Convert data in the traditional format (one state per interval) to mutually exclusive intervals that hold all the states that overlap for that interval.
Arguments
- events
A data frame with columns for treatment name, treatment start and stop dates, plus a column for unique patient identifiers.
- gap
Maximum number of days between intervals before they are considered distinct episodes. Intervals separated by
gapor fewer days are merged into a single contiguous episode.Default value:
0L- id_var
A string specifying the patient identifier column in
events.Default value:
"patient_id".- stockpile
Do identical events within a group need to be combined such that all intervals are mutually exclusive? Default is TRUE. Only turn to FALSE if you are CERTAIN the data contains no overlapping intervals for the same treatment -- the behavior of interval combining is dependent on this assertion.