Chapter 6: Data Collection

Introduction
 Once appropriate research topic is determined, proper data
collection, retention, and sharing are vital to research enterprise.
 Data are foundation of economic research since every study is a
search for information about given topic.
Definition:
 Data refers to any group of facts, measurements, or
observations used to make inferences about problem of
investigation.
 It can range from material created in laboratory, to information
obtained in social-science research, such as filled-out questionnaire,
video and audio recordings, or photographs, etc.
 Cont’d
 No research project has unlimited funds, so selection of most
promising data usually is affected by priorities of cost and
convenience.
 Collection of data should be feasible and data should be
sufficient to test hypotheses.
 The first step in good data management is designing your
experiment that create meaningful and unbiased data, that will
not waste resources, and that will appropriately protect human
and animal subjects.
 Cont’d
 If data are not recorded in a fashion that allows others to
validate findings, results can be called into question.
 Data selection should precede actual data collection.
 Clear data selection standards set in advance help prevent
selective data reporting (selectively excluding data that are not
supportive of a research hypothesis) later in research.
 There are a number of methodological issues researchers should
be aware of when selecting data:-
1. Some of data types are: nominal, ordinal or interval measures.
2. Samples ("frames") and sample size, instruments,
Methodologies, etc.
 Cont’d
Data collection methods
 Data collection is process of gathering and measuring
information on variables of interest in accepted systematic
fashion.
 Rigorous collection methodologies, when based on foundation of
solid data selection, enable researchers to answer research
questions, test hypotheses, and evaluate outcomes.
 Data collection methods vary by discipline and data types; but
the emphasis on ensuring accurate collection remains the same.
 Both selection of appropriate data collection instruments and
clearly delineated instructions for their use reduce likelihood of
error.
 Cont’d
 Consequences from improperly collected data include: Inability
to answer research questions accurately, Inability to repeat and
validate study, Distorted, inaccurate findings, Wasted resources,
Misleading other researchers to pursue fruitless avenues of
investigation, Compromised decisions for public policy or private
decision-making and Harm to human participants and animal
subjects.
 While impact of faulty data collection varies by discipline and
nature of investigation, poor collection may cause disproportionate
harm when results of flawed research are used to support public
policy recommendations.
 Cont’d
 Effective methods make detection of errors easier - whether errors
are intentional and deliberate falsifications or inadvertent
(unintentional) systematic or random errors.
 As with data selection, it is critical that researchers have sufficient
skills to ensure the integrity of their data collection efforts.
 For instance: Quality data collection requires rigorous and
detailed recruitment and training plan for data collectors.
 Data management issues
1) Storage and Protection
 Research data must be stored securely both during a research
project and after it ends.
 Reliable security policies and procedures are essential to
safeguard data stored electronically or in physical form.
 Everyday risks like fire, water or other environmental damage,
or common technical failures like hard disk crashes, must be
considered.
 It's essential to make backup copies of data collection
periodically and store copies in secure location.
 Cont’d
2) Confidentiality
 Confidentiality refers to limiting information access and
disclosure to authorized users and preventing access by or
disclosures to unauthorized persons.
 Who can handle which portion of data, at what point during
project, for what purpose, and so on.
 If research data are maintained on personal computer, it is essential
to keep PC physically secured, update software regularly,
particularly anti-malware utilities, and using access protections
 Cont’d
3) Integrity/reliability/
 Integrity refers to trustworthiness of information.
 It postulates that data have not been modified inappropriately,
whether accidentally or deliberately.
 Integrity includes notion that person or entity in question entered
right information i.e. information reflected actual circumstances
(validity) and under same circumstances would generate identical
data (reliability).
 Data Collection Techniques:
 The critical question here is from where and how to get data.
 Data can be acquired from Secondary and primary sources or from
both
Secondary Sources of data:
 Secondary sources are those, which have been collected by other
individuals or agencies.
 As much as possible secondary data should always be considered
first, if available, why reinvent the wheel if data already exists.
 When dealing with secondary data you should ask: Is owner of data
making them available to you? Is it free of charge? If not, how will
you pay? Are data in format that you can work with? and
description of sampling technique, i.e., how sample was collected is
also necessary
 Cont’d
Sources of Secondary Data
 Secondary data may be acquired from various sources: Reports of
various kinds, books, periodicals, reference books
(encyclopedia), university publications (thesis, dissertations, etc.),
policy documents, statistical compilations, proceedings,
personal documents (historical studies) , Internet, etc.
Advantages of Secondary data
1. It can be found more quickly and cheaply.
2. Most researches on past events or distant places have to rely on
secondary data sources.
