Pre-computes key values required for the outcome imputation step of the Multi-Arm-Bandit
procedure. Calculates the probabilities of success for each treatment block (treatment arm + any blocking specified),
using the grouped means of the original experimental data. When perfect_assignment is FALSE, the average date of
success is calculated for each treatment block at every period.
imputation_precompute(data, whole_experiment, perfect_assignment, data_cols)A named list containing:
original_summary: The tibble(s)/data.table(s) containing the probability of success for each
treatment block, at each period.
dates_summary: A tibble/data.table containing the average success date for
each treatment block at each treatment period.
A data.frame, data.table, or tibble containing input data from the trial. This should be the results of a traditional Randomized Controlled Trial (RCT). Any data.frames will be converted to tibbles internally.
Logical; if TRUE, uses all past experimental data for imputing outcomes. If FALSE, uses only data available up to the current period. In large datasets or with a high number of periods, setting this to FALSE can be more computationally intensive, though not a significant contributor to total run time.
Logical; if TRUE, assumes perfect information for treatment assignment (i.e., all outcomes are observed regardless of the date). If FALSE, hides outcomes not yet theoretically observed, based on the dates treatments would have been assigned for each wave. This is useful when simulating batch-based assignment where treatments were assigned on a given day whether or not all the information from a prior batch was available and you have exact dates treatments were assigned.
A named character vector containing the names of columns in data as strings:
id_col: Column in data; contains unique ID as a key.
success_col: Column in data; binary successes from the original experiment.
condition_col: Column in data; original treatment condition for each observation.
date_col: Column in data; contains original date of event/trial. Only necessary when assigning by "Date". Must be of type Date, not a character string.
month_col: Column in data; contains month of treatment. Only necessary when time_unit = "Month", and when periods should be determined directly by
the calendar months instead of month based time periods. This column can be a string/factor variable with the month names or numeric with the month number. It can easily
be created from your date_col via lubridate::month(data[[date_col]]) or format(data[[date_col]], "%m").
success_date_col: Column in data; contains original dates each success occurred. Only necessary when perfect_assignment = FALSE. Must be of type Date, not a character string.
assignment_date_col: Column in data; contains original dates treatments were assigned to observations. Only necessary when perfect_assignment = FALSE.
Used to simulate imperfect information on the part of researchers conducting an adaptive trial. Must be of type Date, not a character string.
imputation_precompute() is an optimization, meant to reduce the cost of calculating these variables
within the simulation loop. When whole_experiment is TRUE, original_summary is a single tibble/data.table,
and used through the simulation. When whole_experiment is FALSE, original_summary is a list of tibbles/data.tables,
each containing the cumulative probabilities of all periods up to the index i.
If perfect_assignment is FALSE, dates_summary is not calculated, and is NULL.
No covariates are used in the calculation, these are all simply grouped averages.