This module introduces the basic concepts of variance (sampling error) estimation for NHANES II data. You will learn how the complex survey design of NHANES II and clustering of the data affect variance estimation, which methods are appropriate to use when calculating variance for NHANES II data, and how to calculate degrees of freedom and construct confidence limits for NHANES II estimates.
The contents of the Variance Estimation module in the Continuous NHANES tutorial also apply to the NHANES II data. Therefore, links to this module in the basic tutorial are provided below for your reference. The following text points out the key differences between NHANES II and continuous NHANES when it comes to variance estimation.
Methods of Variance Estimation
As with the Continuous NHANES, the Taylor Linearization Method is the recommended method for variance estimation that incorporates the complex survey sample design. Replication approaches are also acceptable however replicate weights for the Balanced Repeat Replication (BRR) Method are not available for the NHANES II.
Survey Design Variables
PSEUDO Primary Sampling Units (PSU) and stratification variables are provided in NHANES II, as opposed to the Masked Variance Units (MVU) and strata provided in the Continuous NHANES. However, this difference does not affect how you use the statistical program in variance estimation.
The stratum and PSU variable names necessary to specify the sample design are N2AH0326 for the PSU variable and N2AH0324 for the stratum variable. These are to be used when analyzing the NHANES II survey.