A cohort is the set of comparable matters a distribution is computed from, defined by stated filters such as forum, case family and filing window. Two figures can only be compared if their cohorts are defined the same way.
Cohorts make comparison fair. A matter's duration or outcome is read against peers that share the factors that matter for the question, and the filters that define those peers are published alongside the number.
A conditional cohort goes one step further. It restricts the peers to matters still open at the age of the matter being measured, so that the result reflects what remained and not what began. This is the basis of an honest re-estimate at a checkpoint.
A cohort is not a sample drawn to make a point. Its definition is fixed before the figure is computed, and pooling across forums or case families is declared with a reason.
Working a file that turns on this term?
Working through a diligence process?
Institutional partners evaluating a position against this platform's outcome and duration models are welcome to reach out directly.