Professional Documents
Culture Documents
Basic Survey Methods
Basic Survey Methods
Basic Survey Methods
Questionnaires
Group administration
Questionnaires
Group administration
Mail administration
Questionnaires
Group administration
Mail administration
Personal
Interviews
Personal
Telephone
Selecting the Survey Method
Population Issues
Can the population be enumerated?
Is the population literate?
Are there language issues?
Will the population cooperate?
What are the geographic restrictions?
Sampling Issues
What data is available?
– Addresses
– Phone numbers
Can respondents be found?
Who is the respondent?
– Individual
– Head of household
– Any member of household
– Groups or agencies
Sampling Issues
Can all members of
population be sampled?
Are response rates likely
to be a problem?
et
he
gS ve
ly
tin ecti ely
.
Ra ti me
eff
ec
tiv
nd
Question Issues
ge eff na
na es atio
Ma urc rm
so info t.
1 e re of n
5 ag de orta . ic.
4 Ma
n
ltitu imp sks c if
u le ta spe
3 2 a m hat is ltip not
2 5 an
Sc ide w mu re
c a ge n sa
1 4 de n o
3 ma ec ti
3 to dir
2 5 ow en ide
eh wh ec
1 4 cid ork dd
3 De ew an
54 e th on
2 iz e ly ati
an v
form
1 4
Org ff ec ti in
3 ee of
2 55 tim de
ge itu
1 4 na ult ant.
3 Ma a m port
an im
2 51 Sc at is
1 4 3 w h
3
2 5
1 4
3
2
1
What types of questions can be asked?
How complex will the questions be?
Will screening questions be needed?
Can question sequence be controlled?
Will lengthy questions be asked?
Will long response scales be used?
Content Issues
Can the respondents be expected
to know about the issue?
Will respondent need to consult
records?
Bias Issues
Can social desirability be avoided?
Can interviewer distortion and
subversion be controlled?
Can false respondents be avoided?
Administrative Issues
Costs
Facilities
Time
Personnel
Interviews
The Role of the Interviewer
Locate and enlist cooperation of
respondents.
Motivate respondents to do good job.
Clarify any confusion/concerns.
Observe quality of responses.
Conduct a good interview.
Training the Interviewers
Describe the entire study.
State who is sponsor of research.
Teach enough about survey research
(should respect method and be
motivated).
Explain the sampling logic and process.
Explain interviewer bias.
“Walk through” interview.
Training the Interviewers
Explain selection procedures, including
– Reading maps
– Identifying households
– Identify respondents
Rehearse interview
Explain supervision
Explain scheduling
The Interviewer’s Kit
Official-looking 3-ring notebook
Maps
Sufficient copies of survey
Official identification
A cover letter
A phone number to call
The Interview
Opening remarks
Asking the questions
Obtaining adequate answers
Recording the response
Concluding the interview
Opening Remarks
Gaining entry -- appearance,
confidence, non-threatening
Doorstep technique -- brief, suggest
don’t ask
Introduction -- name, organization,
credentials
Explaining the study -- general, stress
confidentiality
Asking the Questions
Use questionnaire carefully, but
informally.
Ask questions exactly as written
Follow the order given.
Ask every question.
Don’t finish sentences.
Don’t leave any questions blank.
Obtaining Adequate Responses - The
Probe
Silent probe - a pause
Overt encouragement
Elaboration
– How do you mean? Anything else?
Ask for clarification
Repetition
Recording the Response
Record responses immediately
Include all probes (write them in)
Use abbreviations where possible (for
example, R=respondent; DK=don’t
know)
Concluding the Interview
Thank respondent.
Don’t be brusque or hasty.
Immediately after leaving -- write down
any notes about how the interview went.
Types of Questions
Type of Questions
Unstructured
Structured
Structured Questions
Dichotomous
Structured Questions
Dichotomous
____Yes
____No
Male Female
Structured Questions
Nominal
Structured Questions
Nominal
Occupational Class:
1 = Truck driver
2 = Lawyer
3 = etc.
Structured Questions
Ordinal
Structured Questions
Ordinal
Interval
Structured Questions
Interval
1 2 3 4 5
strongly disagree neutral agree strongly
disagree agree
Structured Questions
Interval
Semantic Differential
very some- neither some- very
much what what much
interesting boring
simple complex
uncaring caring
useful useless
etc.
Structured Questions
Interval
Guttman (Cumulative) Scale
Try to avoid having more than three
levels (two jumps) for any question.
If only two levels, use graphic to jump
(for example, arrow and box).
If possible, jump to a new page.
Decisions About Question Wording
Decisions About Question Wording
If you ask what social class someone’s in,
you assume that they know what social
class is and that they think of themselves
as being in one.
Check assumption in a previous question.
Decisions About Question Wording
Do you think Congress will cut taxes?
Do you think Congress will successfully
resist tax cuts?
Neither of these specifies a time frame.
Decisions About Question Wording
How did you feel about being in the war?
- Probably too direct
How well did the equipment hold up in the
field?
