Weights are created in NHANES III to account for the complex survey design (including oversampling), survey non-response, and post-stratification. When a sample is weighted in NHANES III it is representative of the U.S. civilian noninstitutionalized Census population.
Each Sample person in the NHANES III dataset is assigned a sample weight. This sample weight is created in three steps:
In general a sample person is assigned a weight that is equivalent to the reciprocal of his/her probability of selection. In other words:
However, calculating the base weight for a sample person in NHANES III is much more complicated due to the survey's complex, multistage design. In NHANES III, the following equation, which takes into account the survey design, is used to determine the base weight for a sample person:
where
Adjustment to the interview or exams
The base weights were adjusted for nonresponse to the in-home interview when creating interview weights and further adjusted for non-response to the MEC exam when creating exam weights.
In NHANES III, an individual can be classified as a non-respondent to the interview portion of the survey and/or the exam portion. An individual is considered a non-respondent to the interview if he/she was selected to be in the sample, but did not participate in the in-home interview. Similarly, an individual who agreed to complete the interview but did not agree to, or come in for, the MEC portion of the survey is considered a non-respondent to the exam. Adjustments made for survey non-response account only for sample person interview or exam non-response, but not for component/item non-response (i.e., a sample person declined to have their blood pressure measured in the examination component but completed all other examination components).
As with continuous NHANES, separate weights are provided to account for unit nonresponse to the various portions of the survey (interview, MEC exam, and subsamples). In addition, in NHANES III, frail persons or persons who were unable to come to the MEC were also offered an abbreviated physical exam in their home. The home exam was limited to infants and persons aged 60 years or above. Interviewed persons who completed at least one test or examination at their home were defined as home examined. The home examination included only a very small subset of the contents of the MEC examination. Therefore, analysts should be extremely careful in deciding whether the home examinations could or could not be combined in analyses. The notes section of the data file documentation includes warnings when home examination measurements can or can not be combined with the corresponding MEC measurements.
In general for NHANES III, 39,695 persons were selected into the sample, 33,994 completed the interview, 30,818 were MEC examined, and 31,311 MEC or home examined. For detailed response rates by age and other selected demographic characteristics, please click the link below to see the Table of Nonresponse Rates for NHANES III.
For more information on component/item nonresponse adjustment and re-weighting the data for analyses, see
1. Lohr, Sharon L. Sampling: Design and Analysis, pp.265-272. Duxbury Press, 1999.
Adjustment for NHANES III subsample components
NHANES respondents are asked to participate in a variety of survey components that are statistically defined (or random) subsamples of the NHANES MEC-examined sample. These include a variety of lab, nutrition/dietary, environmental, or mental health components. (Please see the respective survey protocol/documentation for more specific information.) For example, some, but not all, participants are selected to give a fasting blood sample on the morning of their MEC exam. The subsamples selected for these components are chosen at random with a specified sampling fraction (for example, 1/2 of the total examined group) according to the protocol for that component. Each component subsample has its own designated weight, which accounts for the additional probability of selection into the subsample component, as well as the additional nonresponse.
Subsample weights are not designed to be combined. In fact, many subsamples are mutually exclusive. If it is necessary to combine two or more subsamples for your analyses, then appropriate weights would need to be recalculated. However, details on how to recalculate weights when combining subsamples go well beyond the scope of this tutorial. Therefore, it is strongly advised that you do not attempt to combine subsamples in any analysis.
In NHANES III only four exam subsamples were created. These were the morning exam subsample, the afternoon exam subsample, the allergy testing subsample and the central nervous system (CNS) subsample. As with the continuous NHANES, separate weights are provided for these subsamples (both for MEC examined and the combined MEC + Home examined). As mentioned previously it is strongly advised that you do not attempt to combine subsamples in NHANES III.
In addition to accounting for sample person non-response, weights are also post-stratified to match the population control totals for each sampling subdomain. This additional adjustment makes the weighted counts the same as an independent count of the Current Population Survey (CPS) of the U.S. Census.
Post-stratification for NHANES III was made to match the 1990 Decennial Census. In addition, four race/ethnic groups were used in the weighting procedures (non-Hispanic whites, non-Hispanic blacks, Mexican Americans and others). Because no separate estimates are available for Mexican Americans from the 1990 Decennial Census, population control estimates for the civilian noninstitutionalized population for the Current Population Survey (CPS) of March 1990 and March 1993 were used to post stratify the final sampling weights for phase 1 and phase 2 of the NHANES III respectively. These unpublished CPS estimates are adjusted for undercount of selected minority subdomains of the U.S. population. Thus, phase 1 sampling weights add up to the undercount adjusted March 1990 CPS totals, and phase 2 sampling weights add up to the undercount adjusted March 1993 CPS totals for the civilian noninstitutionalized population of the U.S. The midpoint of the NHANES III 6 years combined (1988-1994) was October, 1991. To account for the variation in the U.S. population over the two phases, the final NHANES III sampling weights in the combined 6-year sample were computed as one-half of the sampling weights associated with the individual phases.
In summary, it is important to utilize the weights in analyses to account for the complex survey design (including oversampling), survey nonresponse, and post-stratification in order to ensure that calculated estimates are truly representative of the U.S. civilian noninstitutionalized population.
