Panel Study of Income Dynamics

Overview

The Panel Study of Income Dynamics (PSID) is the longest running longitudinal household survey in the world. The study began in 1968 with a nationally representative sample of over 18,000 individuals living in 5,000 families in the United States. Information on these individuals and their descendants has been collected continuously, including data covering employment, income, wealth, expenditures, health, marriage, childbearing, child development, philanthropy, education, and numerous other topics.

The PSID study website is a good source of information about the study. It contains a user guide, documentation, and list of publications that utilize the data.

Between 1968 and 1997, interviews were conducted annually. Since then, interviews have been biennial. The most recent wave of interviews included over 9,000 families and almost 25,000 individuals.

Public-Use Data

There are both public-use and restricted-use data files available. Users can obtain PSID main and supplemental study ZIP files from the website’s data page. These files contain data in text format, SAS, SPSS, and Stata program files, as well as codebooks and other pertinent documentation. The PSID Data Center allows users to create custom data sets based on chosen variables that are then merged across waves and files. Data can be generated in a variety of formats including ASCII, SAS, SPSS, and Stata.

Because the PSID has over 50 years of data and tens of thousands of participants, it is recommended that researchers use the 

Restricted-Use Data

The restricted-use data are provided only under conditions of a contract between the researcher and the University of Michigan. Restricted data include, but are not limited to, geospatial information, school identifiers, assisted housing linkages, vehicle make and model, child reports of sensitive information, criminal justice system exposure, National Death Index linkages and more. To see all available files, please see the Restricted Data webpage.

Sample Code

We provide sample code for creating demographic variables and building panel data from single-year family files and the cross-year individual file. The data can be found here.