8/7/2019 Questionnaire constructio1

1/4

Questionnaire constructionA questionnaire is a series of questions asked to individuals to obtain statistically useful information about a given topic[1]. When properly constructed and responsibly administered, questionnaires become a vital instrument by whichstatements can be made about specific groups or people or entire populations.Questionnaires are frequently used in quantitative marketing research and social research. They are a valuable methodof collecting a wide range of information from a large number of individuals, often referred to as respondents. Adequatequestionnaire construction is critical to the success of a survey. Inappropriate questions, incorrect ordering ofquestions, incorrect scaling, or bad questionnaire format can make the survey valueless, as it may not accurately reflectthe views and opinions of the participants. A useful method for checking a questionnaire and making sure it isaccurately capturing the intended information is to pretest among a smaller subset of target respondents.

Contents[hide]I. 1 Questionnaire construction issues

A. 1.1 Methods of collectionII. 2 Types of questionsIII. 3 Question sequenceIV. 4 marketingsV. 5 Lists of related topicsVI. 6 ReferencesVII. 7 External links[edit] Questionnaire construction issuesVIII. Know how (and whether) you will use the results of your research before you start. If, for example, the

results won't influence your decision or you can't afford to implement the findings or the cost of the research

outweighs its usefulness, then save your time and money; don't bother doing the research.IX. The research objectives and frame of reference should be defined beforehand, including the questionnaire's

context of time, budget, manpower, intrusion and privacy.X. How (randomly or not) and from where (your sampling frame) you select the respondents will determine

whether you will be able to generalize your findings to the larger population.XI. The nature of the expected responses should be defined and retained for interpretation of the responses, be

it preferences (of products or services), facts, beliefs, feelings, descriptions of past behavior, or standards ofaction.

XII. Unneeded questions are an expense to the researcher and an unwelcome imposition on the respondents.All questions should contribute to the objective(s) of the research.

XIII. If you "research backwards" and determine what you want to say in the report (i.e., Package A is more/lesspreferred by X% of the sample vs. Package B, and y% compared to Package C) then even though youdon't know the exact answers yet, you will be certain to ask all the questions you need - and only the onesyou need - in such a way (metrics) to write your report.

XIV. The topics should fit the respondents frame of reference. Their background may affect their interpretationof the questions. Respondents should have enough information or expertise to answer the questionstruthfully.

XV. The type of scale, index, or typology to be used shall be determined.XVI. The level of measurement you use will determine what you can do with and conclude from the data. If the

response option is yes/no then you will only know how many or what percent of your sample answeredyes/no. You cannot, however, conclude what the average respondent answered.

XVII. The types of questions (closed, multiple-choice, open) should fit the statistical data analysis techniquesavailable and your goals.

XVIII. Questions and prepared responses to choose from should be neutral as to intended outcome. A biasedquestion or questionnaire encourages respondents to answer one way rather than another. Evenquestions without bias may leave respondents with expectations.

XIX. The order or natural grouping of questions is often relevant. Prior previous questions may bias laterquestions.

XX. The wording should be kept simple: no technical or specialized words.XXI. The meaning should be clear. Ambiguous words, equivocal sentence structures and negatives may cause

misunderstanding, possibly invalidating questionnaire results. Double negatives should be reworded aspositives.

XXII. If a survey question actually contains more than one issue, the researcher will not know which one therespondent is answering. Care should be taken to ask one question at a time.XXIII. The list of possible responses should be collectively exhaustive. Respondents should not find themselves

with no category that fits their situation. One solution is to use a final category for other ________.XXIV. The possible responses should also be mutually exclusive. Categories should not overlap. Respondents

8/7/2019 Questionnaire constructio1

2/4

should not find themselves in more than one category, for example in both the married category and thesingle category - there may be need for separate questions on marital status and living situation.

XXV. Writing style should be conversational, yet concise and accurate and appropriate to the target audience.XXVI. Many people will not answer personal or intimate questions. For this reason, questions about age,

income, marital status, etc. are generally placed at the end of the survey. This way, even if therespondent refuses to answer these "personal" questions, he/she will have already answered theresearch questions.

XXVII. Loaded questions evoke emotional responses and may skew results.XXVIII. Presentation of the questions on the page (or computer screen) and use of white space, colors, pictures,

charts, or other graphics may affect respondent's interest or distract from the questions.XXIX. Numbering of questions may be helpful.

XXX. Questionnaires can be administered by research staff, by volunteers or self-administered by therespondents. Clear, detailed instructions are needed in either case, matching the needs of each audience.[edit] Methods of collection

MethodBenefits/CautionsPostalXXXI. Low cost-per-response.

