Skip to contents

Extract Equations for a "nestedLogit" Model

Source: R/equatiomatic.R
extract_eq.nestedLogit.Rd

Provides an equatiomatic::extract_eq() method for "nestedLogit" objects to render the models as LaTeX equations in documents.

It extracts the LaTeX equation for each of the binary logit sub-models comprising a nested logit model, substituting the dichotomy name for the internal ..y placeholder used by nestedLogit().

Usage

extract_eq.nestedLogit(model, submodel = NULL, ...)

Arguments

model

a "nestedLogit" object.

submodel

character; name of a single dichotomy (e.g. "work"). When supplied, a single "equation" object is returned and renders directly in a knitr chunk. When omitted, equations for all dichotomies are returned as a named list of class "nestedLogit_equations".

...

additional arguments passed to equatiomatic::extract_eq(). For example, use use_coefs = TRUE to display fitted coefficients rather than symbols; wrap = TRUE to split the RHS across multiple lines; greek_colors, var_colors, etc. to color the symbols.

Value

When submodel is NULL, an object of class c("nestedLogit_equations", "list") containing one "equation" per dichotomy, named by the dichotomy. Individual equations can be extracted with $name or by passing submodel. When submodel is a dichotomy name, the single corresponding "equation" object is returned and renders directly in a knitr chunk.

Details

Internally, nestedLogit() fits each sub-model on a temporary response column named ..y, so equatiomatic::extract_eq() would render the response as ..y rather than the dichotomy name. This method replaces ..y with the name of each dichotomy.

Because _ is the subscript operator in LaTeX, any underscores in dichotomy names are replaced by . in the displayed equation (e.g., a dichotomy named fish_inv appears as fish.inv). This does not affect the names of the returned list, which retain the original R names.

See also

equatiomatic::extract_eq()

Examples

data("Womenlf", package = "carData")
wlf.nested <- nestedLogit(partic ~ hincome + children,
                 dichotomies = logits(work = dichotomy("not.work",
                                                       working = c("parttime", "fulltime")),
                                      full = dichotomy("parttime", "fulltime")),
                 data = Womenlf)
if (requireNamespace("equatiomatic", quietly = TRUE)) {
  equatiomatic::extract_eq(wlf.nested)
}
#> 
#> Dichotomy: work 
#> $$
#> \log\left[ \frac { P( \operatorname{work} ) }{ 1 - P( \operatorname{work} ) } \right] = \alpha + \beta_{1}(\operatorname{hincome}) + \beta_{2}(\operatorname{children}_{\operatorname{present}})
#> $$
#> 
#> Dichotomy: full 
#> $$
#> \log\left[ \frac { P( \operatorname{full} ) }{ 1 - P( \operatorname{full} ) } \right] = \alpha + \beta_{1}(\operatorname{hincome}) + \beta_{2}(\operatorname{children}_{\operatorname{present}})
#> $$