 Cont’d
Limitations
i. The information often does not meet one’s specific needs.
ii. Definitions might differ, units of measurements may be
different and different time periods may be involved.
iii. Difficult to assess accuracy of information-unknown research
design or conditions under which research took place.
iv. Data could also be out of date.
Primary Sources of Data
 It is data that came into being for first time by people directly
involved in research.
 There are two approaches to primary data collection: qualitative
approach and quantitative approach
 Cont’d
Qualitative data collection approaches
 Qualitative data can be acquired from: case studies, Rapid appraisal
methods, focus group discussions and key informant interviews.
i) Case studies
 case study research involves detailed investigation of particular case
through Interviews or through Direct observation (field visits).
ii)Rapid Rural Appraisal (RRA)
 RRA is systematic expert observation but semi-structured activity
often by multidisciplinary team.
 RRA method takes only short time to complete, tends to be relatively
cheap, and make use of more 'informal' data collection procedures.
 It includes interviews with individuals, households, key informants as
well as group interview techniques.
 Cont’d
iii) Focus group discussions
 FGD is a group discussion guided by facilitator, during which
group members talk freely and spontaneously about certain
topic.
 The group of individuals are expected to have experience or
opinion on topic and selected by researcher.
 Its purpose is to obtain in-depth information on concepts,
perceptions and ideas of group.
 It is more than question-answer interaction.
 The idea is that group members discuss topic and interact among
themselves with guidance from facilitator.
 Cont’d
Why use focus groups?
 The main purpose of focus group research is to draw upon
respondents’ attitudes, feelings, beliefs, experiences and
reactions which would not be captured using other methods.
 Attitudes, feelings and beliefs may likely be revealed via social
gathering and interaction.
 Compared to individual interviews, which aim to obtain individual
attitudes, beliefs and feelings, focus groups elicit multiplicity of
views and emotional processes within group context.
 Cont’d
Strengths and weakness of FGDs
 FGDs can be powerful research tools which provide valuable
information in short period of time and at relatively low cost if
groups have been well chosen, in terms of composition and
number BUT, FGD should not be used for quantitative purposes,
such as testing of hypotheses or generalization of findings for
larger areas, which would require more elaborate surveys.
 It may be risky to use FGDs as single tool, in group discussions,
people tend to center their opinions on most common ones.
 Therefore, it is advisable to combine FGDs with other methods (in-
depth interviews).
 In case of very sensitive topics group members may hesitate to
express their feelings and experiences freely.
 Cont’d
iv)Key Informant Interview
 key informant interview technique is interviewing process for
gathering information from opinion leaders such as elected officials,
government officials, and business leaders, etc.
 This technique is particularly useful for: Raising community
awareness about socio-economic issues, Learning minority viewpoints
and Gaining deeper understanding of opinions and perceptions, etc.
v)Triangulation
 Triangulation refers to use of more than one approach to
investigation of research question in order to enhance confidence in
findings
 The purpose of triangulation is to obtain confirmation of findings
through convergence of different perspectives.
 Cont’d
Why use triangulation?
 By combining multiple methods, and empirical materials, researchers
can hope to overcome weakness or biases and problems that are
associated with single method.
Taxonomy of triangulation
1. Data triangulation: Involves gathering data at different times and
situations, from different subjects using different sampling techniques.
 Surveying relevant stakeholders about impact of policy intervention
would be example.
 Cont’d
 Economic forecasters who rely on national accounts for their modeling
exercises find that there is lag between data and prevailing economic
conditions.
 They often make use of different data sources (and types) to fill this gap.
Example: Using survey data alongside time series data.
2. Investigator triangulation: involves using more than one field
researcher to collect and analyze data relevant to specific research object.
 Asking scientific experimenters to attempt to replicate each other’s work
is example.
3. Theoretical triangulation: involves making explicit references to more
than one theoretical tradition to analyze data.
 This is intrinsically method that allows for different disciplinary
perspectives upon issue.
 This could also be called pluralist or multi-disciplinary triangulation.
 Cont’d
4. Methodological triangulation: involves combination of different
research methods or using different varieties of same method.
 Two forms of methodological triangulation:-
1. Within method triangulation involves making use of different
varieties of the same method.
 Thus, in economics, making use of alternative econometric
estimators would be an example.
2. Between methods triangulation involves making use of different
methods.
 Using ‘quantitative’ and ‘qualitative’ methods in combination..
 Quantitative Primary Data Collection Methods
 quantitative research method involves numeric or statistical
approach to research design.
 It involves collection of data so that information can be
quantified and subjected to statistical treatment.
 Primary data may be collected through: Direct personal
observation method, or Survey or questioning other persons,
from literature search, or Combining them.