How well were new recruits trained?
Decisions About Question Wording
Does question contain difficult or unclear
terminology?
Does the question make each alternative
explicit?
Is the wording objectionable?
Is the wording loaded or slanted?
Decisions About Question Content
Decisions About Question Content
Do you need the age of each child or
just the number of children under 16?
Do you need to ask income or can you
estimate?
Decisions About Question Content
What are your feelings towards African-
Americans and Hispanic-Americans?
What do you think of proposed changes
in benefits and hours?
Decisions About Question Content
If you ask about earnings, might not
mention all income
If ask if they’re in favor of public TV, ask
for whom (might not mention it’s because
of Sesame Street for the kids)
Decisions About Question Content
If you ask about attitudes towards
Catholics, can you interpret this without
finding out about their attitudes towards
religion?
Decisions About Question Content
If they say they support public TV, do
they watch it?
If they would be willing to have their tax
dollars spent on it?
Decisions About Question Content
‘Do you think Dean Rusk acted correctly
in the Bay of Pigs crisis?’ -- can’t say if
they don’t know who he is.
In TV surveys, ‘regular’ watchers can be
asked about program content, ‘never
watch’ should not be asked.
Decisions About Question Content
How well did you like the book?
Versus...
Did you recommend the book to others?
Did you look for other books by that
author?
Decisions About Question Content
For instance, seasonal specificity.
If you ask what they usually watch and
it’s summer, you’ll get a different answer
than in the winter.
Decisions About Question Content
Ask about the benefits of a tax cut
without asking about the disadvantages
Ask about the disadvantages of
eliminating welfare without asking about
the benefits
Decisions About Question Content
To find out age or income, give brackets.
To find out about charitable
contributions, ask how much “people you
know” typically give.
To find out what magazines they read,
offer to buy used ones.
Levels of Measurement
The Levels of Measurement
Nominal
Ordinal
Interval
Ratio
Some Definitions
Variable
Variable
Some Definitions
Variable
Variable
Attribute
Attribute Attribute
Attribute
Some Definitions
Variable
Variable Gender
Gender
Attribute
Attribute Attribute
Attribute
Some Definitions
Variable
Variable Gender
Gender
Attribute
Attribute Attribute
Attribute Female
Female Male
Male
Qualities of Variables
Exhaustive -- Should include all
possible answerable responses.
Mutually exclusive -- No respondent
should be able to have two attributes
simultaneously (for example, employed
vs. unemployed -- it is possible to be
both if looking for a second job while
employed).
What Is Level of Measurement?
The relationship of the values that are
assigned to the attributes for a variable
What Is Level of Measurement?
The relationship of the values that are
assigned to the attributes for a variable
Relationship
What Is Level of Measurement?
The relationship of the values that are
assigned to the attributes for a variable
Values 1 2 3
Relationship
What Is Level of Measurement?
The relationship of the values that are
assigned to the attributes for a variable
Values 1 2 3
Relationship
What Is Level of Measurement?
The relationship of the values that are
assigned to the attributes for a variable
Values 1 2 3
Relationship
Why Is Level of Measurement
Important?
Helps you decide what statistical
analysis is appropriate on the values
that were assigned
Helps you decide how to interpret the
data from that variable
Nominal Measurement
The values “name” the attribute
uniquely.
Nominal Measurement
The values “name” the attribute
uniquely.
The name does not imply any
ordering of the cases.
Nominal Measurement
The values “name” the attribute
uniquely.
The value does not imply any
ordering of the cases, for example,
jersey numbers in football.
Nominal Measurement
The values “name” the attribute
uniquely.
The value does not imply any
ordering of the cases, for example,
jersey numbers in football.
Even though player 32 has higher
number than player 19, you can’t say
from the data that he’s greater than or
more than the other.
Ordinal Measurement
Has an absolute zero that is meaningful
Ratio Measurement
Has an absolute zero that is meaningful
Can construct a meaningful ratio
(fraction)
Ratio Measurement
Has an absolute zero that is meaningful
Can construct a meaningful ratio
(fraction), for example, number of
clients in past six months
Ratio Measurement
Has an absolute zero that is meaningful
Can construct a meaningful ratio
(fraction), for example, number of
clients in past six months
It is meaningful to say that “...we had
twice as many clients in this period as
we did in the previous six months.
The Hierarchy of Levels
Nominal
The Hierarchy of Levels
Ordinal
Interval
Ordinal Attributes can be ordered
Ratio
Interval Distance is meaningful
1=strongly disagree
2=disagree
et
he
gS ely
tin c tiv .
Ra ime
effe
t ffe
ctiv
ely
nd
na
ge se na
Ma urce atio
o rm
3=undecided
1 e res f info t.
5 g o an
na ude port s. .
