Survey Research
Week 6 Lecture 1
1
General features
Large-scale probability sampling
A study on snipping behavior of online auction
took 368 eBay bidders as respondents
Systematic Procedures: Interviews and
questionnaires
Answers are numerically coded and analyzed
with the aid of statistical software
Used extensively for both descriptive and
explanatory purposes
16/04/03 Survey Research 2
Survey research designs
Cross-sectional design
Collects data at one time
Longitudinal Designs
Takes place over time with two or more data
collections
Trend design
Each survey collects data on the same items or variables
with a new independent sample of the same target
population
Panel studies
Each survey collects data at different times from the
same respondents
16/04/03 Survey Research 3
Data collection methods
Face-to-face interviewing
High cost
High response rate
Maximize trust and cooperation
Telephone interviewing
45%-60% of cost of face-to-face interview
High response rate
Difficult to gain trust and cooperation
Self-administered questionnaires
Hand delivered
Mail survey
Web survey
16/04/03 Survey Research 4
Item styles
Open-ended question
Respondents answer in their own words
Closed-ended question
Respondents choose a response from those provided
Examples
What drives you to bid in the last minutes in a second-price
auction? (OPEN)
Which one of the factors listed below drives you to bid in the
last minutes? (CLOSE)
() Checking around if there are other auctions offering the same
item
() Don’t want other bidders get benefit from my expertise of the
auction item
() Avoid bidding war
() Other _____________(please explain)
16/04/03 Survey Research 5
Open vs. closed
Open-ended question
Great freedom for respondent to answer
Responses may be ambiguous
Coding is time-consuming and costly which
usually results in some degree of error
Entail more work from respondents
Closed-ended question
Require less effort and less facility with words
Difficult to develop good closed questions
Recommendation for designing closed-end
question: use open questions in preliminary
interviews or pretests
16/04/03 Survey Research 6
Open or closed?
General guidelines
The objective of the survey
The level of information possessed by
respondents in regard to the topic
How well respondents’ opinions are
thought out or structured
Motivation of respondents to communicate
16/04/03 Survey Research 7
Response formats
Pre-coded single-choice questions
What year are you in?
First year --------------- 1( )
Second year --------------- 2( )
Third year --------------- 3( )
Forth year/honors --------------- 4( )
Presence-absence questions
Thinking back the E-tailers you’ve purchased from, have you ever? (Circle to indicate
“yes” or “no”)
Yes No
Provided feedback on the products or services they sell ----- 1 0
Completed a survey for that e-tailer ----- 1 0
Bought anything else recommended by that e-tailer ----- 1 0
16/04/03 Survey Research 8
Response formats (II)
Rank-ordering questions
Rank-order the three most important things you want in the job you make your
life’s work? (1 indicates the most important one)
______ Making a lot of money
______ Being creative
______ Being free from supervision
______ Having opportunities for advancement
______ Avoiding a high pressure job
Likert-style questions
Respondents are asked to indicate the degree of
their agreement or disagreement with a statement
Lots of variations to assess attitudes and opinions
16/04/03 Survey Research 9
Existing questions
Questions that have been used in
previous research
Shortcuts the measurement and testing
processes
Enables researchers to compare results
across studies
Unless questionnaire items have been
copy-righted, no permission is required
16/04/03 Survey Research 10
Sketches or Preliminaries
Cover letter
Identifying researcher and survey sponsor
General purpose and importance of the study
Description of the survey
The opening question
Interesting and non-threatening topic
Begin with an open-ended question
The placement of sensitive and routine questions
Uninteresting routine questions such as background
information are often placed toward the end of the survey
instrument
Fit sensitive questions into the question sequence logically
16/04/03 Survey Research 11
Using language effectively
Are the items unambiguous, easily read and
sufficiently brief
Avoid indefinite words such as “usually”, “seldom”, “many”,
“few”, “here”, “there”
How often do you use Internet?
() Seldom or never
() Often
() Very often
Is the instrument’s vocabulary appropriate for the
respondents you intend to interview?
Which technologies are enabled in your smart device?
() Bluethoose
() Wi-fi
() GSM
16/04/03 Survey Research 12
Using language effectively(II)
Do the questions contain a single idea, or any
of them addressing two or more issues at
once?
Double-barreled question – two separate
ideas are presented together as a unit
The system is easy to use and helpful
Avoid using “and”, “or” in any questions
16/04/03 Survey Research 13
The frame of reference problem
Respondents may answer a question from
several perspectives or frames of reference
Follow the question with some probe
Specify the frame of reference within the
question
Use a set of questions
Moves from a general question to progressively
more specific questions
Begins with the most specific questions and ends
with the most general
16/04/03 Survey Research 14
Pretesting
Cognitive interviewing
Identify potential wording, ordering and formatting
problems
“Thinkaloud” interviews
The respondents are asked to think out loud, reporting
everything that comes to mind, while arriving an answers
to the question
Pilot study
Having a small sample of respondents complete
the questionnaire or undergo the interview
If the results of cognitive testing can be
generalized under realistic interviewing conditions
16/04/03 Survey Research 15
Interviews
Unstructured interview
General objectives, wide ranging discussion and
spontaneous individual questions
Structured interview
Specific objectives, well-designed questionnaire
Semi-structured interview
Specific objectives, certain freedom in meeting
them
Key questions are developed in advance
Example
Unstructured => structured =>unstructured
16/04/03 Survey Research 16
Interview procedures
Initiate the interview
Put the respondent at ease
Be businesslike
Keep the interview situation as private as possible
Ask every question exactly as written
Do not assume the answer to any question
Do not put answers in the respondent’s mouth
Use an appropriate neutral probe when needed
Record responses on the interview schedule as you
go along
16/04/03 Survey Research 17