Purpose

The t-test  and chi-square statistics are used to test statistical hypotheses about population parameters.  This module will demonstrate the use of these statistics in NHANES data analysis.

 

Task 1: Use the t-test Statistic

The t-test is used to test the null hypothesis that the means or proportions of two population subgroups are equal OR that the difference between two means or proportions equals zero when the estimates are based on a small probability sample. When using a simple random sample, small is defined as less than 30.

• Key Concepts about Using the t-Test Statistic in NHANES
• How to Set Up a t-test in NHANES Using SUDAAN
• How to Set Up a t-test in NHANES Using SAS 9.2 Survey Procedures
• How to Set Up a t-test in NHANES Using Stata
• Download Sample Code and Datasets

 

Task 2: Generate Confidence Intervals

A confidence interval (CI) gives a range of plausible values of a population parameter, such as a population mean, geometric mean, or percent.  CIs yield a measure of the variability of the point estimate of the parameter obtained by taking a probability sample of the population. NHANES surveys have numerous (continuous) variables on demographic and health characteristics of the U.S. non-institutionalized population, such as a age, serum total cholesterol, and body mass index.  

• Key Concepts about Generating Confidence Intervals in NHANES
• How to Calculate Confidence Intervals for Geometric Means Using SUDAAN
• How to Obtain Confidence Intervals for Geometric Means Using Stata
• Download Sample Code and Datasets

 

Task 3: Perform Chi-Square Test

The chi-square test is used to test the association between two variables cross-classified in a two-way table and the homogeneity of their association.

• Key Concepts about Using the Chi-Square Test in NHANES
• How to Perform a Chi-Square Test in NHANES Using SUDAAN
• How to Perform a Chi-Square Test in NHANES Using SAS Survey Procedures
• How to Perform a Chi-Square Test in NHANES Using Stata
• Download Sample Code and Datasets