The Questionnaire Development
Process
Questionnaire
 Definition – A set of questions designed to generate
the information necessary to meet research objectives
 Characteristics
 Elicits information from respondents
 Results can be tabulated
 Standardized across respondents
 Understandable to respondents
 A good questionnaire must:
 provide the necessary information
 be considerate of respondents
 meet coding and data processing requirements
The Questionnaire Design Process
Determine Survey
Objectives and
Constraints
Determine Data
Collection Methods
Evaluate the
Questionnaire and
Layout
Establish
Questionnaire Flow
and Layout
Decide on Question
Wording
Determine Question
Response Format
Obtain Approval
from all Relevant
Parties
Pretest and Revise
Prepare Final Copy
Implementation
Step 1: Determine Survey Objectives
 Translates research objectives into information
requirements
 Survey objectives should be spelled out as
clearly and precisely as possible
 Rule 1 - Let the research objectives
dictate what questions to ask
 Rule 2 - Avoid unnecessary questions
Step 2: Determine the Data Collection
Method
 We previously discussed the variety of ways that
survey data can be gathered
 Personal
 Telephone
 Electronic
 Mail
 Self administered
 Each method has a different impact on survey
design
Step 3: Determine the Question
Response Format
Open-Ended Questions
 Open-ended questions are those in which the
respondent can reply in his/her own words
 Example of an open-ended question:
What are the advantages, if any, of ordering
from a mail order catalog compared with
buying at a nearby retail outlet?
Open-Ended Questions
Open-ended questions are useful:
 to interpret closed-ended responses
 when there are too many alternatives to list
 when alternatives vary between
respondents or are not clear
 when intensity of feeling is important
 when verbatim response is helpful
 for some sensitive issues (e.g. divorce)
Open-Ended Questions
Advantages
 More information
 Wide range of responses
 Maybe more accurate description
Limitations
 Respondent articulateness can lead to
error/variation
 Time consuming for respondent
 Coding and analysis is difficult
Step 3: Determine the Question
Response Format
Closed-Ended Questions
 A closed-ended question is one that requires the
respondent to make a selection from a list of
options
 The primary advantage of closed-ended questions
is avoiding the problems of open-ended questions
(such as subjectivity, coding, etc.)
 May be dichotomous or multiple choice
Closed-Ended Questions
 Types
 Dichotomous – Respondent chooses between
two alternatives
 Multiple-Choice – Respondent selects from
among several alternatives
 Example of a multiple-choice question:
Who do you think will win the World Series?
A. Tampa Bay Devil Rays
B. Boston Red Sox
C. Philadelphia Phillies
D. Los Angeles Dodgers
Step 3: Determine the Question
Response Format
Scaled-Response Questions
 Question format that permits measurement of the
“intensity” of a respondent’s answers
 Example of a scaled-response question:
Now that you have tried the new sugar-free
Slurpee, would you say that you would… (Check
one)
definitely buy it
probably buy it
might or might not buy it
probably not buy it
definitely not buy it
Closed-Ended Questions
Advantages
 Easier to answer
 Reduce measurement error by overcoming
respondent articulateness and possible interviewer
bias
 Easy to code and analyze
 More likely to respond for some personal data
(e.g. income, age)
Disadvantages
 Information is lost
 Answers may not be precise
 Not able to develop alternatives
Step 4: Question Wording
 Rule 3: Use simple words
 e.g., not “marital status” but whether
“married,” “single” or “divorced”
 Rule 4: Use unambiguous words
(words that are easily and clearly
understood)
 e.g. not “where do you usually buy school
supplies?”
but “from which retailer(s) did you buy school
supplies this year?”
“where” and “usually” are often ambiguous
Question Wording
 Rule 5: Avoid “double-barreled”
questions (two questions in one)
 e.g., “What is your opinion about the price and
convenience of DART?”
 Rule 6: Avoid leading questions
(questions that imply an answer)
 e.g. “Do you agree that the government should
cut taxes so that we can lead better lives?”
