SURVEYSSURVEYS
SURVEYS ASK A RESPONDENT FOR INFORMATION USING VERBAL OR WRITTEN QUESTIONING
RESPONDENTSRESPONDENTS RESPONDENTS
ARE A REPRESENTATIVE SAMPLE OF PEOPLE
GATHERING INFORMATION GATHERING INFORMATION VIA SURVEYSVIA SURVEYS
• QUICK• INEXPENSIVE• EFFICIENT• ACCURATE• FLEXIBLE
PROBLEMSPROBLEMS
• POOR DESIGN• IMPROPER EXECUTION
Communication ApproachesCommunication Approaches
Self-Administered
Survey
Survey via PersonalInterview
TelephoneSurvey
COMMUNICATING WITH COMMUNICATING WITH RESPONDENTSRESPONDENTS
• PERSONAL INTERVIEWS• DOOR-TO-DOOR• WIRK PLACE• SHOPPING MALL INTERCEPTS
• TELEPHONE INTERVIEWS• SELF-ADMINISTERED
QUESTIONNAIRES
PERSONAL INTERVIEWSPERSONAL INTERVIEWS
Door-to-Door Personal Interview
Speed of Data Collection Moderate to fast
Geographical Flexibility Limited coverage
Respondent Cooperation Excellent
Versatility of Questioning Quite versatile
Questionnaire Length Long
Item Nonresponse Low
Possibility of Respondent LowestMisunderstanding
Degree of Interviewer HighInfluence of Answer
Supervision of Interviewers Moderate
Door-to-Door Personal Interview
Anonymity of Respondent Low
Ease of Call Back or Follow-up Difficult
Cost Highest
Special Features Visual materials may beshown or demonstrated;extended probing possible
Door-to-Door Personal Interview
Mall Intercept Personal Interview
Speed of Data Collection Fast
Geographical Flexibility Confined, urban bias
Respondent Cooperation Moderate to low
Versatility of Questioning Extremely versatile
Questionnaire Length Moderate to Long
Mall Intercept Personal Interview
Item Nonresponse Medium
Possibility of Respondent LowestMisunderstanding
Degree of Interviewer HighestInfluence of Answers
Supervision of Interviewers Moderate to high
Mall Intercept Personal Interview
Anonymity of Respondent Low
Ease of Call Back or DifficultFollow-up
Cost Moderate to high
Special Features Taste test, viewing of TV Commercials possible
Telephone Telephone SurveySurvey
Traditional
CATI systems
Computer-administered
Questionnaire Length Moderate
Item Nonresponse Medium
Possibility of Respondent AverageMisunderstanding
Degree of Interviewer ModerateInfluence of Answer
Supervision of Interviewers High, especially withcentral location WATSinterviewing
Telephone Surveys
Speed of Data Collection Very fast
Geographical Flexibility High
Respondent Cooperation Good
Versatility of Questioning Moderate
Telephone Surveys
Anonymity of Respondent Moderate
Ease of Call Back or Follow-up Easy
Cost Low to moderate
Special Features Fieldwork and supervisionof data collection aresimplified; quite adaptableto computer technology
Telephone Surveys
Advantages of the Telephone Advantages of the Telephone SurveySurvey
• Lower costs than personal interview
• Expanded geographic coverage
• Use of few interviewers
• Reduced interviewer bias
• Fast completion time
• Better access to some participants
• Random dialing possible
• CATI (Computer Assisted Telephone Interviewing) possible
Disadvantages of the Disadvantages of the Telephone SurveyTelephone Survey
