Modeling partitions of individuals

TL;DR

This paper introduces a new statistical framework based on exponential family distributions to analyze how individuals form exclusive groups, with applications to social and organizational mechanisms in various settings.

Contribution

It develops a novel exponential family model for partitions, providing mathematical properties and estimation strategies, applied here to hackathon team formation.

Findings

The framework effectively models group formation mechanisms.

Application to hackathons reveals insights into team assembly.

Mathematical properties support model estimation and inference.

Abstract

Despite the central role of self-assembled groups in animal and human societies, statistical tools to explain their composition are limited. We introduce a statistical framework for cross-sectional observations of groups with exclusive membership to illuminate the social and organizational mechanisms that bring people together. Drawing from stochastic models for networks and partitions, the proposed framework introduces an exponential family of distributions for partitions. We derive its main mathematical properties and suggest strategies to specify and estimate such models. A case study on hackathon events applies the developed framework to the study of mechanisms underlying the formation of self-assembled project teams.