The steps below assume that you are already familiar with the sample weights. If you need information about sample weights and how to use them in your analysis, please review the Weighting module in the Continuous NHANES Web Tutorial before continuing.
Currently, the protocol to obtain the subsamples of selected environmental chemicals is based on a random sample with a specified sampling fraction (for example, 1/2 or 1/3 of the total examined group within specific age ranges). Each chemical group subsample has its own designated sample weight, which accounts for the complex survey design (including oversampling, survey non-response, and post-stratification).
To produce estimates appropriately adjusted for survey non-response, it is important to check the completeness of all the variables in your analysis and select the sample weight variable that applies to all members of the smallest subpopulation to be analyzed. The following table lists the types of sample weights by decreasing sample size.
|Sample Size||Component||Data file(s) Containing Sample Weight Variable||Weight Variable|
|Smallest||Special subsamples for environmental chemical data||Laboratory – according to chemical group||Depends on the subsample|
For the urinary phthalate data combined with the demographic data, the weight variable for analysis will be the urinary phthalates subsample weight (variable WTSPH4YR for the 1999-2000 and 2001-2002 data, and variable WTSB2YR in 2003-2004 data) . In doing so, you will be analyzing the environmental chemical data for individuals who have urinary phthalate measurements. This means that only persons with non-zero subsample weights will be analyzed.