• Lower response rate than personal interview
• Higher costs if interviewing geographically dispersed sample
• Interview length limited
• Unlisted phone numbers
• Some unavailable by phone
• Lack of visuals
SELF-ADMINISTERED SELF-ADMINISTERED QUESTIONNAIRESQUESTIONNAIRES
• MAIL• PLACE OF BUSINESS• DROP-OFF• COMPUTERIZED• E-MAIL• INTERNET
MAIL SURVEYSMAIL SURVEYS
Mail Survey
Speed of Data Collection Researcher has no controlover return of questionnaire; slow
Geographical Flexibility High
Respondent Cooperation Moderate--poorly designedquestionnaire will have low
response rate
Versatility of Questioning Highly standardized format
Mail Survey
Questionnaire Length Varies depending on incentive
Item Nonresponse High
Possibility of Respondent Highest--no interviewerMisunderstanding present for clarification
Degree of Interviewer None--interviewer absentInfluence of Answer
Supervision of Interviewers Not applicable
Mail Survey
Anonymity of Respondent High
Ease of Call Back or Follow-up Easy, but takes time
Cost Lowest
Increasing Response Rates
• Effective Cover Letter
• Money Helps
• Interesting Questions
• Follow-Ups
• Advanced Notification
• Survey Sponsorship
• Keying Questionnaires
How to Increase Response Rates for Mail Surveys
• Write a “Sales Oriented” Cover Letter• Money Helps
- As a token of appreciation
• Stimulate Respondents’ Interest with Interesting Questions• Follow Up
- Keying questionnaires with codes• Advanced Notification• Sponsorship by a Well-known and Prestigious Institution
INTERNET SURVEYSINTERNET SURVEYS
• Speed of Data Collection– instantaneous
• Geographic Flexibility
– worldwide
• Respondent Cooperation– varies depending on web site
INTERNET SURVEYSINTERNET SURVEYS
• Versatility of questioning
– extremely versatile
• Questionnaire Length– modest
• Item Nonresponse– software can assure none
INTERNET SURVEYSINTERNET SURVEYS
• Possibility for Respondent misunderstanding– high
• Interviewer Influence of Answers– none
• Supervision of Interviewers– none
INTERNET SURVEYSINTERNET SURVEYS
• Anonymity of Respondent– Respondent can be anonymous or known
• Ease of Callback or Follow-up– difficult
• Cost– low
• Special Features– allows graphics and motion
INTERNET SURVEYSINTERNET SURVEYS• Item Nonresponse
software can assure none• Possibility for Respondent
misunderstanding– high
• Degree of Interviewer Influence of Answers– none
• Supervision of Interviewers– none
There is no best form of There is no best form of survey; each has survey; each has advantages and advantages and disadvantages.disadvantages.
Selected Questions to Selected Questions to determine the appropriate determine the appropriate
technique:technique:
• Is the assistance of an interviewer necessary?
• Are respondents interested in the issues being investigated?
• Will cooperation be easily attained?
Selected Questions to Selected Questions to determine the appropriate determine the appropriate
technique:technique:
• How quickly is the information needed?
• Will the study require a long and complex questionnaire?
• How large is the budget?
