage has the character string model that is the name of environment called.

All details are identical to those of formula in glm. In the context of regression, y~0 represents a model that does not involve any variables in data. y~1 represents a model that involve an intercept term, but no other variables in data. y~. represents a model that involve all variables in data.

Value

An object of class imprecise with the components:

xreg	the logical value, Is the model described in formula regression?
ztrunc	the logical value supplied.
formula	the formula supplied.
y	the model reponse used in formula.
X	the model matrix used in formula.
fit	the object of classes ztpreg or glm depending on the value of ztrunc; the model is fitted by a maximum likelihood method.
stage	the environment name called.
init	the list of estrimates for parameters in model and and its variance-covariance matrix.

Note

The current version provides the only sampling model poisson. In the near future, binomial and normal will be added.

Author(s)

Chel Hee Lee <[e-mail]>

References

Lee (2013) “Imprecise inferential framework”, PhD thesis.

See Also

glm, formula, ztpreg

Examples

## Not run: 
# not provided yet

## End(Not run)

ipeglim documentation built on May 2, 2019, 4:31 p.m.