Page 272 - Statistics for Dummies

256
Part V: Statistical Studies and the Hunt for a Meaningful Relationship
With large populations (in the thousands, say) it’s the size of the sample, not

the size of the population, that matters. For example, if you randomly sample
1,000 individuals from a large population, your accuracy level is estimated to
be within 3.2 percentage points, no matter whether you sample from a small
town of 10,000 people, a state of 1,000,000 people, or all of the United States.
That fact was one of the things that blew my mind about statistics when I first
learned it, and it still does today — it’s amazing how accurate you can get with
such a comparatively small sample size.
However, with small populations, you have to apply different methods to
determine accuracy and sample size. A sample of 10 out of a population of 100
takes a much larger piece out of the pie than a sample of 10 out of 10,000 does,
for example. More advanced methods involving a finite population correction
handle issues that come up with small populations.
Carrying out a survey
The survey has been designed, and the participants have been selected. Now
you have to go about the process of carrying out the survey, which is another
important step — one where lots of mistakes and biases can occur.
Collecting the data
During the survey itself, the participants can have problems understanding
the questions, they may give answers that aren’t among the choices (in the
case of a multiple choice question), or they may decide to give answers that
are inaccurate or blatantly false; the latter is called response bias. (As an exam-
ple of response bias, think about the difficulties involved in getting people to
tell the truth about whether they’ve cheated on their income-tax forms.)

Some of the potential problems with the data-collection process can be
minimized or avoided with careful training of the personnel who carry out
the survey. With proper training, any issues that arise during the survey are
resolved in a consistent and clear way, and fewer errors are made in record-
ing the data. Problems with confusing questions or incomplete choices for
answers can be resolved by conducting a pilot study on a few participants
prior to the actual survey and then, based on their feedback, fixing any prob-
lems with the questions.
Personnel can also be trained to create an environment in which each respon-
dent feels safe enough to tell the truth; ensuring that privacy will be protected
also helps encourage more people to respond. To minimize interviewer bias,
the interviewers must follow a script that’s the same for each subject.

3/25/11 8:13 PM
24_9780470911082-ch16.indd 256
24_9780470911082-ch16.indd 256 3/25/11 8:13 PM