Page 278 - Statistics for Dummies

262
Part V: Statistical Studies and the Hunt for a Meaningful Relationship
Boiling Down the Basics of Studies
Although many different types of studies exist, you can basically boil them
down to two types: experiments and observational studies. This section
examines what exactly makes experiments different from other studies. But
before I dive in to the details, I need to lay some jargon on you.
Looking at the lingo of studies
To understand studies, you need to find out what their commonly used terms
mean:
✓ Subjects: Individuals participating in the study.
✓ Observational study: A study in which the researcher merely observes
the subjects and records the information. No intervention takes place,
no changes are introduced, and no restrictions or controls are imposed.
✓ Experiment: This study doesn’t simply observe subjects in their natural
state; it deliberately applies treatments to them in a controlled situation
and studies their effects on the outcome.
✓ Response: The response is the variable whose outcome is the million
dollar question; it’s the variable whose outcome is of interest. For exam-
ple, if researchers want to know what happens to your blood pressure
when you take a large amount of Ibuprofen each day, the response vari-
able is blood pressure.
✓ Factor: A factor is the variable whose effect on the response is being
studied. For example, if you want to know whether a particular drug
increases blood pressure, your factor is the amount of the drug taken.
If you want to know which weight loss program is most effective, your
factor would be the type of weight loss program used.
You can have more than one factor in a study; however, in this book
I stick with discussing one factor only. For the analysis of two-factor
studies, including the use of Analysis of Variance (ANOVA) and multiple
comparisons to compare treatment combinations, you can check out my
book Statistics II For Dummies, also published by Wiley.
✓ Level: A level is one possible outcome of a factor. Each factor has a cer-
tain number of levels. In the weight loss example, the factor is the type
of weight loss program and the levels would be the specific programs
studied (for example Weight Watchers, South Beach, or the famous
Potato Diet). Levels need not be ascending in any way; however, in a
study like the drug example, the levels would be the various dosages
taken each day, in increasing amounts.

3/25/11 8:13 PM
25_9780470911082-ch17.indd 262
25_9780470911082-ch17.indd 262 3/25/11 8:13 PM