CONTENTS

Table of Contents
Introduction

1. Evaluation and the Program Planning Process
2. Data Analysis, or "What Do You Mean by That?"
3. Special Challenges in Evaluating Prevention Programs

Supplements
Resources

Evaluation for the Unevaluated:
Program Evaluation 102

Descriptive Statistics

Various types of statistics can be used to illustrate results and draw conclusions. These include mean, median, and mode.

Mean

The mean is the average of a group of numbers. For example, the Cool After School participants used marijuana a total of 85 days. Thus, mean marijuana use was 1.7 days. This is the total number of days divided by the number of participants (85/50 = 1.7).

Median

The median is the halfway point. Half the numbers are above a certain point and half are below. In Jack's program, median alcohol use was 2 days. Half the participants used alcohol fewer than 2 days and half used alcohol more than 2 days. For marijuana, the median was 0 days.

Mode

The mode is the most common response. In Jack's program, the mode for marijuana use was 0 days, because more kids reported 0 than any other number. The mode for alcohol use was 2 days. Thus, more students used alcohol than marijuana.

Using the Statistics

Before - What do all these numbers mean and what do you do with them? They can help you determine needs and program accordingly.

For example, these statistics indicate that alcohol is the most commonly used substance. This is a key piece of information for Jack in planning educational activities; it tells him he needs to focus on alcohol.

After - Statistics can also show whether your program worked.

For example, if mean alcohol use declines, the program is helping. If mean alcohol use increases, changes may be needed. But, as you'll see in Evaluation 201, it's important to look at all the data carefully before drawing any conclusions.

It's also important to understand that any results are open to interpretation. For example, some people would consider a decrease in marijuana among boys a big success even if girls' use didn't decline. Others would consider it a failure if marijuana use among girls didn't decrease as well. Looking at data in different ways can give you an idea of what worked. It may be that your program succeeds in some ways and needs improvment in others.