Accuracy and Decision Time for a Class of Sequential Decision Aggregation Rules

This work focuses on decentralized decision making in a population of individuals each implementing the sequential probability ratio test. The individual decisions are combined into a decentralized decision via an aggregation rule chosen from a family of aggregation rules, denoted as q out of N rule. We study how the population size affects the performance of the decentralized decision making, i.e., the decision accuracy and time. In a group applying the q ouf of N, a global decision is reached as soon as q out of the N decision makers agree on an answer. Under the assumption of measurement independence among individuals, we introduce a novel numerical method that allows the analysis of the decision accuracy and time of a group of decision makers. We present the numerical method and show a preliminary sets of results that can be obtained using such a method.