Descriptive Data: The Survey

1
Chapter 6

• Descriptive DataThe Survey

2
General Survey Types

• Telephone
• Personal
• Mail
• Internet

3
Types of Surveys (1)

• Personal
• Door-To-Door Interviewing
• face to face with consumers in their homes.
• Mall Intercept
• conducted in public areas of malls by
  intercepting shoppers and interviewing them
  face-to face.

4
Types of Surveys (2)

• Telephone Interviewing
• Central Location Telephone Interviews
• calls to respondents from a centrally located
  marketing research facility.
• Computer-Assisted-Telephone Interviewing (CITI)
• interviewer enters answers directly into a
  computer.

5
Types of Surveys (3)

• IVR Automated Telephone Surveys
• using interactive voice response technology to
  conduct interviews.
• Direct Computer Interviewing
• computer asks questions and accepts responses.

6
Types of Surveys (4)

• Mail Surveys (self-administered)
• Ad Hoc Mail Surveys
• Questionnaires sent to selected names and
  addresses with no prior contact by the
  researcher.
• Mail Panels
• Precontacted and screened participants who are
  periodically sent questionnaires (longitudinal)

7
Potential Sources of Error
O Observed (what we actually measure) T True
Score (what we want to measure) S Systematic
Error (things we can control) R Random Error
(things we can not control)
8
Sample Survey Situation

• Research Question
• What does US citizen feel is the likelihood the
  President Clinton will be removed from office?
• Approach
• Survey first 100 people on a voter registration
  list with a one-question telephone survey
• Indicate how strongly you agree/disagree with the
  following statement
• I think President Clinton should be impeached
• strongly agree---------------------strongly
  disagree

9
Types of Error in Survey Research (1)

• Random Sampling Error
• results from chance variation
• Systematic Sampling Error
• results from the research design or execution
• Frame error from inaccurate or incomplete sample
  frame.
• Population specification error from incorrect
  definition of the universe or population.
• Selection error from improper sampling
  procedures

10
Types of Error in Survey Research (2)

• Measurement Error
• from a variation between the information being
  sought and that actually obtained
• Types of Measurement Error
• Surrogate information error form discrepancy
  between the information needed to solve a problem
  and that sought by the researcher
• Measurement instrument bias from the design of
  the questionnaire or measurement instrument.

11
Types of Error in Survey Research (3)

• Measurement Error (continued)
• Types of Measurement Error
• Interviewer error from the interviewer
  influencing the respondent
• Processing error from incorrect transfer of
  information from the document to the computer
• Nonresponse bias from a systematic difference
  between those who do and do not respond
• Response bias from deliberate misrepresentation
  or unconscious falsification of answer

12
Tactics Employed to Increase Mail Survey Response
Rate (1)
Advance postcard or telephone call alerting
respondent of survey Follow-up postcard or
phone call Monetary incentives (nickel, dime,
quarter, half-dollar) Premiums (pencil, pen,
keychain, etc.) Postage stamps rather than
metered envelopes Self-addressed, stamped
return envelope Personalized address and
well-written cover letter Promise of
contributions to favorite charity
13
Tactics Employed to Increase Mail Survey Response
Rate (2)
Entry into drawing for prize Emotional
appeals Affiliation with universities or
research institutions Personally signed cover
letter Multiple mailings of the
questionnaire Bids for sympathy Reminder
that respondent participated in previous study
14
Factors Determining Choice of Particular Survey
Method (1)

• Sampling Precision Required
• Budget Available
• The Need to Expose the Respondent to Various
  Stimuli
• Quality of Data Required
• Length of the Questionnaire

15
Factors Determining Choice of Particular Survey
Method (2)

• Necessity of Having Respondent Perform Certain
  Specialized Tasks
• Incident Rate
• Percentage of people or households in the general
  population that fit the qualifications to be
  sampled.
• Degree of Structure of the Questionnaire

16
Comparative Evaluation of Survey Methods (1)
17
Comparative Evaluation of Survey Methods (2)
18
(No Transcript)