4 Ma ultit im ask ec
ific
a m hat is le t t sp
3 2 ltip no
2 5 an
Sc ide w e mu are
g s
4 de
c na tion
1 3 ma
3 to irec
ow nd
4=agree
2 5 eh he e
cid kw cid
1 4
D e o r de
w nd
3 the na
2 54 n ize el y a tio
a ctiv m
1 4 Org ffe for
3 ee f in
5 tim eo
2 5
ge tud .
na ulti r tant
5=strongly agree
1 4 a m
3 M a po
an im
2 51 Sc at is
1 4 3 wh
3
2 5
1 4
3
2
1
Deciding Which Items to Select
Item-total
Throw out items that have a low
correlations correlation with the total
(summed) score across all
items.
Internal
For each item, get the average
consistency rating for the top quarter of
judges and the bottom quarter.
Do t-test; higher t-values mean
the items are better
discriminators, so keep them.
How Does Respondent Use?
Gives a 1-to-5 (or sometimes a 0-to-4)
rating for each item on the scale.
Sum these across all items.
This is why this is sometimes called a
“summated” scale.
don’t forget to reverse any reversal
items.
Guttman Scaling
Guttman Scaling
Also known as
– Scalogram analysis
– Cumulative scaling
Purpose:
– Establish a one-dimensional continuum
– Perfectly predict item responses from total
score
– Seldom perfect in practice
Guttman Scaling
There are several statistical techniques
for examining the table to find a
cumulative scale.
Because there is seldom a perfectly
cumulative scale, we usually have to
test how good it is.
These statistics also estimate a scale
score value for each item.
How Does Respondent Use?
For selected items (the final scale), they
simply answer whether they agree or
not (yes/no).
Since each item has a scale value, we
can add these values.
Total score is the sum of the scale items
respondent agreed to.
Thurstone Scaling
Thurstone Scaling - Methods
Equal-appearing intervals
Successive intervals
Paired comparison
Equal-Appearing Intervals
1 2 3 4 5 6
Manage resources effectively. Organize the work when
4 directions are not specific.
39
7 8 9 10 11
Decide how to manage
multiple tasks.
20
25
20
15
10
0
1 2 3 4 5 6 7 8 9 10 11
Equal-Appearing Intervals
25
20
15
10
0
1 2 3 4 5 6 7 8 9 10 11
25
20
15
10
0
1 2 3 4 5 6 7 8 9 10 11
1 2 3 4 5 6 7 8 9 10 11
Decide how to manage Organize the work when Decide how to manage Organize the work when Organize the work when
multiple tasks. directions are not specific. multiple tasks. directions are not specific. directions are not specific.
20 39 20 39 39
Follow a specific procedure for
sorting/comparing items in terms of
the concept of interest.
Use a simple statistical analysis to
determine scale value for each item.
Select items from across the scale
range.
How Does Respondent Use?
Respondent checks agree or disagree
for each item.
The respondent’s total score is the
average scale value of all the items
agreed to.
General Issues in Scaling
What Is a Scale?
The assignment...
What Is a Scale?
The assignment...
...of objects...
The assignment...
...of objects... ...to numbers...
The assignment...
...of objects... ...to numbers...
...according to a rule...
What Is a Scale?
The assignment...
...of objects... ...to numbers...
...according to a rule...
Scale Versus Response Scale
One-dimensional constructs
Dimensionality
One-dimensional constructs
Height
Dimensionality
One-dimensional constructs
Height
Shorter Taller
Dimensionality
One-dimensional constructs
Height
Shorter Taller
Thirst
Dimensionality
One-dimensional constructs
Height
Shorter Taller
Thirst
Less thirsty More thirsty
Dimensionality
One-dimensional constructs
Height
Shorter Taller
Thirst
Less thirsty More thirsty
Self-esteem
Dimensionality
One-dimensional constructs
Height
Shorter Taller
Thirst
Less thirsty More thirsty
Self-esteem
Less More
Dimensionality
Two-dimensional construct
Dimensionality
Two-dimensional Construct
Academic ability
Dimensionality
Two-dimensional construct
Academic ability
Verbal
Dimensionality
Two-dimensional construct
Academic ability
Verbal
Worse Better
Dimensionality
Quantitative
Two-dimensional construct
Academic ability
Verbal
Worse Better
Dimensionality
Quantitative
Two-dimensional construct
Better
Academic ability
Verbal
Worse Better
Worse
Dimensionality
Three-dimensional construct
Dimensionality
Three-dimensional construct
Dimensionality
Evaluation
Dimensionality
Evaluation
Unfavorable Favorable
Dimensionality
Potency
Evaluation
Unfavorable Favorable
Dimensionality
Potency
Powerful
Evaluation
Powerless
Unfavorable Favorable
Dimensionality
Activity Potency
Powerful
Evaluation
Powerless
Unfavorable Favorable
Dimensionality
Activity Potency
Powerful
Passive
Evaluation
Powerless
Unfavorable Favorable
Types of Scales
One-dimensional
Easier to understand
Useful for
understanding
multidimensional
Many concepts may be
one-dimensional
Multidimensional
Reflect multiple
properties
simultaneously
The Major One-Dimensional Scale Types
Thurstone
Likert
Guttman