Question Wording
 Rule 7: Avoid “loaded” questions
(framing questions so that they are
leading or emotionally charged)
 e.g., “Do you think chemical companies are doing
everything possible to control pollution?”
 Rule 8: Avoid implicit assumptions or
alternatives – State them clearly
 e.g., “Do you favor a law mandating methanol-free
gasoline” [if it means an increase in gas prices]
Question Wording
 Rule 9: Avoid burdensome questions
(questions that tax memory or skills)
 e.g., “How many different brands of breakfast
cereal have you bought in the last twelve months?”
 Rule 10: Clarify references (how should
respondent answer)
 e.g., “State your annual income” [personal income
or household income?]
Question Wording
 Rule 11: Alternatives should be
mutually exclusive, collectively
exhaustive, and have reasonable range
e.g., What is your annual household income?
__ $0 - $10,000
__ $10,000 - $15,000
__ $15,000 - $20,000
__ $40,000 - $60,000
What is wrong with this question and how
would you correct it?
Question Wording – Scaled Responses
 Rule 12: Use appropriate phrases
e.g.,
B. Are you: (1) amazingly happy, (2) middling
happy or (3) kind of unhappy (check one)
A. Are you: (1) very happy, (2) happy or (3)
unhappy (check one)
 Rule 13: Avoid order bias
e.g., should you start with (1) as “very happy” or
(1) as “unhappy?”
Question Wording - Sensitive /
Embarrassing Questions
 Questions about borrowing money, personal
hygiene, sexual activity, criminal history, etc. must
be phrased carefully to minimize measurement error
 Suggestions/Techniques - Not Rules
 Ask non-threateningly and mix with other questions
e.g., How many times each day do you brush your teeth?
 Frame question to prompt more honest responses
e.g., Many people find it difficult to brush their teeth twice a
day. How often do you brush your teeth?
Step 5: Questionnaire Flow and
Layout
Use screening
questions to
identify qualified
respondents
After identifying
qualified respondent,
begin with a question
that piques the
respondent’s interest
Ask general
questions first
Ask questions that
require “work” in
the middle of the
questionnaire
Insert “prompters”
at strategic points
Position sensitive,
threatening, and
demographic
questions as the
end
Step 5: Questionnaire Flow and Layout
 Rule 14: Opening questions should be
simple and interesting – begin with open-
ended question if warm-up is necessary
 Rule 15: Use “funnel approach” – ask
most general questions first, then
increasingly specific questions
 Rule 16: Questions should flow smoothly
and logically
Step 5: Questionnaire Flow and Layout
 Rule 17: Ask “screener” questions up
front to assess respondent qualifications
 Rule 18: Ask sensitive questions near the
end
 Rule 19: Ask for demographic information
at the end
 Rule 20: The questionnaire’s appearance
should be attractive and professional
Step 6: Evaluate the Questionnaire
 Is each question necessary?
 Is the questionnaire too long?
 Will the questions provide the desired information to
accomplish the research objectives?
 Is the layout attractive and professional?
Step 8: Pretest and Revise
 Rule 21: Always pretest your questionnaire
Pretesting can be done by giving the questionnaire to
a few friends, “experts”, and potential respondents
(may be 5-10 persons total), asking them to fill out,
and obtaining their feedback
Step 8: Pretest and Revise
Pretest the questionnaire for:
 wording of individual questions
 flow of the questionnaire
 skip patterns
 length
 respondent interest and attention
Step 9: Prepare Final Copy
 Even the final copy phase does not allow the
researcher to relax.
 Precise typing instructions, spacing, numbering,
and precoding must be set up, monitored, and
proofread,
before …
Step 10: Implement the Survey
Questions should flow logically from one to the next
General questions should be asked before more specific ones
Earlier questions should not influence response to later ones
Questions should flow from factual and behavioural questions to attitudinal and opinion
questions
Questions should flow from the least sensitive to the most sensitive.
