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

Module Content Objectives Background Comparing Means Attrition Versus Loss to Followup New Information: Change Scores and Participation How To Construct Scatter Plots How To Interpret Scatter Plots Linear Relationship Strength of the Relationship: Pearson's Correlation Coefficient What Do All the Numbers and Plots Mean? Adding Points to a Scatter Plot Lessons Learned: What Jack Should Have Asked His Evaluator What Did Jack Learn About His Program From These Analyses? How Can Jack Use This Statistical Information to Improve His Program? How Can Jack Use This Statistical Information To Better Promote His Program? Module 4 Quiz

Attrition Versus Loss to Followup

When kids drop out of a program, we call this attrition. If the kid does not attend on a certain day and we cannot collect data, we call this loss to followup. Jack has been very lucky because he has been able to collect some data on all 50 of his participants. The only data he is missing are two answers to the marijuana question at posttest. It's important to understand attrition and loss to followup, because both can affect your data and lead to biased results.

Attrition may make your program look successful when it may not be. If kids are dropping out, it could be that the program isn't working for them and their drug use could be increasing. Since you probably won't have the followup data on the dropouts, those possible high scores will not be included in your drug use data. Therefore, the posttest mean for drug use will be lower because it excludes dropouts.

On the other hand, loss to followup could make a successful program look unsuccessful. Suppose some kids have stayed in the program all along but for whatever reason have missed the days on which data were collected. Maybe they were sick or had plans to visit their grandparents. Who knows?

In this case, the kids who were absent for data collection would be more likely to have lower levels of drug use. Again, since you won't have the data on these kids, their scores will not be included in your data analysis.