SURVEY RESEARCHBeing valid and reliable means that the respondents
should quickly grasp each question’s meaning as
you intended, answer completely and honestly, and
believe that their answers are meaningful.
You do not want questions that confuse or frus-
trate respondents. This means that you must exer-
cise extra care if the respondents are heterogeneous,
come from life situations unfamiliar to you, or have
different priorities than yours. You must be vigilant
if the respondents use a different vocabulary or think
in different ways than you do.
You want the questions to be equally clear, rel-
evant, and meaningful to all respondents, but you face
a dilemma. If the respondents have diverse back-
grounds and frames of reference, the same question
wording may not have the same meaning for every-
one, yet you want everyone to hear the same ques-
tion because you will combine all answers into
numerical data for analysis. If each question is tai-
lored to each respondent, you would not know
whether variations in the data are due to question
wording or real differences among the respondents.
Survey question writing takes skill, practice,
patience, and creativity. You can understand princi-
ples of question writing by knowing ten things to
avoid when you write survey questions. The list
includes only frequently encountered potential
problems.^131.Avoid jargon, slang, and abbreviations.
Jargon and technical terms come in many forms.
Plumbers talk about snakes,lawyers about a con-
tract of uberrima fides,and psychologists about the
Oedipus complex.Slang is a kind of jargon within
a subculture. For example, people who are home-
less talk about a snowbird,and snowboarders talk
about goofy foot. People inside a profession or
members of a distinct subculture may be familiar
and comfortable with the jargon or slang terms but
only confuse outsiders. Also, avoid using abbrevi-
ations and acronyms. The same ones often have
many meanings. For example, I received a letter
from the Midwest Sociological Society (MSS).
Look up the acronym, and you will see that MSS
refers to Manufacturers Standardization Society,
Marine Systems Simulator, Medical Student Soci-
ety, and Minnesota Speleological Society, among a
dozen others that use the MSS abbreviation. I belong
to a professional association, the Association
for Asian Studies, or AAS. Six other academic
organizations use the same acronym: American
Astronomical Society, American Association of
Suicidology, American Audiology Society, Ameri-
can Astronautical Society, American Antiquarian
Society, and the Assyrian Academic Society.
When you survey the public, you should use
the language of popular culture (i.e., what is on
television or in a local newspaper with about an
eighth-grade reading vocabulary). Survey research-
ers have found that respondents often misun-
derstand basic terms and are confused by many
words. For example, a survey asked respondents
whether they thought television news was impar-
tial. Researchers later learned that large numbers of
respondents had ignored the word impartial—a
term the researchers assumed everyone would
know. Less than half of the respondents had inter-
preted the word as intended with its proper mean-
ing. More than one-fourth had no idea of its
meaning; others gave it unusual meanings, and one-
tenth thought it was directly opposite to its true
meaning. In another case, one in four respondents
who had less than a high school degree (about 20
percent of the U.S. adult population) did not know
what vaginal intercoursemeant.^14
2.Avoid ambiguity, confusion, and vague-
ness.Ambiguity and vagueness plague most ques-
tion writers. It is very easy to make implicit
assumptions that can confuse respondents. For
example, the question “What is your income?”
could mean weekly, monthly, or annually; family or
personal; before taxes or after taxes; for this year or
last year; from salary or from all sources. Such con-
fusion can cause inconsistencies in respondents’
answers to the question. If you want before-tax
annual family income for last year, you should
explicitly ask for it. Many respondents may not
know this, but they tell you their weekly take-home
pay (see item 6 following as to questions beyond
respondent capabilities).^15 Indefinite words or
response categories are also sources of ambiguity.
For example, an answer to the question “Do you
jog regularly? Yes _____ No _____ ” hinges on the
meaning of the word regularly.Some respondents