1971-2002 Organization survey, a replication dataset.

The goal of the survey was to examine the determinants and
effects of corporate innovations in the realms of harassment prevention and workforce
diversity. Data come from a retrospective survey with a stratified random
national sample of establishments drawn from the 1999 EEO1 files, matched with confidential
government data from EEO1 reports on the workforce composition of surveyed establishments.
These confidential data can be obtained through an Intergovernmental Personnel Act
(IPA) agreement.
The sample was stratified by industry
(sampling equally from food, chemicals, computer equipment, transportation
equipment, wholesale trade, retail trade, insurance, business services, and
health services); by size (selecting 35% of the establishments with fewer than
500 employees in 1999); and by "age" in the EEO-1 dataset (we chose half of the sample from
establishments that had been in the dataset since at least 1980, and half from
those that had been in the dataset since at least 1992). Surveys were conducted with
human resources managers or general managers, who were asked about the adoption
of a list of personnel policies and programs and the years of adoption. The
survey was conducted in 2002 by the Princeton University Survey Research Center.
Additional information about the survey can be found in the Supporting
Information for the PNAS article related to these data. Full citation information
will be updated when it becomes available. Information is also available in:

Kalev Alexandra, Frank Dobbin and Erin Kelly. (2006). Best Practices or Best Guesses? Assessing the Efficacy of Corporate
Affirmative Action and Diversity Policies. American Sociological
Review, 71(4), 589-617