University of Maryland

Allocating Samples for Selection Decisions with Multiple Uncertain Attributes

This page contains the following sections:

Research Team: Dennis D. Leber, National Institute of Standards and Technology, and Jeffrey W. Herrmann, University of Maryland.


This research project is studying the collection of information for multiple attribute (multiple-criteria) selection problems.

In some cases, a decision-maker has a limited budget to collect data (samples) that will be used to analyze a multiple attribute selection decision. Because the sampling (measurement) process has uncertainty, more samples provide better information, but each sample can measure only one attribute of one alternative. With a limited budget, determining the number of samples to observe from each alternative and attribute is an critical information gathering decision. We have developed and tested multiple approaches to determine which approaches maximize the probability of selecting the true best alternative.

This research is generating knowledge about the performance of sample allocation schemes for multiple attribute (multiple-criteria) selection problems.

Related Publications

Last updated on August 5, 2016, by Jeffrey W. Herrmann.