Page 275 - Statistics for Dummies

Chapter 16: Polls, Polls, and More Polls
Regarding the quality of results, selecting a smaller initial sample size and fol-

lowing them up more aggressively is a much better approach than selecting a
larger group of potential respondents and having a low response rate, because
of the bias introduced by non-response.
Interpreting results and finding problems
The purpose of a survey is to gain information about your target population; 259
this information can include opinions, demographic information, or lifestyles
and behaviors. If the survey has been designed and conducted in a fair and
accurate manner with the goals of the survey in mind, the data should pro-
vide good information as to what’s happening with the target population
(within the stated margin of error; see Chapter 12). The next steps are to
organize the data to get a clear picture of what’s happening; to analyze the
data to look for links, differences, or other relationships of interest; and then
to draw conclusions based on the results.
Organizing and analyzing
After a survey has been completed, the next step is to organize and analyze
the data (in other words, crunch some numbers and make some graphs).
Many different types of data displays and summary statistics can be created
and calculated from survey data, depending on the type of information that
was collected. (Numerical data, such as income, have different character-
istics and are usually presented differently than categorical data, such as
gender.) For more information on how data can be organized and summa-
rized, see Chapters 5 through 7. Depending on the research question, differ-
ent types of analyses can be performed on the data, including coming up with
population estimates, testing a hypothesis about the population, or looking
for relationships, to name a few. See Chapters 13, 14, 15, 18, and 19 for more
on each of these analyses, respectively.

Watch for misleading graphs and statistics. Not all survey data are organized
and analyzed fairly and correctly. See Chapter 3 for more about how statistics
can go wrong.

Drawing conclusions
The conclusions are the best part of any survey — they’re why the research-
ers do all of the work in the first place. If the survey was designed and carried
out properly — the sample was selected carefully and the data were organized
and summarized correctly — the results should fairly and accurately repre-
sent the reality of the target population. But, of course, not all surveys are
done right. And even if a survey is done correctly, researchers can misinter-
pret or overinterpret results so that they say more than they really should.

3/25/11 8:13 PM
24_9780470911082-ch16.indd 259 3/25/11 8:13 PM
24_9780470911082-ch16.indd 259