Choosing Question Structure Marketing Research Help

A question may be unstructured or structured. In the following sections, we define unstructured questions and discuss their relative advantages and disadvantages and then consider the major types of structured questions: multiple choice, dichotomous, and scales.”

Unstructured Questions

Unstructured questions are open-ended questions that respondents answer in their own words, They are also referred to as free-response or free-answer questions. The following are some examples:

• What is your occupation?
• What do you think of people who patronize discount department stores?
• Who is your favorite political figure?

Open-ended questions are good as first questions on a topic. They enable the respondents to express general attitudes and opinions that can help the researcher interpret their responses to structured questions. Unstructured questions have a much less biasing influence on response than structured questions. Respondents are free to express any views. Their comments and explanations can provide the researcher with rich insights. Hence, unstructured questions are useful in exploratory research.

A principal disadvantage is that potential for interviewer bias is high. Whether the interviewers record the answers verbatim or write down only the main points, the data depend on the skills of the interviewers. Tape recorders should be used if verbatim reporting is important.

Another major disadvantage of unstructured questions is that the coding of responses is costly and time-consuming.’? The coding procedures required to summarize responses in a format useful for data analysis and interpretation can be extensive. Implicitly, unstructured or open-ended questions give extra weight to respondents who are more articulate. Also, unstructured questions are not suitable for self- or computer-administered questionnaires (mail, mail panel, CAPI, e-mail, and Internet), because respondents tend to be more brief in writing than in speaking.

Precoding can overcome some of the disadvantages of unstructured questions. Expected responses are recorded in multiple-choice format, although the question is presented to the respondents as an open-ended question, Based on the respondent’s reply, the interviewer selects the appropriate response category. This approach may be satisfactory when the respondent can easily formulate the response, and it is easy to develop precoded categories because the response alternatives are limited. For example, this example may be used to obtain information on ownership of appliances. It has also been used successfully in business surveys, as shown by the following example.

Real Research

Assessing Access Attitudes

A major telecommunications firm conducted a national telephone survey to determine the attitudes of businesses toward telecommunication services. One of the questions was asked as an open-ended question with precoded responses.

Which company or companies is your business presently using for long-distance telephone service? If more than one, please indicate the names of all the companies, (ASK AS AN OPENED QUESTION. ALLOW FOR MULTIPLE RESPONSES AND SCORE AS FOLLOWS.)

1. _____VERIZON
3. _____ QWEST
4. _____AT&T
5, _____Regional Bell operating co. (insert name)
6, _____Other (specify)
7, _____Don’t know/no answer.

In general. open-ended questions are useful in exploratory research and as opening questions, Otherwise. their disadvantages outweigh their advantages in a large survey.’?

Structured Questions

Structured questions specify the set of response alternatives and the response format, A structured question may be multiple choice, dichotomous, or a scale.

MULTIPLE-CHOICE QUESTIONS In multiple-choice questions, the researcher provides a choice of answers and respondents are asked to select one or more of the alternatives given, Consider the following question.

Do you intend to buy a new car within the next six months?
_____Definitely will not buy
_____Probably will not buy
_____Probably will buy
_____Definitely will buy
_____Other (please specify)

Several of the issues with respect to itemized rating scales also apply to multiple-choice answers, Two additional concerns in designing multiple-choice questions are the number of alternatives that should be included and order or position bias The response alternatives should include the set of all possible choices, The general guideline is to list all alternatives that may be of importance and include an alternative labeled “Other (please specify).” as shown here. The response alternatives should be mutually exclusive, Respondents should also be able to identify one, and only one, alternative, unless the researcher specifically allows two or more choices (for example, “Please indicate all the brands of soft drinks that you have consumed in the past week”), If the response alternatives are numerous, consider using more than one question 10 reduce the information-processing demands on the respondents.

