The Kaiser Family Foundation/Health Research and Educational Trust 2003 Annual Employer Health Benefits Survey (Kaiser/HRET) reports findings from a telephone survey of 2,365 randomly selected public and private employers, including 1,856 who responded to the full survey and 1,119 who indicated whether or not they provide health coverage. Firms range in size from small enterprises with as few as 3 workers to corporations with more than 300,000 employees. The Kaiser/HRET Employer Health Benefits Survey is based on previous surveys sponsored by the Health Insurance Association of America from 1986-1991 and Baring Point (KPMG at the time of the surveys) from 1991-1998.
Researchers at Health Research and Educational Trust and the Kaiser Family Foundation designed and analyzed the survey. National Research LLC conducted the fieldwork between January and May 2002 with an overall response rate of 50%.
This year several changes were made to the survey methodology in order to strengthen the validity of our results. For 2003, the most recently released statistics from the US Census Bureau was used as the basis for calculating the employer weight rather than the Dun and Bradstreet database of the nation's firms used in past surveys. Census data are drawn from a more representative sample of the nation's firms, and indicate that 59% of firms have 3-9 workers, not 74% as reported in Dun and Bradstreet's sample. This change, however, had little impact on worker-based estimates since the smallest firms represent less than 10% of all workers.
The second major change made to the 2003 survey was a non-response adjustment made to the question about whether the firm offers workers health benefits. Experience from previous years' surveys indicated that firms not offering health benefits are less inclined to participate in the full survey, and there was reason to believe the same might be true of the single offer rate question. This year, we tested non-response among firms that decline to participate in the full survey by conducting a follow-up survey with all firms who responded to the single question about offering health benefits, and matching responses between firms who were called twice. A McNemar and chi-squared test indicated that the follow-up survey results were valid and confirmed our hypothesis that firms that do not offer health insurance are less likely to respond to a survey of health benefits. This year we also instituted weight trimming to reduce the influence of weight outliers on the survey results.
All statistical tests are performed at the 0.05 levels except where otherwise noted. A select set of data were tested at the 0.10 level to explore the possibility of emerging changes in the health care offer rate, employee share of premium, premium growth among small firms, coverage rates, and prescription drug carve-outs.
Sponsors
The Kaiser Family Foundation, based in Menlo Park, California, is an independent national health care philanthropy dedicated to providing information and analysis on health issues to policymakers, the media, the general public. The Foundation is not associated with Kaiser Permanente or Kaiser Industries.
The Health Research and Educational Trust is a private, not-for-profit organization involved in research, education, and demonstration programs addressing health management and policy issues. Founded in 1944, HRET, collaborates with health care, government, academic, business, and community organizations across the United States to conduct research and disseminate findings that help shape the future of health care.
