A Machine Learning Approach to Improving Occupational Income Scores

Principal Investigator(s):  View help for Principal Investigator(s) Martin Saavedra, Oberlin College; Tate Twinam, The College of William & Mary

Version:  View help for Version V2

Name File Type Size Last Modified
Iowa_State_Census_1915_data.dta application/x-stata 21.8 MB 08/01/2019 01:54:PM
LIDO_score_1950.dta application/x-stata 83.9 MB 07/30/2019 07:22:AM
LIDO_score_1950_Iowa.dta application/x-stata 297 KB 01/24/2018 12:16:PM
ReadMe.docx application/vnd.openxmlformats-officedocument.wordprocessingml.document 13.4 KB 08/05/2019 08:26:AM
census1950_2000.dta application/x-stata 1.3 GB 08/05/2019 06:54:AM
construct_1950_based_LIDO.do text/x-stata-syntax 1 KB 07/30/2019 06:51:AM
construct_2000_based_LIDO.do text/x-stata-syntax 1.4 KB 08/05/2019 05:46:AM
figure_1_replication.do text/x-stata-syntax 2.5 KB 08/05/2019 08:03:AM
figure_2_replication.do text/x-stata-syntax 3 KB 08/01/2019 01:53:PM
lasso_2000.dta application/x-stata 32.6 MB 11/29/2016 05:59:PM

Project Citation: 

Saavedra, Martin, and Twinam, Tate. A Machine Learning Approach to Improving Occupational Income Scores. Ann Arbor, MI: Inter-university Consortium for Political and Social Research [distributor], 2019-08-05. https://doi.org/10.3886/E111103V2

Project Description

Summary:  View help for Summary These files are the replication files for "A Machine Learning Approach to Improving Occupational Income Scores" by Martin Saavedra and Tate Twinam.

Abstract: Historical studies of labor markets frequently lack data on individual income. The occupational income score (OCCSCORE) is often used as an alternative measure of labor market outcomes. We consider the consequences of using OCCSCORE when researchers are interested in earnings regressions. We estimate race and gender earnings gaps in modern decennial Censuses as well as the 1915 Iowa State Census. Using OCCSCORE biases results towards zero and can result in gaps of the wrong sign. We use a machine learning approach to construct a new adjusted score based on industry, occupation, and demographics. The new income score provides estimates closer to earnings regressions. Lastly, we consider the consequences for estimates of intergenerational mobility elasticities.

Scope of Project

Subject Terms:  View help for Subject Terms Occupational Income Scores; OCCSCORE ; Intergenerational Mobility
Geographic Coverage:  View help for Geographic Coverage United States


Related Publications

Download this project

Published Versions

V2 [2019-08-05]

V1 [2019-08-05]

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.