Questions should flow from unaided (which brand do you prefer) to aided questions
(which brand do you prefer Tide, Cheer, Gain)
 Demographic questions should come at the end.
Other Considerations
1. initial questions - screening and rapport questions
2. Middle - product specific questions
3. End demographic questions.
Other Considerations
Use multiple questions instead of one
 Similar questions together
 consistent mindset for respondents
 Develop a logical flow
 Use transitions between sections (E.g. In this section we ask questions about X)
Distinguish between instructions, questions and responses
Filter and pivot questions should be used as necessary.
A FILTER question is one that screens out
respondents who are not qualified to answer a
second question.
A PIVOT question is a type of filter question that is
used to determine what version of a second
question to ask.
The layout and physical attractiveness of a
questionnaire are important aspects
 Questionnaires should be designed to appear as
short as possible
 Questionnaires should not appear overcrowded
 Leave lots of space for open ended questions
 Questionnaires in booklet form are often
recommended
QUESTIONNAIRE LAYOUT
OPENING
Provide first name (at least)
Provide name of company doing research
Provide reason for survey and topic
State that no selling will be involved and no personal data other than for
statistical purposes
Tell respondent approximate time to complete
Reinforce that respondent’s time is appreciated
Invite to participate
AND CLOSING
Thank for time
Ask if they had a positive experience and remind them that their opinions count
Pretesting and Correcting Problems
Purpose of pretest: To ensure that the questionnaire meets the expectations
in terms of the information that will be obtained
Is question necessary – does it serve a purpose, will info be used
Missing important variables – does it provide the info needed
Match questions to objectives
Pretest Specific Questions For
• Variation
• Meaning
• Task difficulty
• Respondent interest and attention
• Ambiguous, ill-defined, loaded, double-barreled questions
Pretest the Questionnaire
• Flow of the questionnaire
• Skip patterns
•Length
Respondent Interest and Attention
Validity
 Validity refers to the question of whether our
measurements are actually hitting on the construct we
think they are
 While we can obtain specific statistics for reliability
(even different types), validity is more of a global
assessment based on the evidence available
 We can have reliable measurements that are invalid
 Classic example: The scale which is consistent and
able to distinguish from one person to the next
Logical Statistical
Face Content Predictive
Construct
Concurrent
Validity
Consistency
Reliability Objectivity
Types of Validity
 Criterion validity
 the degree to which the measure correlates with various outcomes
 Does some new personality measure correlate with the Big 5
 Concurrent Validity
 Criterion is in the present
 Measure of perception and current scholastic behavioral problems
 Predictive Validity
 Criterion in the future
 SAT and college gpa
 Construct-related validity
 How much is it an actual measure of the construct of interest
 Convergent Validity
 Correlates well with other measures of the construct
 Depression scale correlates well with other dep scales
 Discriminant Validity
 Is distinguished from related but distinct constructs
 Dep scale != Stress scale
Reliability
 the consistency of your measurement
instrument
 the degree to which an instrument measures
the same way each time it is used under the
same condition with the same subjects
This clock reads 6:15
If nothing changes – if time
stands still, will the clock still
say the same thing?
YES! It’s very reliable. You
always know exactly what it is
going to say.
Types of Reliability
 Relative Reliability
 Absolute reliability is the degree to which Relative reliability is the ... the differences between
the means of two sets
 Relative reliability is the degree to which individuals maintain their position in a sample over
repeated measurements.
 Absolute Reliability
 Absolute reliability is the degree to which Relative reliability is the degree to which repeated
measurements vary for individuals, individuals maintain their position in a ie the less they
vary, the higher the reliability in a sample over repeated measurements.
 Rater reliability (Objectivity)
 Intra-rater reliability
 In statistics, intra-rater reliability is the degree of agreement among repeated
administrations of a diagnostic test performed by a single rater.
 Interrater reliability.
