U.S. Wage Data for Bootstrap Inference in Modal Regression

A wage dataset from the United States is included as supplemental material for a paper on uniform inference methods for conditional mode estimation. The paper, authored by Tao Zhang of Cornell University, develops two bootstrap methods for constructing confidence intervals around modal regression estimates derived from quantile regression. Simulation experiments and a real data analysis using this wage data demonstrate the finite-sample performance of the proposed inference methods.

Use Cases

• Testing bootstrap inference methods for conditional mode estimation based on the described quantile regression approach.
• Benchmarking new statistical methods against the simulation and real-data results presented in the paper.
• Studying the relationship between covariates and wage outcomes using the provided U.S. wage dataset.

Strengths

• Includes R code for implementing the proposed bootstrap inference methods.
• The paper extends analysis to high-dimensional settings where covariate dimension increases with sample size.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.

Provenance

Source

Cornell University

Collection Method

Likely sourced from a U.S. wage survey or study, as referenced in the paper's real data analysis.

Time Range

null

Freshness

Last update date is unknown; freshness unverified.

Geography

United States