Page 269 - Statistics for Dummies

Chapter 16: Polls, Polls, and More Polls
Designing the introduction with ethics in mind
While this rule doesn’t apply to little polls that you see on the Internet and in
magazines, serious surveys need to provide information pertaining to impor-
tant ethical issues. First, they should include what pollsters call a cover letter —
an introduction that explains the purpose of the survey, what will be done with
the data, whether the information the respondent supplies will be confidential
or anonymous (see the sidebar “Anonymity versus confidentiality” later in this
chapter), and that the person’s participation is appreciated but not required. 253
The cover letter should also provide the researcher’s contact information for
respondents to use if they have questions or concerns.
If the survey is done by any institution or group that is federally regulated,
such as a university, research institute, or a hospital, the survey has to be
approved in advance by a committee designated to review, regulate, and/or
monitor the research to make sure it’s ethical, scientific, and follows regula-
tions. Such committees are called institutional review boards (IRBs), indepen-
dent ethics committees (IECs), or ethical review boards (ERBs). The survey
cover letter should explain who has approved the research. If you don’t see
such information, ask.
Formulating the questions
After the purpose, type, timing, and ethical issues of the survey have been
addressed, the next step is to formulate the questions. The way that the
questions are asked can make a huge difference in the quality of the data that
will be collected. One of the single most common sources of bias in surveys
is the wording of the questions. Research shows that the wording of the
questions can directly affect the outcome of a survey. Leading questions, also
called misleading questions, are designed to favor a certain response over
another. They can greatly affect how people answer the questions, and their
responses may not accurately reflect how they truly feel about an issue.

For example, here are two ways that I’ve seen survey questions worded
about a proposed school bond issue (both of which are leading questions):
Don’t you agree that a tiny percentage increase in sales tax is a worthwhile
investment in improving the quality of the education of our children?
Don’t you think we should stop increasing the burden on the taxpayers and
stop asking for yet another sales tax hike to fund the wasteful school system?

From the wording of each of these leading questions, you can easily see how
the pollsters want you to respond. To make matters worse, neither question
tells you exactly how much of a tax increase is being proposed, which is also
misleading.

The best way to word a question is in a neutral way, giving the reader the nec-
essary information required to make an informed decision. For example, the
tax issue question is better worded this way:

3/25/11 8:13 PM
24_9780470911082-ch16.indd 253 3/25/11 8:13 PM
24_9780470911082-ch16.indd 253