XXXII. Mail is subject to postal delays, which canbe substantial when posting remote areas or

unpredictable events such as naturaldisasters.

XXXIII. Survey participants can choose to remainanonymous.

XXXIV. It is not labour intensive.TelephoneXXXV. Questionnaires can be conducted swiftly.XXXVI. Rapport with respondents

XXXVII. High response rateXXXVIII. Be careful that your sampling frame (i.e.,

where you get the phone numbers from)doesn't skew your sample, For example, ifyou select the phone numbers from aphone book, you are necessarilyexcluding people who only have a mobile

phone, those who requested anunpublished phone number, and

individuals who have recently moved tothe area because none of these people

will be in the book.XXXIX. Are more prone to social desirability biases

than other modes, so telephone interviewsare generally not suitable for sensitive

topics [2][3]ElectronicXL. This method has a low ongoing cost, and on

most surveys costs nothing for the participantsand little for the surveyors. However, Initial set-up costs can be high for a customised design

due to the effort required in developing theback-end system or programming the

questionnaire itself.XLI. Questionnaires can be conducted swiftly,

without postal delays.XLII. Survey participants can choose to remain

anonymous, though risk being trackedthrough cookies, unique links and other

technology.XLIII. It is not labour intensive.

XLIV. Questions can be more detailed, as opposedto the limits of paper or telephones.[ citation

needed ]XLV. This method works well if your survey

8/7/2019 Questionnaire constructio1

3/4

contains several branching questions. Help orinstructions can be dynamically displayed

with the question as needed, and automaticsequencing means the computer can

determine the next question, rather thanrelying on respondents to correctly follow skip

instructions.XLVI. Not all of the sample may be able to access

the electronic form, and therefore resultsmay not be representative of the target

population.

Personally AdministeredXLVII.Questions can be more detailed, as opposedto the limits of paper or telephones.However, respondents are often limited totheir working memory: specially designedvisual cues (such as prompt cards) may help

in some cases.XLVIII. Rapport with respondents is generally

higher than other modesXLIX. Typically higher response rate than other

modes.L. Can be extremely expensive and time

consuming to train and maintain an interviewer

panel. Each interview also has a marginal costassociated with collecting the data.

LI. Usually a convenience (vs. a statistical orrepresentative) sample so you cannot

generalize your results. However, use ofrigorous selection methods (e.g. those used bynational statistical organisations) can result in a

much more representative sample. [edit] Types of questionsLII. Contingency questions - A question that is answered only if the respondent gives a particular

response to a previous question. This avoids asking questions of people that do not apply to them (forexample, asking men if they have ever been pregnant).

LIII. Matrix questions - Identical response categories are assigned to multiple questions. The questions areplaced one under the other, forming a matrix with response categories along the top and a list of questions

down the side. This is an efficient use of page space and respondents time.LIV. Closed ended questions - Respondents answers are limited to a fixed set of responses. Most scales

are closed ended. Other types of closed ended questions include:A. Yes/no questions - The respondent answers with a yes or a no.

B. Multiple choice - The respondent has several option from which to choose.C. Scaled questions - Responses are graded on a continuum (example : rate the appearance of the

product on a scale from 1 to 10, with 10 being the most preferred appearance). Examples of types ofscales include the Likert scale, semantic differential scale, and rank-order scale (See scale for a complete

list of scaling techniques.).LV. Open ended questions - No options or predefined categories are suggested. The respondent supplies

their own answer without being constrained by a fixed set of possible responses. Examples of types of openended questions include:

A. Completely unstructured - For example, What is your opinion of questionnaires?B. Word association - Words are presented and the respondent mentions the first word that

comes to mind.C. Sentence completion - Respondents complete an incomplete sentence. For example, The

most important consideration in my decision to buy a new house is . . .D. Story completion - Respondents complete an incomplete story.

E. Picture completion - Respondents fill in an empty conversation balloon.F. Thematic apperception test - Respondents explain a picture or make up a story about what they

think is happening in the picture[edit] Question sequence

LVI. Questions should flow logically from one to the next.LVII. The researcher must ensure that the answer to a question is not influenced by previous

8/7/2019 Questionnaire constructio1

4/4

questions.LVIII. Questions should flow from the more general to the more specific.

LIX. Questions should flow from the least sensitive to the most sensitive.LX. Questions should flow from factual and behavioural questions to attitudinal and opinion

questions.LXI. Questions should flow from unaided to aided questions.

LXII. According to the three stage theory (also called the sandwich theory), initial questions should bescreening and rapport questions. Then in the second stage you ask all the product specific questions. In

the last stage you ask demographic questions.