sample_cm_per_click

Adds 4 new nested columns to the input_df: `beta_params`,
 `gamma_params_rev`, `gamma_params_cost`and `samples`

Uses simple Bayesian conjugate prior update rules to calculate
the win probability of each option, value remaining in the test, and
percent lift over the baseline for various marketing objectives.
References:
Fink, Daniel (1997) "A Compendium of Conjugate Priors" <https://www.johndcook.com/CompendiumOfConjugatePriors.pdf>.
Stucchio, Chris (2015) "Bayesian A/B Testing at VWO" <https://vwo.com/downloads/VWO_SmartStats_technical_whitepaper.pdf>.

Ryan Angi

grizbayr

Bayesian Inference for A|B and Bandit Marketing Tests

sample_cm_per_click function

<dl><dt>input_df</dt>
<dd>Dataframe containing option_name (str), sum_conversions (dbl), sum_revenue (dbl),
and sum_clicks (dbl).</dd>
<dt>priors</dt>
<dd>Optional list of priors alpha0, beta0 for Beta, k0, theta0 for Gamma Inverse Revenue,
and k01, theta01 for Gamma Cost (uses alternate priors so they can be different from Revenue).
Default \(Beta(1,1)\) and \(Gamma(1, 250)\) will be use otherwise.</dd>
<dt>n_samples</dt>
<dd>Optional integer value. Defaults to 50,000 samples.</dd></dl>

Arguments

Sample CM Per Click — sample_cm_per_click

<dl>

<dt>input_df</dt>
<dd>Dataframe containing option_name (str), sum_conversions (dbl), sum_revenue (dbl),
and sum_clicks (dbl).</dd>


<dt>priors</dt>
<dd>Optional list of priors alpha0, beta0 for Beta, k0, theta0 for Gamma Inverse Revenue,
and k01, theta01 for Gamma Cost (uses alternate priors so they can be different from Revenue).
Default \(Beta(1,1)\) and \(Gamma(1, 250)\) will be use otherwise.</dd>


<dt>n_samples</dt>
<dd>Optional integer value. Defaults to 50,000 samples.</dd>

</dl>

sample_cm_per_click: Sample CM Per Click

Description

Usage

Value

Arguments

Details