Order or position bias is the respondents’ tendency to check an alternative merely because it occupies a certain position or is listed in a certain order. Respondents tend to check the first or the last statement in a list, particularly the first. For a list of numbers (quantities or prices), there is a bias toward the central value on the list. To control for order bias, several forms of the questionnaire should be prepared with the order in which the alternatives are listed varied from form to form. Unless the alternatives represent ordered categories, each alternative should appear once in each of the extreme positions, once in the middle, and once somewhere in between Multiple-choice questions overcome many of the disadvantages of open-ended questions, because interviewer bias is reduced and these questions are administered quickly. Also, coding and processing of data are much less costly and time-consuming, In self-administered questionnaires, respondent cooperation is improved if the majority of the questions are structured, Multiple-choice questions are not without disadvantages, Considerable effort is required to design effective multiple-choice questions. Exploratory research using open-ended questions may be required to determine the appropriate response alternatives. It is difficult to obtain information on alternatives not listed. Even if an “Other (please specify)” category is included, respondents tend to choose among the listed alternatives. In addition, showing respondents the list of possible answers produces biased responses. There is also the potential for order bias.21

DICHOTOMOUS QUESTIONS A dichotomous question has only two response alternatives: yes or no, agree or disagree, and so on, Often, the two alternatives of interest are supplemented by a neutral alternative, such as “no opinion,” “don’t know,” “both,” or “none,’,22 The question asked before about intentions to buy a new car as a multiple-choice question can also be asked as a dichotomous question.

Do you intend to buy a new car within the next six months?
_____ yes
_____ No
_____ Don’t know

The decision to use a dichotomous question should be guided by whether the respondents approach the issue as a yes-or-no question. Although decisions are often characterized as series of binary or dichotomous choices, the underlying decision-making process may reflect uncertainty, which can best be captured by multiple-choice responses, For example, two individuals may be equally likely to buy a new car within the next six months if the economic conditions remain favorable. However, one individual, who is being optimistic about the economy, will answer “yes,” whereas the other, feeling pessimistic, will answer “no.”

Another issue in the design of dichotomous questions is whether to include a neutral response alternative. If it is not included, respondents are forced to choose between “yes” and “no” even if they feel indifferent. On the other hand, if a neutral alternative is included, respondents can avoid taking a position on the issue, thereby biasing the results, We offer the following guidelines, If a substantial proportion of the respondents can be expected to be neutral, include a neutral alternative, If the proportion of neutral respondents is expected to be small, avoid the neutral alternative.

The general advantages and disadvantages of dichotomous questions are very similar to those of multiple-choice questions, Dichotomous questions are the easiest type of questions to code and analyze, but they have one acute problem: The response can be influenced by the wording of the question. To illustrate, the statement, “Individuals are more to blame than social conditions for crime and lawlessness in this country,” produced agreement from 59.6 percent of the respondents, However, on a matched sample that responded to the opposite statement, “Social conditions are more to blame than individuals for crime and lawlessness in this country,” 43.2 percent (as opposed to 40.4 percent) agreed.23 To overcome this problem, the question should be framed in one way on one-half of the questionnaires and in the opposite way on the other half, This is referred to as the split ballot technique.

SCALES  To illustrate the difference between scales and other kinds of structured questions, consider the question about intentions to buy a new car One way of framing this using a scale is as follows:

Do you intend to buy a new car within the next six months?


This is only one of several scales that could be used to ask this question As shown in the following example, a survey may contain different types of questions.

Real Research

Question Structure in GAP

The Global Airline Performance (GAP) study is a survey conducted to measure the opinions of air travelers on 22 airlines departing from 30 airports across the world. It reaches 240,000 passengers each year and conducted in seven languages. This survey uses different types of structured questions, including multiple choice, dichotomous, and scales. as illustrated in the following.24 Q. How did you make your reservation? (Please pick ONE only)

____Airline Web site

____ Airline phone reservations or ticket office

____ Through travel agent Other

Q. Are you using an e-ticket (electronic paperless ticket) on this trip?

Q. Based on your experience of today’s flight, would you select this airline for your next trip on this route?

___ Definitely would (5).
___ Probably would (4)
___ Might/might not (3)
___ Probably not (2)
___ Definitely not (1)

Posted on November 28, 2015 in Questionnaire and Form Design

Share the Story

Back to Top
Share This