contrast_models: Estimate the Difference Between Models

Description Usage Arguments Details Value Examples

Description

The posterior distributions created by perf_mod() can be used to obtain the posterior distribution of the difference(s) between models. One or more comparisons can be computed at the same time.

Usage

1
2
contrast_models(x, list_1 = NULL, list_2 = NULL,
  seed = sample.int(10000, 1))

Arguments

x

An object produced by perf_mod().

list_1, list_2

Character vectors of equal length that specify the specific pairwise contrasts. The contrast is parameterized as list_1[i] - list_2[i]. If the defaults are left to NULL, all combinations are evaluated.

seed

A single integer for sampling from the posterior.

Details

If a transformation was used when x was created, the inverse is applied before the difference is computed.

Value

A data frame of the posterior distribution(s) of the difference(s). The object has an extra class of "posterior_diff".

Examples

1
2
3
4
5
6
7
8
9
# Example objects from the "Getting Started" vignette at
#  https://topepo.github.io/tidyposterior/articles/Getting_Started.html

# File for pre-run model is at
ex_dat <- "https://bit.ly/2S1v6H9"

# load(load(url(ex_dat))

# head(glm_v_nnet)

tidyposterior documentation built on May 2, 2019, 2:49 p.m.