logitRng

This function takes prior / posterior draws of the Bayesian logit model,
applies theinverse logit (logistic) transformation to obtain probabilities,
and then generates random samples from binomial distributions.

A toolkit for causal inference in experimental and observational
studies. Implements various simple Bayesian models including linear,
negative binomial, and logistic regression for impact estimation.
Provides functionality for randomization and checking baseline equivalence
in experimental designs. The package aims to simplify the process of
impact measurement for researchers and analysts across different fields.
Examples and detailed usage instructions are available at
<https://book.martinez.fyi>.

Ignacio Martinez

Impact Measurement Toolkit

logitRng function

<dl><dt>alpha</dt>
<dd>Numeric. A draw of alpha param from the logit model</dd>
<dt>tau</dt>
<dd>Numeric. A draw of tau param from the logit model</dd>
<dt>beta</dt>
<dd>Vector. A draw of beta params from the logit model</dd>
<dt>treat</dt>
<dd>A 0 / 1 vector of treatment indicator</dd>
<dt>X</dt>
<dd>Data to be predicted</dd>
<dt>N</dt>
<dd>Numeric. Size of the sample, should depend on size of the data.</dd></dl>

Arguments

Calculate logit link and sample from binomial distribution — logitRng

<dl>

<dt>alpha</dt>
<dd>Numeric. A draw of alpha param from the logit model</dd>


<dt>tau</dt>
<dd>Numeric. A draw of tau param from the logit model</dd>


<dt>beta</dt>
<dd>Vector. A draw of beta params from the logit model</dd>


<dt>treat</dt>
<dd>A 0 / 1 vector of treatment indicator</dd>


<dt>X</dt>
<dd>Data to be predicted</dd>


<dt>N</dt>
<dd>Numeric. Size of the sample, should depend on size of the data.</dd>

</dl>

logitRng: Calculate logit link and sample from binomial distribution

Description

Usage

Value

Arguments