csranks: An R Package for Estimation and Inference Involving Ranks

TL;DR

The paper introduces the R package csranks, which provides tools for estimation and inference involving ranks, including confidence sets and regression methods, demonstrated through applications in country rankings and intergenerational mobility.

Contribution

The paper presents new R package csranks that implements advanced methods for rank-based inference and estimation, facilitating analysis in social sciences and economics.

Findings

Effective estimation of confidence sets for ranks.

Application to PISA country rankings.

Measurement of intergenerational mobility.

Abstract

This article introduces the R package csranks for estimation and inference involving ranks. First, we review methods for the construction of confidence sets for ranks, namely marginal and simultaneous confidence sets as well as confidence sets for the identities of the tau-best. Second, we review methods for estimation and inference in regressions involving ranks. Third, we describe the implementation of these methods in csranks and illustrate their usefulness in two examples: one about the quantification of uncertainty in the PISA ranking of countries and one about the measurement of intergenerational mobility using rank-rank regressions.