The Census Tree: Machine Learning Models

Principal Investigator(s):  View help for Principal Investigator(s) Joseph Price, Brigham Young University; Kasey Buckles, University of Notre Dame; Adrian Haws, Cornell University; Haley Wilbert, University of Notre Dame

Version:  View help for Version V1

Name File Type Size Last Modified
Readme_models_BHPW.docx application/vnd.openxmlformats-officedocument.wordprocessingml.document 24.5 KB 08/14/2023 05:25:AM
model_1850_1860.dat text/plain 1.3 MB 08/13/2023 04:41:PM
model_1850_1870.dat text/plain 686.1 KB 05/19/2023 12:10:PM
model_1850_1880.dat text/plain 388.2 KB 05/15/2023 09:07:PM
model_1850_1900.dat text/plain 686.4 KB 06/02/2023 08:14:AM
model_1850_1910.dat text/plain 383.4 KB 05/23/2023 06:56:PM
model_1850_1920.dat text/plain 645.2 KB 06/01/2023 04:33:PM
model_1850_1930.dat text/plain 353.1 KB 06/01/2023 04:10:PM
model_1850_1940.dat text/plain 121.9 KB 06/01/2023 01:51:PM
model_1860_1870.dat text/plain 685.8 KB 06/01/2023 12:20:PM

Project Citation: 

Price, Joseph, Buckles, Kasey, Haws, Adrian, and Wilbert, Haley. The Census Tree: Machine Learning Models. Ann Arbor, MI: Inter-university Consortium for Political and Social Research [distributor], 2023-08-14. https://doi.org/10.3886/E193324V1

Project Description

Summary:  View help for Summary
The Census Tree is the largest-ever database of record links among the historical U.S. censuses, with over 700 million links for people living in the United States between 1850 and 1940. These links allow researchers to construct a longitudinal dataset that is highly representative of the population, and that includes women, Black Americans, and other under-represented populations at unprecedented rates. 

This folder includes all 36 machine learning models trained on Family Tree links for U.S. Census records from 1850 to 1940 (see Buckles, Haws, Price, and Wilbert (2023), available at https://censustree.org). We also include code to create features and obtain predicted match scores from a set of potential links.

Funding Sources:  View help for Funding Sources National Science Foundation. Directorate for Social, Behavioral and Economic Sciences (SES-2049762); Russell Sage Foundation (G-1063)

Scope of Project

Subject Terms:  View help for Subject Terms census data; record linking; historical data
Geographic Coverage:  View help for Geographic Coverage United States
Time Period(s):  View help for Time Period(s) 1850 – 1940
Data Type(s):  View help for Data Type(s) census/enumeration data; other
Collection Notes:  View help for Collection Notes See https://censustree.org for more information.

Methodology

Data Source:  View help for Data Source See https://censustree.org for detailed documentation.
Unit(s) of Observation:  View help for Unit(s) of Observation a record link between the indicated censuses

Related Publications

Download this project

Published Versions

V1 [2023-08-14]

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 it arrived from the data depositor. ICPSR has not checked or processed this material. Users should consult the investigator(s) if further information is desired.