Evaluation of Compensation Data Collected Through the EEO-1 Form (2023) / Chapter Skim
Currently Skimming:
Pages 1-12
The Chapter Skim interface presents what we've algorithmically identified as the most significant single chunk of text within every page in the chapter.
Select key terms on the right to highlight them within pages of the chapter.
From page 1... ...
Prior to the data collection that is the focus of this report there were no other sources of federal data from employers regarding the relationship among pay, employer, and employee characteristics that could be used for enforcement purposes. To access pay data and improve its ability to investigate pay disparities, EEOC expanded its EEO-1 data collection (known as Component 1)
|
From page 2... ...
The panel comprised economists, sociologists, statisticians, survey methodologists, lawyers, and employer advisors with expertise in measuring data quality, pay gaps, pay discrimination, and pay equity. Several panel members had previously used EEO data in their own research, and two had served on the 2012 National Research Council panel that reviewed EEO-1 data.
|
From page 3... ...
The collection was paused in 2017 and resumed by court order in 2019. To understand how these unique experiences may have contributed to data quality, the panel reviewed the 2013 National Research Council Report, the 2015 Sage Computing report, and the 2016 EEOC information collection request and accompanying instruments.
|
From page 4... ...
. The panel then examined how Component 2 data compare to pay gaps measured using microdata on individuals from the American Community Survey (see Chapter 6)
|
From page 5... ...
The panel found numerous and varied data issues in the 2017–2018 Component 2 collection. Figure S-1 provides a high-level summary of the panel's estimates of various key dimensions of data quality for the 2018 Component 2 data: coverage, unit response rates, missing data, and extreme values.
|
From page 6... ...
. "Used for exemplar analyses" excludes firms with more than 1.4 million employees, Type 6 reports (which did not collect pay data)
|
From page 7... ...
Using established, improved meth ods, other federal agencies have demonstrated that individual-level pay data can substantially reduce respondent burden, increase precision in estimating pay gaps, and protect confidentiality. The Bureau of Labor Statistics' Occupational Employment and Wage Statistics collection is an example.
|
From page 8... ...
Still, to the extent that EEOC can fix the data issues or clean the problematic data, the data can be useful. CONCLUSION 6-1: After cleaning, 2017–2018 Component 2 data could be used to obtain estimates of raw pay gaps at the national level by sex, race/ethnicity, and occupation.
|
From page 9... ...
This issue is not due to coverage or data errors but instead relates to the number of observations available for comparison within a given small establishment. CONCLUSION 7-2: The 2017–2018 Component 2 data have limited utility in analyzing pay differences within establishments that lack variation in employee characteristics of pay, sex, race/ethnicity, and occupation.
|
From page 10... ...
RECOMMENDATION 2-1: EEOC should combine the Component 1 and 2 instruments into a single data-collection instrument, thus lessen ing respondent burden and reducing the chances for inconsistencies or reporting errors. Data-collection protocols allowed establishments with fewer than 50 employees to be reported using either Type 6 reports (containing limited data)
|
From page 11... ...
CONCLUSION 5-1: Important data-quality issues exist in the 2017– 2018 Component 2 data, including missing data, response inconsisten cies, implausible extreme values, and measurement unreliability. These errors are large and, if not addressed, could generate misleading results.
|
From page 12... ...
As stated in Conclusion 3-2, the panel found that current pay bands are simply too wide to be useful in many situations. RECOMMENDATION 3-4: If EEOC continues to collect pay data in bands, narrower pay bands should be adopted, and the number of
|
Key Terms
This material may be derived from roughly machine-read images, and so is provided only to facilitate research.
More
information on Chapter Skim is available.