 In statistics, intra-rater reliability is the degree of agreement among repeated
administrations of a diagnostic test performed by more than one rater.s
Questionnair Designing lec3 RESEARCH METHODOLOGY

Questionnair Designing lec3 RESEARCH METHODOLOGY

  • 1.
  • 2.
    Questionnaire  Definition –A set of questions designed to generate the information necessary to meet research objectives  Characteristics  Elicits information from respondents  Results can be tabulated  Standardized across respondents  Understandable to respondents  A good questionnaire must:  provide the necessary information  be considerate of respondents  meet coding and data processing requirements
  • 3.
    The Questionnaire DesignProcess Determine Survey Objectives and Constraints Determine Data Collection Methods Evaluate the Questionnaire and Layout Establish Questionnaire Flow and Layout Decide on Question Wording Determine Question Response Format Obtain Approval from all Relevant Parties Pretest and Revise Prepare Final Copy Implementation
  • 4.
    Step 1: DetermineSurvey Objectives  Translates research objectives into information requirements  Survey objectives should be spelled out as clearly and precisely as possible  Rule 1 - Let the research objectives dictate what questions to ask  Rule 2 - Avoid unnecessary questions
  • 5.
    Step 2: Determinethe Data Collection Method  We previously discussed the variety of ways that survey data can be gathered  Personal  Telephone  Electronic  Mail  Self administered  Each method has a different impact on survey design
  • 6.
    Step 3: Determinethe Question Response Format Open-Ended Questions  Open-ended questions are those in which the respondent can reply in his/her own words  Example of an open-ended question: What are the advantages, if any, of ordering from a mail order catalog compared with buying at a nearby retail outlet?
  • 7.
    Open-Ended Questions Open-ended questionsare useful:  to interpret closed-ended responses  when there are too many alternatives to list  when alternatives vary between respondents or are not clear  when intensity of feeling is important  when verbatim response is helpful  for some sensitive issues (e.g. divorce)
  • 8.
    Open-Ended Questions Advantages  Moreinformation  Wide range of responses  Maybe more accurate description Limitations  Respondent articulateness can lead to error/variation  Time consuming for respondent  Coding and analysis is difficult
  • 9.
    Step 3: Determinethe Question Response Format Closed-Ended Questions  A closed-ended question is one that requires the respondent to make a selection from a list of options  The primary advantage of closed-ended questions is avoiding the problems of open-ended questions (such as subjectivity, coding, etc.)  May be dichotomous or multiple choice
  • 10.
    Closed-Ended Questions  Types Dichotomous – Respondent chooses between two alternatives  Multiple-Choice – Respondent selects from among several alternatives  Example of a multiple-choice question: Who do you think will win the World Series? A. Tampa Bay Devil Rays B. Boston Red Sox C. Philadelphia Phillies D. Los Angeles Dodgers
  • 11.
    Step 3: Determinethe Question Response Format Scaled-Response Questions  Question format that permits measurement of the “intensity” of a respondent’s answers  Example of a scaled-response question: Now that you have tried the new sugar-free Slurpee, would you say that you would… (Check one) definitely buy it probably buy it might or might not buy it probably not buy it definitely not buy it
  • 12.
    Closed-Ended Questions Advantages  Easierto answer  Reduce measurement error by overcoming respondent articulateness and possible interviewer bias  Easy to code and analyze  More likely to respond for some personal data (e.g. income, age) Disadvantages  Information is lost  Answers may not be precise  Not able to develop alternatives
  • 13.
    Step 4: QuestionWording  Rule 3: Use simple words  e.g., not “marital status” but whether “married,” “single” or “divorced”  Rule 4: Use unambiguous words (words that are easily and clearly understood)  e.g. not “where do you usually buy school supplies?” but “from which retailer(s) did you buy school supplies this year?” “where” and “usually” are often ambiguous
  • 14.
    Question Wording  Rule5: Avoid “double-barreled” questions (two questions in one)  e.g., “What is your opinion about the price and convenience of DART?”  Rule 6: Avoid leading questions (questions that imply an answer)  e.g. “Do you agree that the government should cut taxes so that we can lead better lives?”
