Professional Documents
Culture Documents
ETHICAL ISSUES
Intrusion Informed consent Rights to withdraw at any stage or not to complete particular items Beneficence Non-maleficence Confidentiality, anonymity and non-traceability Threat or sensitivity Avoidance of bias Validity and reliability in the questionnaire Reactions of the respondent
OPERATIONALIZING A QUESTIONNAIRE
Clarify the questionnaires general purposes and then translate them into a specific, concrete aim or set of aims. Identify and itemize subsidiary topics that relate to its central purpose. Formulate specific information requirements relating to each issue. Plan with the data analysis in mind.
TYPES OF QUESTION
Open to closed Choose the metric (scale of data): Nominal Ordinal Interval Ratio Do not assume that respondents have the information/knowledge/views
TYPES OF QUESTION
DICHOTOMOUS MULTIPLE CHOICE RATING SCALES YES/NO ONE/MANY RESPONSES ODD/EVEN NUMBERS FREE RESPONSE
OPEN-ENDED
TYPES OF QUESTION
RANKING 1st/2nd. ETC. MANY RESPONSES DISTRIBUTING MARKS MARKS OUT OF TEN
RATIO DATA
CONSTANT SUM
RATIO DATA
DICHOTOMOUS QUESTIONS
Good for clear answers; Yes/no questions are often better rephrased as to what extent or how much types of question.
MULTIPLE CHOICE
Need for a pilot to gather exhaustive categories of response; Do not allow for range of response; If more than one response permitted then each choice is a separate variable.
LIKERT SCALES
Useful for measuring degrees of intensity of feeling; No assumption of equal intervals; No assumptions of matched intensity of feeling; No way of knowing if respondents are telling the truth; No way of knowing if there should be other categories or items; Halo effect; Allows for different scaling and mid-points, e.g.: (a) strongly disagree neither agree nor disagree strong agree; (b) not at all a very great deal; Central tendency; Ordinal data.
OPEN-ENDED QUESTIONS
Enable authentic responses; More time-consuming and difficult to analyze/process.
RANKING SCALES
Enables comparisons to be made by respondents across items; Enables sensitivity of response to be addressed; Can be strong on reality of decision making; Too many items to rank may result in unrealistic ranking (people may not have strong enough opinions to be able to rank) Too many decisions to be made; Ordinal data.
CONSTANT SUM
Divide a fixed number of points between a range of items; Yields priorities, comparative highs and lows and equality of choice quickly and easily in the respondents own terms; Requires participants to make comparative judgements and choices across items; May be too difficult if there are too many items across which to spread marks; People may make computational errors in distributing marks; Ordinal data.
Ensure that the question stem does not frame the answer: The tourism industry is
successful because . . . ..
Start with simple factual questions and then move to more sensitive questions; Provide instructions for how to complete and return the questionnaire; Have a cover sheet which explains the purposes of the questionnaire and which sets out ethical issues.
SEQUENCING QUESTIONS
Take care with order effects Earlier responses affect later responses Early tone/mood-setting affects later moods in completing questionnaires Primacy effect Items high in a list tend to be chosen more than items lower in a list Respondents choose the first reasonable answer from a list, even though a later response statement might be more fitting Avoid placing sensitive questions at the start Embed them later questions Move from objective facts to subjective views
PURPOSES OF PILOTING
To check clarity of items/layout/sections/presentation/ instructions; To gain feedback on appearance; To eliminate ambiguities/uncertainty/poor wording; To check readability; To gain feedback on question type (suitability/feasibility/ format (e.g. open/closed/multiple choice); To gain feedback on appropriateness of question stems; To generate categories for responses in multiple choices; To generate items for further exploration/discussion; To gain feedback on response categories; To gain feedback on length/timing (when to conduct the data collection as well as how long each takes to complete (e.g. each interview/questionnaire))/coverage/ease of completion;
PURPOSES OF PILOTING
To identify redundant items/questions (those with little discriminability); To identify irrelevant questions; To identify non-responses; To identify how motivating/non-engaging/threatening/ intrusive/offensive items may be; To identify sensitive topics and problems in conducting interviews; To test for inter-rater reliability; To minimise counter-transference; To gain feedback on leading questions; To identify items which are too easy/difficult/complex/ remote from experience; To identify commonly misunderstood or non-completed items.