Review Data and Create New Variables

Purpose

Reviewing NHANES dietary data and creating new variables may be necessary before you can use the variables in the dataset.  NHANES data may need to be adjusted if the dataset has missing data, skip patterns, or outliers.  Depending on the purpose of your analysis, you also may need to create new variables (e.g., create food groups from individual food codes).  

Task 1: Identify, Recode, and Evaluate Missing Data

Missing values may distort your analysis results. You must evaluate the extent of missing data in your dataset to determine whether the data are useable without additional re-weighting for item non-response.

• Key Concepts about Missing Data in NHANES
• How to Identify and Recode Missing Data

Task 2: Check for Skip Patterns and Explain How They Affect Results

The significance of a skip pattern depends on the question leading to the skip pattern, the questions within that skip pattern, and the variables you intend to analyze.

WARNING

If you fail to address skip patterns, you may obtain data on only a proportion of the sample, instead of the entire survey sample.

• Key Concepts about Skip Patterns in NHANES
• How to Identify and Recode Skip Patterns in NHANES Data

 

Task 3: Check the Data for Influential Outliers

Before you analyze your data, it is very important that you identify outliers and determine how they might affect your analysis.

• Key Concepts about Outliers in NHANES
• How to Identify Outliers and Evaluate Their Impact

 

Task 4: Create New Variables

The nature of the dietary data requires you to be facile in the methods you use to create variables. Therefore, it is important that you know various ways to recode data to create a new variable. Creating new variables is an extremely important step for preparing an analytical dataset using dietary data, if you want to regroup foods into new groups or create new food groups using individual food codes.

• Key Concepts about Creating New Variables in NHANES
• How to Create New Variables