Skip Navigation Bar
 

National Information Center on Health Services Research and Health Care Technology (NICHSR)

Showing uncertainty due to sampling
Page 4 of 4
Consider the following chart that shows the percent of people who experienced psychological distress in the 30 days before they participated in the National Health Interview Survey.

Click the below image to view



Source: Early Release of Selected Estimates Based on Data From the 2006 National Health Interview Survey [downloaded from http://www.cdc.gov/nchs/about/major/nhis/released200706.htm]

Notice that the chart shows the 95% confidence interval calculated to show the effect of the fact that the data are based on a sample rather than interviews with every person in the population. The calculation reflects not only the number of persons in the sample, but also the methods used to select the sample.

While it is relatively easy to show the effect of sampling on a survey result, the same kinds of statistical uncertainties are found in each kind of health data. These result from inevitable imperfections in the administration of statistical procedures, data collections and administrative records systems.
 
Page 4 of 4