  • 15.
    Question Wording  Rule7: Avoid “loaded” questions (framing questions so that they are leading or emotionally charged)  e.g., “Do you think chemical companies are doing everything possible to control pollution?”  Rule 8: Avoid implicit assumptions or alternatives – State them clearly  e.g., “Do you favor a law mandating methanol-free gasoline” [if it means an increase in gas prices]
  • 16.
    Question Wording  Rule9: Avoid burdensome questions (questions that tax memory or skills)  e.g., “How many different brands of breakfast cereal have you bought in the last twelve months?”  Rule 10: Clarify references (how should respondent answer)  e.g., “State your annual income” [personal income or household income?]
  • 17.
    Question Wording  Rule11: Alternatives should be mutually exclusive, collectively exhaustive, and have reasonable range e.g., What is your annual household income? __ $0 - $10,000 __ $10,000 - $15,000 __ $15,000 - $20,000 __ $40,000 - $60,000 What is wrong with this question and how would you correct it?
  • 18.
    Question Wording –Scaled Responses  Rule 12: Use appropriate phrases e.g., B. Are you: (1) amazingly happy, (2) middling happy or (3) kind of unhappy (check one) A. Are you: (1) very happy, (2) happy or (3) unhappy (check one)  Rule 13: Avoid order bias e.g., should you start with (1) as “very happy” or (1) as “unhappy?”
  • 19.
    Question Wording -Sensitive / Embarrassing Questions  Questions about borrowing money, personal hygiene, sexual activity, criminal history, etc. must be phrased carefully to minimize measurement error  Suggestions/Techniques - Not Rules  Ask non-threateningly and mix with other questions e.g., How many times each day do you brush your teeth?  Frame question to prompt more honest responses e.g., Many people find it difficult to brush their teeth twice a day. How often do you brush your teeth?
  • 20.
    Step 5: QuestionnaireFlow and Layout Use screening questions to identify qualified respondents After identifying qualified respondent, begin with a question that piques the respondent’s interest Ask general questions first Ask questions that require “work” in the middle of the questionnaire Insert “prompters” at strategic points Position sensitive, threatening, and demographic questions as the end
  • 21.
    Step 5: QuestionnaireFlow and Layout  Rule 14: Opening questions should be simple and interesting – begin with open- ended question if warm-up is necessary  Rule 15: Use “funnel approach” – ask most general questions first, then increasingly specific questions  Rule 16: Questions should flow smoothly and logically
  • 22.
    Step 5: QuestionnaireFlow and Layout  Rule 17: Ask “screener” questions up front to assess respondent qualifications  Rule 18: Ask sensitive questions near the end  Rule 19: Ask for demographic information at the end  Rule 20: The questionnaire’s appearance should be attractive and professional
  • 23.
    Step 6: Evaluatethe Questionnaire  Is each question necessary?  Is the questionnaire too long?  Will the questions provide the desired information to accomplish the research objectives?  Is the layout attractive and professional?
  • 24.
    Step 8: Pretestand Revise  Rule 21: Always pretest your questionnaire Pretesting can be done by giving the questionnaire to a few friends, “experts”, and potential respondents (may be 5-10 persons total), asking them to fill out, and obtaining their feedback
  • 25.
    Step 8: Pretestand Revise Pretest the questionnaire for:  wording of individual questions  flow of the questionnaire  skip patterns  length  respondent interest and attention
  • 26.
    Step 9: PrepareFinal Copy  Even the final copy phase does not allow the researcher to relax.  Precise typing instructions, spacing, numbering, and precoding must be set up, monitored, and proofread, before … Step 10: Implement the Survey
  • 27.
