The Center of Disease Control conducts national surveys to collect various health related data in order to monitor the health situation for the Americans. One of the surveys is the Youth Risk Behavior Survey which is a survey to understand the health behavior of the young Americans. A sample of data is created using data from 1999, 2001, and 2003. The original goal was to model the weight of the youth and to understand the significance of the various youth behavior factor that would affect their weights, such as exercise, eating and others.

Data Files:

SPSS data file - CDCWeight.sav

EXCEL data file - CDCWeight.xls

In this data, the** bmi_age**
is an age-adjusted weight category variable. It categorizes the weight of
individuals in the data into four categories:

- Underweight,
- Normal,
- At risk of overweight,
- Overweight.

The definitions for the rest of the variables in the data set are described in the SPSS data file. You may use this data to set up your research hypothesis and test your hypothesis or perform confidence interval estimation.

Possible hypotheses could be:

- Correlation between weight and eating habits.
- Correlation between weight and exercise.
- Correlation between weight and TV watching.
- ...

You may generate many hypotheses from this data set.