Purpose

This module introduces the basic concepts of variance (sampling error) estimation for NHANES data.  You will learn how the complex survey design of NHANES and clustering of the data affect variance estimation, which methods are appropriate to use when calculating variance for NHANES data, and how to calculate degrees of freedom and construct confidence limits for NHANES estimates.

 

Task 1: Explain Variance Estimation Within NHANES

This first task describes the importance of accounting for the complex sampling structure of NHANES when estimating variances. In general, using statistical weights that reflect the probability of selection and propensity of response for sampled individuals will affect parameter estimates, while incorporating the attributes of the complex sample design (i.e. differential weighting, clustering and stratification) will affect variance estimates (estimated standard errors and thereby test statistics and confidence intervals).

• Key Concepts about Variance Estimation Within NHANES

 

 

Task 2: Describe Methods for Variance Estimation Used in NHANES

The second task briefly describes the method used to calculate variance estimates with NHANES data and the sample design parameters required.

• Key Concepts about Variance Estimation Methods in NHANES
• How to Use the Method for Variance Estimation in NHANES with SUDAAN
• How to Use the Method for Variance Estimation in NHANES with SAS Survey Procedures
• Download Sample Code and Dataset

 

 

Task 3: Calculate Degrees of Freedom for Performing Statistical Tests and Calculating Confidence Limits

This third task will discuss calculation of degrees of freedom using SUDAAN and SAS Survey procedures. The accurate determination of degrees of freedom is important for performing statistical tests and calculating confidence limits.

• Key Concepts about Degrees of Freedom for Performing Statistical Tests and Calculating Confidence Limits
• How to Perform Statistical Test and Calculate Confidence Limits with Degrees of Freedom
• Download Sample Code and Dataset