Data and Code for: Labor Market Inequality And The Changing Life Cycle Profile Of Male And Female Wages

Principal Investigator(s): View help for Principal Investigator(s) Richard Blundell, University College London; Hugo Lopez, University of Chicago. Social Sciences Division; James Ziliak, University of Kentucky

Version: View help for Version V1

Name	File Type	Size	Last Modified
Replication File			03/18/2025 08:10:PM
README_Blundell_Lopez_Ziliak.pdf	application/pdf	314.1 KB	03/18/2025 04:08:PM

Project Citation:

Blundell, Richard, Lopez, Hugo, and Ziliak, James. Data and Code for: Labor Market Inequality And The Changing Life Cycle Profile Of Male And Female Wages. Nashville, TN: American Economic Association [publisher], 2025. Ann Arbor, MI: Inter-university Consortium for Political and Social Research [distributor], 2025-09-09. https://doi.org/10.3886/E200241V1

Project Description

Summary: The code in this replication package assembles the data needed and replicates the analysis of the paper “Labor Market Inequality and the Changing Life Cycle Profile of Male and Female Wages,” by Richard Blundell, Hugo Lopez, and James P. Ziliak. The first file is a Stata file 0_InstallPackages.do which installs a number of plug-in ADO files needed for successful execution (only run once). The second is also a Stata file 1_FullDataPrep.do which calls a number of Stata DO files to compile all the necessary data files and prepares the data for the analysis. The resulting Stata dataset, RunningData_withtaxsim.dta, is found in the replication file /ProcessedData/, and because Matlab relies on csv files, the resulting Matlab input files are at /ProcessedData/MatlabDataInputFiles/. The replicator should expect the code to run for about 3 hours. Then, the Matlab file a2_QuantileEstimation.m should be executed. The parameter estimates reported in the figures and tables come from a Windows desktop version that takes about 5 hours for each of four subsamples for each model specification. Due to the computational complexity of the bootstrap quantile with selection estimator, we made use of a computing cluster with a SLURM job scheduler. There are 8 Matlab bootstrap programs—four to produce standard errors in Tables 1-4 of the manuscript and four to produce standard errors for Supplemental Appendix Tables D1-D4. These boostrap computations were submitted in parallel (i.e. all at once as separate programs) and each took on average 6 days when running on 4 cores. Then the Stata file 3_Figures&Tables.do should be run to produce all 9 figures (30 in the appendix) and 4 tables (7 in the appendix).

Funding Sources: Economic and Social Research Council (United Kingdom) (ES/M010147/1)

Scope of Project

Subject Terms: gender gaps; life cycle earnings; employment; quantile selection

JEL Classification:
J10 Demographic Economics: General
J30 Wages, Compensation, and Labor Costs: General

Geographic Coverage: United States

Time Period(s): 1976 – 2018

Collection Date(s): 2019 – 2021

Universe: Prime-age men and women age 25-55

Data Type(s): survey data

Methodology

Data Source: United States Bureau of the Census Annual Social and Economic Supplement, 1976-2019
University of Kentucky Center for Poverty Research National Welfare Data, 1980-2018
Additional sources described in README

Unit(s) of Observation: Individual

Geographic Unit: state level

Related Publications

Download this project

Published Versions

V1 [2025-09-09]

Export Metadata

Dublin Core

DDI 2.5

Report a Problem

Found a serious problem with the data, such as disclosure risk or copyrighted content? Let us know.

This material is distributed exactly as received from the data depositor. As of April 2026, depositors are required to submit study materials in accessible formats. ICPSR has not reviewed, checked, or processed this material. For additional information about the study, please contact the investigator(s) directly. If you have questions about the accessibility of materials distributed by ICPSR or require further assistance, please visit ICPSR's Accessibility Center.