Social Research - Washington State University

Report
Survey Research in Criminology
Survey



Survey is a series of questions asked of
a number of people and designed to
measure the attitudes, beliefs, values,
and personality traits
Measurement tool
Some variables are easy to measure
(demographics)
Measurement


Reliability refers to the extent to which
a measuring instrument contains
variable errors, that is , errors that
appear inconsistently each time a given
unit is measured
Validity is concerned with the question
“Am I measuring what I intend to
measure?”
Vague concepts



Social capital
Commitment to school
Attachment to parents/friends
Measuring “Attachment to
Parents ”



a) time spent with family;
b) importance of parental influence;
c) parents’ involvement in youths’ lives;
High scores on these dimensions will
reflect emotionally close attachment to
parents.
Types of Surveys



Face-to-face (interview)
Self-administered (mail, web)
Phone
Provide
different
answers
Reasons for differences



Social desirability
Acquiescence (culturally-based
tendency to agree)
Norm of even-handedness
Mail Survey




Very popular instrument for research because
it promises to deliver fairly wide coverage for
a study (at reasonable cost, time, and effort)
Compared to personal interview the mail
survey requires no field staff, no money
associated with that
No interviewer bias
Greater privacy for respondents
Disadvantages of Mail Surveys



Nonresponse (20 %)
A number of respondents might
misinterpret the questions
Item nonresponse
Surveys

The goal of writing questions for selfadministered questionnaire is to develop a
query that every potential respondent will
interpret in the same way, be able to
respond accurately, and be willing to
answer
Types of survey questions

Closed-ended format:
Are you _____male ______female?

Open-ended format:
What is the thing that you like most
about your criminology class? Why?
Questionnaire wording



Wording of the questions has an
important impact on results
Respondents can misinterpret even
well-formulated questions
Avoid grammatical complexity that can
lead to trouble
Bad Question

“Living where you do now and meeting
the expenses you consider necessary,
what would be the smallest income
(before any deductions) you and your
family would need to make ends meet
EACH MONTH?”
How answer categories might
impact results of the study






How many hours per
day do you typically
study?
Less than 0.5 hours
0.6 -1 hour
1.1- 2 hours
2.1 – 2.5 hours
More than 2.5 hours






How many hours per
day do you typically
study?
Less than 2.5 hours
2.6 – 3 hours
3.1 – 4 hours
4.1 – 4.5 hours
More than 4.5 hours
Reported Hours of studying
Low version
Telephone
High version
Reported Hours/Day
Mail
Mail
2.5 hours or more
23%
42%
69%
Less than 2.5 hours
77%
58%
31%
Telephone
70%
30%
Vagueness and ambiguity


“Do you think that children suffer any ill
effects from watching programs with
violence in them, other than ordinary
Westerns?”
What is wrong with this question?
Avoid threatening questions


“Do you happen to have murdered your
wife?”
“As you know, many people have been
killing their wives these days. Do you
happened to have killed yours?”
Rules for writing questions

Each respondent has to have a chance
to answer a question
What is wrong with the following
question?
If you fixed dinner at home last
night, did you eat meat as part of that
meal?
 Yes
 No

What is wrong with the following
question?
How often did you attend religious
services during the past year?
 Never
 Rarely
 Occasionally
 Regularly

A revision
How often did you attend religious
services during the past year?







Not at all
A few times
About once a month
Two to three times per month
About once a week
More than once a week
Use equal numbers of positive and
negative categories for scalar questions
How satisfied were you
with the service you
received when you bought
air conditioner?
How satisfied were
you with the service you
received when you
bought air conditioner?


Completely satisfied
 Mostly satisfied
 Somewhat satisfied
 Neither satisfied nor
dissatisfied
 Dissatisfied


Completely satisfied
 Mostly satisfied
 Neither satisfied nor
dissatisfied
 Somewhat dissatisfied
 Dissatisfied
Avoid double-barreled
questions
Should the city build a new
swimming pool that includes lanes for
swimming laps that is not enclosed for
winter use?

Yes

No

A revision
Should the city build a new swimming pool
that includes lanes for swimming laps?
 Yes
 No

Should the city build a new swimming pool
that is not enclosed for winter use?

Yes

No

What is wrong with this question? (Panel
for the evaluation of Crime Surveys)
Were the police informed of this
incident in any way?
 No
 Do not know –Skip to check item G
 Yes-Who told them?
1.Household member
2.Someone else

What is wrong with this question? (Panel
for the evaluation of Crime Surveys)
What were the injures you suffered, if any?








None-skip to question 10
Raped
Attempted rape
Knife or gunshot wounds
Broken bones or teeth knocked out
Internal injures, knocked unconscious
Bruises, black eye, cuts, scratches, swelling
Other____________(specify)
Constructing the
Questionnaire


Easy to understand and answer
Each respondent must comprehend the
questions as well as visual layout in the
same way
In self-administered questionnaires, information is
communicated through four distinct languages, each of
which may independently influence question meaning.
Verbal language: The words used to communicate questions
and directions in questionnaires.
Numeric language: Numbers used to convey a sense of
sequence or order.
Symbolic language: Symbols defined by one’s culture, used to
convey meaning independent of any words.
Graphical language: Variations in the display of words,
numbers, and/or symbols that affect the meaning of words,
numbers, and symbols, because…
Eye Movement Patterns with Equal and
Unequal Information
Under conditions of visually “equal”
information, we tend to follow culturally
prescribed patterns.
When information is visually “unequal”
what we see and comprehend is often
influenced by visual qualities of the
information.
Eye Movement Pattern
Eye Movement Pattern; Unequal Information
Eye Movement Pattern
Gestalt Psychology Principles of Visual
Perception
Principle of Proximity: We tend to
group together things that are close to
one another and more distant from
other (similar) objects.
Principle of Proximity
(Similar figures in closer proximity will be seen
as a group)
Principle of Proximity
(Similar figures in closer proximity will be seen
as a group)
Principle of Proximity
(Similar figures in closer proximity will be seen
as a group)
Principle of Similarity
(Similar figures will be seen as a group.)
Do you see groups?
Principle of Similarity
(Similar figures will be seen as a group.)
Do you see groups?
Figure/Ground Variations Can Also
Facilitate Grouping
It is difficult to switch from one grouping
to the other
extent to
to you
you agree
or disagree that
To what extent
agree or
this sentence is difficult to read? Would you
strongly agree,
agree, somewhat agree,
say that you strongly
opinion, somewhat
have opinion,no
somewhat
disagree or strongly
disagree that this sentence is difficult to read.
Visual Elements: Meaning from Brightness
Meaning comes from culture; brightness variations allows culture to
be expressed.
Visual Elements: Meaning from Brightness
Meaning comes from culture;
brightness variations allow
culture to be expressed.
Figure and Ground
Figure and Ground
PAGE 1, Original Survey
Before
After
PAGE 2, Original Version
BEFORE
AFTER

similar documents