Click here to return to the previous page
Response Rate
Kaiser/HRET drew its sample from a Survey Sampling Incorporated list (based on an original Dun and Bradstreet list) of the nation’s private and public employers with three or more workers. To increase precision, Kaiser/HRET stratified the sample by industry and the number of workers in the firm. Kaiser/HRET attempted to repeat interviews with prior years’ survey respondents (with at least ten employees) who also participated in 2005, 2006, or both. As a result, 1,481 firms in this year’s total sample of 1,997 firms participated in either the 2005, 2006, or both surveys.3 The overall response rate is 49%.
The vast majority of questions are asked only of firms that offer health benefits. A total of 1,839 responding firms indicated that they offered health benefits. The overall response rate of firms that offer health benefits is 50%.
From previous years’ experience, we have learned that firms that decline to participate in the study are less likely to offer health benefits. Therefore, we asked one question to all firms in the study with which we made phone contact where the firm declined to participate. The question was, “Does your company offer or contribute to a health insurance program as a benefit to your employees?” A total of 3,078 firms responded to this question (including 1,997 who responded to the full survey and 1,081 who responded to this one question). Their responses are included in our estimates of the percentage of firms offering health benefits.4 The response rate for this question is 75%.
Firm Size and Industry Definitions, Rounding, and Imputation
Throughout the report, exhibits categorize data by size of firm, region, and industry. Firm size definitions are as follows: All Small, 3 to 199 workers; and All Large, 200 or more workers. Occasionally, firm size categories will be broken into smaller groups. The All Small group may be categorized by: 3 to 24 workers, and 25 to 199 workers; or 3 to 9 workers, 10 to 24 workers, 25 to 49 workers, and 50 to 199 workers. The All Large group may be categorized by: 200 to 999 workers, 1,000 to 4,999 workers, and 5,000 or more workers. Exhibit M.1 shows detailed characteristics of the survey sample. Exhibit M.3 identifies which states are in each region.
Exhibit M.2 displays the distribution of the nation’s firms, workers, and covered workers (employees receiving coverage from their employer). Among the over three million firms nationally, approximately 60% are firms employing 3 to 9 workers; such firms employ 9% of workers and 6% of covered workers. In contrast, less than one percent of firms are firms employing 5,000 or more workers; these firms employ 34% of workers and 36% of covered workers. Therefore, the smallest firms dominate any national statistics about what employers in general are doing. In contrast, firms with 5,000 or more workers are the most important employer group in calculating statistics regarding covered workers, since they employ the largest percentage of the nation’s workforce.
The Kaiser/HRET survey compares premium increases to changes in workers’ hourly wages and overall inflation, both obtained from the Bureau of Labor Statistics (BLS). Workers’ hourly wage change is calculated from the Current Employment Statistics Survey (CES)5 using seasonally adjusted data for private workers. Overall inflation is calculated using the Consumer Price Index US city average for all urban consumers (CPI-U).6 We report annual increases in these data from April of the prior year to April of the current year because this is typically the field time of the survey.
Some exhibits in the report do not sum up to totals due to rounding effects. In a few cases, numbers from distribution exhibits may not add to equal numbers referenced in the text due to rounding effects. Throughout the report, while overall totals as well as totals for size and industry are statistically valid, some breakdowns may not be available due to limited sample sizes. In instances where the sample size is fewer than 30, exhibits include the notation NSD (Not Sufficient Data).
To control for item nonresponse bias, Kaiser/HRET imputes values that are missing for most variables in the survey. On average, less than five percent of these observations are imputed for any given variable. In prior years, many variables were imputed following a hotdeck approach, while others followed a distributional approach (where values were randomly determined from the variable’s distribution, assuming a normal distribution). This year, all variables are imputed following a hotdeck approach. This imputation method does not rely on a normal distribution assumption and replaces missing values with observed values from a firm with similar characteristics, in this case, size and industry. Due to the low imputation rate for most variables, the change in methodology is not expected to have a major impact on the results. In some cases, due to small sample size, imputed outliers are excluded. There are a few variables that Kaiser/HRET has decided should not be imputed; these are typically variables where “don’t know” is considered a valid response option (for example, firms’ opinions about effectiveness of various strategies to control health insurance costs).
Click here to continue on to the next page
