estimate_value_remaining: Estimate Value Remaining

In grizbayr: Bayesian Inference for A|B and Bandit Marketing Tests

Estimate Value Remaining

Description

Estimates value remaining or loss (in terms of percent lift, absolute, or relative).

Usage

estimate_value_remaining(
  input_df,
  distribution,
  priors = list(),
  wrt_option = NULL,
  metric = "lift",
  threshold = 0.95
)

Arguments

input_df	Dataframe containing option_name (str) and various other columns depending on the distribution type. See vignette for more details.
distribution	String of the distribution name
priors	Optional list of priors. Defaults will be use otherwise.
wrt_option	string the option loss is calculated with respect to (wrt). If NULL, the best option will be chosen.
metric	string the type of loss. absolute will be the difference, on the outcome scale. 0 when best = wrt_option lift will be the (best - wrt_option) / wrt_option, 0 when best = wrt_option relative_risk will be the ratio best/wrt_option, 1 when best = wrt_option
threshold	The confidence interval specifying what the "worst case scenario should be. Defaults to 95%. (optional)

Value

numeric value remaining at the specified threshold

Examples

input_df <- tibble::tibble(option_name = c("A", "B", "C"),
    sum_clicks = c(1000, 1000, 1000),
    sum_conversions = c(100, 120, 110))
estimate_value_remaining(input_df, distribution = "conversion_rate")
estimate_value_remaining(input_df,
    distribution = "conversion_rate",
    threshold = 0.99)
estimate_value_remaining(input_df,
    distribution = "conversion_rate",
    wrt_option = "A",
    metric = "absolute")

grizbayr documentation built on Oct. 9, 2023, 5:10 p.m.