Page 280 - Statistics for Dummies

264
Part V: Statistical Studies and the Hunt for a Meaningful Relationship
Examining experiments
The object of an experiment is to see if the response changes as a result of
the factor you are studying; that is, you are looking for cause and effect. For
example, does taking Ibuprofen cause blood pressure to increase? If so, by
how much? But because results will vary with any experiment, you want to
know that your results have a high chance of being repeatable if you found
something interesting happening. That is, you want to know that your results
were unlikely to be due to chance; statisticians call such results statistically
significant. That’s the objective of any study, observational, or experimental.
A good experiment is conducted by creating a very controlled environment —
so controlled that the researcher can pinpoint whether a certain factor or
combination of factors causes a change in the response variable, and if so,
the extent to which that factor (or combination of factors) influences the
response. For example, to gain government approval for a proposed blood
pressure drug, pharmaceutical researchers set up experiments to determine
whether that drug helps lower blood pressure, what dosage level is most
appropriate for each different population of patients, what side effects (if any)
occur, and to what extent those side effects occur in each population.
Designing a Good Experiment
How an experiment is designed can mean the difference between good
results and garbage. Because most researchers are going to write the most
glowing press releases that they can about their experiments, you have to
be able to sort through the hype to determine whether to believe the results
you’re being told. To decide whether an experiment is credible, check to see
if it meets all the following criteria for a good experiment. A good experiment:
✓ Makes comparisons
✓ Includes a large enough sample size so that the results are accurate
✓ Chooses subjects that most accurately represent the target population
✓ Assigns subjects randomly to the treatment group(s) and the control
group
✓ Controls for possible confounding variables
✓ Is ethical
✓ Collects good data
✓ Applies the proper data analysis
✓ Makes appropriate conclusions
In this section, each of these criteria is explained and illustrated with examples.

3/25/11 8:13 PM
25_9780470911082-ch17.indd 264
25_9780470911082-ch17.indd 264 3/25/11 8:13 PM