    Questions should flowlogically from one to the next General questions should be asked before more specific ones Earlier questions should not influence response to later ones Questions should flow from factual and behavioural questions to attitudinal and opinion questions Questions should flow from the least sensitive to the most sensitive. Questions should flow from unaided (which brand do you prefer) to aided questions (which brand do you prefer Tide, Cheer, Gain)  Demographic questions should come at the end. Other Considerations 1. initial questions - screening and rapport questions 2. Middle - product specific questions 3. End demographic questions.
  • 28.
    Other Considerations Use multiplequestions instead of one  Similar questions together  consistent mindset for respondents  Develop a logical flow  Use transitions between sections (E.g. In this section we ask questions about X) Distinguish between instructions, questions and responses
  • 29.
    Filter and pivotquestions should be used as necessary. A FILTER question is one that screens out respondents who are not qualified to answer a second question. A PIVOT question is a type of filter question that is used to determine what version of a second question to ask.
  • 30.
    The layout andphysical attractiveness of a questionnaire are important aspects  Questionnaires should be designed to appear as short as possible  Questionnaires should not appear overcrowded  Leave lots of space for open ended questions  Questionnaires in booklet form are often recommended QUESTIONNAIRE LAYOUT
  • 31.
    OPENING Provide first name(at least) Provide name of company doing research Provide reason for survey and topic State that no selling will be involved and no personal data other than for statistical purposes Tell respondent approximate time to complete Reinforce that respondent’s time is appreciated Invite to participate AND CLOSING Thank for time Ask if they had a positive experience and remind them that their opinions count
  • 32.
    Pretesting and CorrectingProblems Purpose of pretest: To ensure that the questionnaire meets the expectations in terms of the information that will be obtained Is question necessary – does it serve a purpose, will info be used Missing important variables – does it provide the info needed Match questions to objectives Pretest Specific Questions For • Variation • Meaning • Task difficulty • Respondent interest and attention • Ambiguous, ill-defined, loaded, double-barreled questions Pretest the Questionnaire • Flow of the questionnaire • Skip patterns •Length Respondent Interest and Attention
  • 33.
    Validity  Validity refersto the question of whether our measurements are actually hitting on the construct we think they are  While we can obtain specific statistics for reliability (even different types), validity is more of a global assessment based on the evidence available  We can have reliable measurements that are invalid  Classic example: The scale which is consistent and able to distinguish from one person to the next
  • 34.
    Logical Statistical Face ContentPredictive Construct Concurrent Validity Consistency Reliability Objectivity
  • 35.
    Types of Validity Criterion validity  the degree to which the measure correlates with various outcomes  Does some new personality measure correlate with the Big 5  Concurrent Validity  Criterion is in the present  Measure of perception and current scholastic behavioral problems  Predictive Validity  Criterion in the future  SAT and college gpa  Construct-related validity  How much is it an actual measure of the construct of interest  Convergent Validity  Correlates well with other measures of the construct  Depression scale correlates well with other dep scales  Discriminant Validity  Is distinguished from related but distinct constructs  Dep scale != Stress scale
  • 36.
    Reliability  the consistencyof your measurement instrument  the degree to which an instrument measures the same way each time it is used under the same condition with the same subjects This clock reads 6:15 If nothing changes – if time stands still, will the clock still say the same thing? YES! It’s very reliable. You always know exactly what it is going to say.
  • 37.
    Types of Reliability Relative Reliability  Absolute reliability is the degree to which Relative reliability is the ... the differences between the means of two sets  Relative reliability is the degree to which individuals maintain their position in a sample over repeated measurements.  Absolute Reliability  Absolute reliability is the degree to which Relative reliability is the degree to which repeated measurements vary for individuals, individuals maintain their position in a ie the less they vary, the higher the reliability in a sample over repeated measurements.  Rater reliability (Objectivity)  Intra-rater reliability  In statistics, intra-rater reliability is the degree of agreement among repeated administrations of a diagnostic test performed by a single rater.  Interrater reliability.  In statistics, intra-rater reliability is the degree of agreement among repeated administrations of a diagnostic test performed by more than one rater.s