Skip to contents

With repeated observations on the same patient, resampling rows treats two visits by one person as two independent facts. That narrows every interval it touches. When the project declares a cluster, whole patients are drawn instead, which is what the specification's clustered design asks for.

Usage

mm_resample(cohort, cluster_id = NULL)

Arguments

cohort

Rows to resample.

cluster_id

Column naming the patient, or NULL for row-level.

Value

Integer row indices, with replacement.