CONTENTS

Table of Contents
Introduction

1. Descriptive Statistics in Evaluation
2. Subgroup Analysis
3. Variable - Are They Related?
4. Correlation
5. The t-Test of Difference Between Means

Supplements
Resources
Glossary

Wading Through the Data Swamp:
Program Evaluation 201

Mean Alcohol Use

Now let's look at these same kids' response to the GPRA Youth Survey Alcohol Question (Question 1).

Days of Alcohol Use, Past 30 Days

Here's how the scores look plotted on a graph.

For these alcohol use scores, the mean is 1.64.
The median is 2 (half the scores are above 2, half below).
The mode is also 2 (the most common response).

The responses to this question show that nearly all (90 percent) of the kids were drinking some alcohol before they entered the program, but few of them drink that much. (At least not as much as the marijuana smokers used pot). Only two said they drank more than 1 to 2 days in the past 30.

This figure looks much more like a bell shape than the marijuana curve but is still not normally distributed. In order to know for sure we would need to check the skewness of the distribution. This can be done by an evaluator using a statistical software package such as SPSS or SAS.

This example shows us that we can have almost the same mean for past month use of alcohol and marijuana. However, the numbers of kids using are extremely different, as shown by the differences in the shape of the distributions. In this case, 30 percent of kids report using marijuana compared to 90 percent of kids using alcohol.