This research project investigates and explores the development and evaluation of statistical procedures for using sample survey data to rank or compare several populations with respect to a characteristic of interest. While the problem of comparing populations in a collection of populations is closely related to the problem of ranking the populations, our research in this project focuses more on ranking. Specifically, the research includes an investigation of methods for quantifying and presenting the uncertainty in an estimated ranking of populations. Visualizations can help in the presentation of rankings and their uncertainty to wide audiences.

The desire to rank (either explicitly or implicitly) units such as states based on data from sample surveys is ubiquitous. We seek to share visualizations of rankings of units with supporting uncertainty (and theory) that are simple and easy to use. As an example, a series of ranking tables are released from the American Community Survey in which the fifty states and the District of Columbia are ordered based on estimates of certain characteristics of interest.

Wright, T. (2024). “Understanding and Optimal Tightening of the KWW Joint Confidence Region for a Ranking,” Research Report Series (Statistics #2024-01), Center for Statistical Research and Methodology, U.S. Census Bureau, Washington, D.C.

Martin Klein, Tommy Wright, Jerzy Wieczorek. (2020), "A Joint Confidence Region for An Overall Ranking of Populations" Journal of the Royal Statistical Society, Series C, 69, Part 3, 589-606.

Estimated Rankings of All States (Data Visuals)

Visualization: Joint Confidence Region for a Ranking

Vignette: R Vignette for Reproducing Figures from "A Joint Confidence Region for an Overall Ranking of Populations"

Wieczorek, J. (2020) RankingProject: The Ranking Project: Visualizations for Comparing Populations, R Package Version 0.2.0. (Available at https://cran.r-project.org/package=RankingProject)

Tommy Wright, Martin Klein, Jerzy Wieczorek. (2019), "A Primer on Visualizations for Comparing Populations, Including the Issue of Overlapping Confidence Intervals." The American Statistician, 73:2, 165-178, DOI: 10.1080/00031305.2017.1392359

Comparisons of A State with Each Other State (Data Visuals)

Visualization: Fifty-One Shaded Columns Comparison Plot

Vignette: R Vignette for Reproducing Figures from "A Primer on Visualizations for Comparing Populations, Including the Issue of Overlapping Confidence Intervals"

Wieczorek, J. (2017), RankingProject: The Ranking Project: Visualizations for Comparing Populations, R Package Version 0.1.1. (Available at https://cran.r-project.org/package=RankingProject)

Multiple Comparisons: To Adjust or Not to Adjust? Adam Hall/Tommy Wright (May 26, 2021)

Wright, T., Klein, M., and Wieczorek, J. (2014). “Ranking Populations Based on Sample Survey Data,” Research Report Series (Statistics #2014-12), Center for Statistical Research and Methodology, U.S. Census Bureau, Washington, D.C.

Tommy Wright, Martin Klein, and Jerzy Wieczorek. (2013), "An Overview of Some Concepts for Potential Use in Ranking Populations Based on Sample Survey Data." Proceedings of the 59th World Statistics Congress of the International Statistical Institute, At Hong Kong.

Martin Klein, Tommy Wright. (2011), "Ranking Procedures for Several Normal Populations: An Empirical Investigation." International Journal of Statistical Sciences, 11, 37-58.

Tommy Wright, Nathan Yau (FlowingData.com/U.S. Census Bureau), Adam Hall, Jerzy Wieczorek (Colby College)

Tommy Wright, Center for Statistical Research and Methodology
Phone: 301-763-1702; Email: tommy.wright@census.gov

Disclaimer: This research project does not reflect the views of the U.S. Census Bureau. All presented methods, rankings, and graphics have an exploratory (research and development) spirit; feedback from many is sought.