test_data

A small normal dataset with a proportional
outcome to illustrate the use of this package.
The outcome has mean
<code>expit(0.5 + 0.1 * x_var1 + 0.2 * x_var2 + 0.3 * x_var3 + SUBJ_VAL)</code>
where SUBJ_VAL are the values of the random effect
The SD of y is then shrunk by 0.9 relative to a binomial distribution,
and then beta values are generated. Arbitrarily close to the endpoints
gives zeros and ones.

datasets

Performs bootstrap resampling for most models that update() works for. There
are two primary functions: bootstrap_model() performs block resampling if random effects
are present, and case resampling if not; bootstrap_ci() converts output from
bootstrap model runs into confidence intervals and p-values. By default,
bootstrap_model() calls bootstrap_ci().
Package motivated by Humphrey and Swingley (2018) <arXiv:1805.08670>.

Colman Humphrey

glmmboot

Bootstrap Resampling for Mixed Effects and Plain Models

test_data function

A data frame with 300 rows and 4 variables:<dl class="dl-horizontal">
 <dt>x_var1</dt><dd>independent normally distributed variable</dd>
 <dt>x_var2</dt><dd>independent normally distributed variable</dd>
 <dt>x_var3</dt><dd>independent normally distributed variable</dd>
 <dt>subj</dt><dd>levels of random effect</dd>
 <dt>y</dt><dd>outcome: lives in interval [0,1]</dd>
</dl>

Format

Simulated data containing three fixed effects and one random effect — test_data

A data frame with 300 rows and 4 variables:<dl class='dl-horizontal'>
 <dt>x_var1</dt><dd>independent normally distributed variable</dd>
 <dt>x_var2</dt><dd>independent normally distributed variable</dd>
 <dt>x_var3</dt><dd>independent normally distributed variable</dd>
 <dt>subj</dt><dd>levels of random effect</dd>
 <dt>y</dt><dd>outcome: lives in interval [0,1]</dd>
</dl>

test_data: Simulated data containing three fixed effects and one random effect

Description

Usage

Arguments

Format