Pre-testingPre-testing• A trial run with a group of respondents to iron out fundamental problems in the instructions or survey design
Sources of ErrorSources of Error
ErrorSources
Measurement Questions
Interviewer
Participant
Participant MotivationParticipant Motivation
Designing QuestionnairesDesigning Questionnaires
Easy to readEasy to read
Offer clear directionsOffer clear directions
Include personalizationInclude personalization
Notify in advanceNotify in advance
Encourage responseEncourage response
Totalerror
Systematicerror (bias)
Random samplingerror
Tree Diagram of Total Survey Error
RANDOM SAMPLING RANDOM SAMPLING ERRORERROR
• A STATISTICAL FLUCTUATION THAT OCCURS BECAUSE OF CHANCE VARIATION IN THE ELEMENTS SELECTED FOR THE SAMPLE
SYSTEMATIC ERRORSYSTEMATIC ERROR
• SYSTEMATIC ERROR RESULTS FROM SOME IMPERFECT ASPECT OF THE RESEARCH DESIGN OR FROM A MISTAKE IN THE EXECUTION OF THE RESEARCH
Systematicerror (bias)
Administrativeerror
Respondenterror
Tree Diagram of Total Survey Error
SAMPLE BIASSAMPLE BIAS
• SAMPLE BIAS - WHEN THE RESULTS OF A SAMPLE SHOW A PERSISTENT TENDENCY TO DEVIATE IN ONE DIRECTION FROM THE TRUE VALUE OF THE POPULATION PARAMETER
Respondenterror
Nonresponseerror
Responsebias
Tree Diagram of Total Survey Error
RESPONDENT ERRORRESPONDENT ERROR
• A CLASSIFICATON OF SAMPLE BIAS RESULTING FROM SOME RESPONDENT ACTION OR INACTION
• NONRESPONSE BIAS• RESPONSE BIAS
NONRESPONSE ERRORNONRESPONSE ERROR
• NONRESPONDENTS - PEOPLE WHO REFUSE TO COOPERATE
• NOT-AT-HOMES• SELF-SELECTION BIAS
• OVER-REPRESENTS EXTREME POSTIONS• UNDER-REPRESENTS INDIFFERENCE
Tree Diagram of Total Survey Error
Responsebias
Unconsciousmisrepresentation
Deliberatefalsification
RESPONSE BIASRESPONSE BIAS
• A BIAS THAT OCCURS WHEN RESPONDENTS TEND TO ANSWER QUESTIONS WITH A CERTAIN SLANT THAT CONSCIOUSLY OR UNCONSCIOUSLY MISREPRESENTS THE TRUTH
Acquiescence bias
Extremity bias
Interviewer bias
Auspices bias
Social desirability bias
Tree Diagram of Total Survey Error
Acquiescence biasAcquiescence bias
• A category of response bias that results because some individuals tend to agree with all questions or to concur with a particular position.
Extremity biasExtremity bias
• A category of response bias that results because response styles vary from person to person; some individuals tend to use extremes when responding to questions.
Interviewer biasInterviewer bias
• A response bias that occurs because the presence of the interviewer influences answers.
Auspices biasAuspices bias
• Bias in the responses of subjects caused by the respondents being influenced by the organization conducting the study.
Social desirability biasSocial desirability bias
• Bias in responses caused by respondents’ desire, either conscious or unconscious, to gain prestige or appear in a different social role.
Systematicerror (bias)
Administrativeerror
Respondenterror
Tree Diagram of Total Survey Error
ADMINISTRATIVE ERRORADMINISTRATIVE ERROR
• IMPROPER ADMINISTRATION OF THE RESEARCH TASK
• BLUNDERS• CONFUSION• NEGLECT• OMISSION
Data processing error
Sample selection error
Interviewer error
Interviewer cheating
Tree Diagram of Total Survey Error
Administrative errorAdministrative error
• Interviewer cheating - filling in fake answers or falsifying interviewers.
• Data processing error - incorrect data entry, computer programming, or other procedural errors during the analysis stage.
• Sample selection error -improper sample design or sampling procedure execution.
• Interviewer error - field mistakes.
M E TH O DO F
C O M M U N IC A TIO N
S TR U C TU R E DA N D D IS Q U IS E D
Q U E S TIO N S
TE M P O R A LC L A S S IF IC A TIO N S
C L A S S IF Y IN GS U R V E Y
R E S E A R C HM E TH O D S
TIME PERIOD FOR TIME PERIOD FOR SURVEYSSURVEYS
• CROSS-SECTIONAL• LONGITUDINAL
Cross-sectional studyCross-sectional study
• A study in which various segments of a population are sampled.
• Data are collected at a single moment in time.
Longitudinal studyLongitudinal study
• A survey of respondents at different times, thus allowing analysis of changes over time.
• Tracking study - compare trends and identify changes – consumer satisfaction
CONSUMER PANEL CONSUMER PANEL
• A longitudinal survey of the same sample of individuals or households to record (in a diary) their attitudes, behavior, or purchasing habits over time.
The endThe end