1) The Observation Method: Observation includes full range of
monitoring behavioral and non-behavioral activities.
Advantages: It is less challenging and has less bias. One can collect
data at time it occurs and need not depend on reports by others. With
this method one can capture whole event as it occurs.
 Cont’d
Weakness of Observation Method
1. The observer normally must be at scene of event when it takes
place. But it is often difficult or impossible to predict when and
where event will occur.
2. Observation is slow and expensive process since it requires either
human observers or some type of costly investigation(surveillance)
equipment.
3. Its most reliable results are restricted to data that can be
determined by open or deliberate action or surface indicator.
4. It is limited as way to learn about past, or difficult to gather
information on such topics as intensions, attitudes, opinions
and preferences.
 Cont’d
The Survey Method: this is most commonly used method in
economic research.
 To survey is to ask people questions in questionnaire - mailed or
handled by interviewers.
Strength of Survey Method
 It is versatile or flexible method - capable of many different uses.
It does not require that there be visual or other objective
perception of sought information by researcher.
 Questioning might be best way to learn about opinion and
attitudes of people.
 Surveys tend to be more efficient and economical than
observations -surveying using telephone or mail is less expensive.
 Cont’d
Weakness of Survey Method
 The quality of information secured depends heavily on ability and
willingness of respondents.
 Respondent may interpret questions or concept differently from
what was intended by researcher.
 Respondent may deliberately mislead researcher by giving false
information.
 Surveys could be carried out through: Face to face personal
interview, By telephone interview, By mail or e-mail, or By
combination of all these.
 Cont’d
a) Personal Face to face Interview
 It is two-way conversion where respondent is asked to provide
information.
 It involves one person interviewing another person for personal or
detailed information.
Advantages
 The depth and detail of information that can be secured far
exceeds information secured from telephone or mail surveys.
 Interviewers can probe additional questions, gather supplemental
information through observation, etc.
 Interviewers can make adjustments to language of interview
because they can observe problems and effects with which
interviewer is faced.
 Limitations of Personal Face to face Interview
 Method is expensive enterprise – usually US$50+ per interview.
 Hence, personal interviews are generally used only when subjects
are not likely to respond to other survey methods.
 Interviewer may also be reluctant to visit unfamiliar
neighborhoods.
 Biased results grow out of three types of errors:-
i. Sampling error – error introduced when dealing with sample
instead of population
ii. Non-response error
iii. Response error
 cont’d
b) Telephone Interview
 Telephone can be helpful medium of communication in setting up
interviews and screening large population for rare respondent type.
 Telephone surveys are fastest method of gathering information
from relatively large sample.
 Unlike mail survey, telephone survey allows opportunity for
some opinion probing.
 Telephone surveys generally last less than ten minutes.
Strength of this method
 Moderate travel and administrative costs, faster completion of
study and Responses can be directly entered on to computer
 Cont’d
Limitations of this method
 Respondents must be available by phone.
 length of interview period is short so can result in less complete
responses.
 Those interviewed by phone find experience to be less rewarding
than personal interview.
 Cont’d
C) Interviewing by mail (Solicited responses)
 Self-administrated questionnaires may be used in surveys.
 They are ideal for large sample sizes, or when sample comes from
wide geographic area.
Advantages
 Lower cost than personal interview, Persons who might
otherwise be inaccessible can be contacted (major corporate
executives), Respondents can take more time to collect facts, and
there is no possibility of interviewer bias.
Disadvantages
 Non response error is high, and large amount of information may
not be acquired.
 Cont’d
d) Online Surveys (E-mail and internet)
 E-mail surveys are relatively new and little is known about effect of
sampling bias in internet surveys.
Advantages:
 Very inexpensive -saves inputting costs as well and Respondents feel
privacy.
Disadvantages:
 Very biased toward wealthy, even very poor have less online access in
industrialized world.
 While it is clearly most cost effective and fastest method of distributing
survey, demographic profile of internet user does not always
represent general population.
 Therefore, before doing an e-mail or internet survey, carefully consider
effect that this bias might have on results.
 Survey Instrument Design (questionnaire design)
 Actual instrument design begins by drafting specific
measurement questions in form of questionnaire.
 Questionnaires are easy to analyze.
 Data entry and tabulation for nearly all surveys can be easily
done with many computer software packages.
 Questionnaires are familiar to most people.
 Nearly everyone has had some experience completing
questionnaires and they generally do not make people
apprehensive(frightened).
 Questionnaires reduce bias.
 There is uniform question presentation.
 The researcher's own opinions will not influence answer.
 Cont’d
 Mailed questionnaires are less intrusive(disturbing).
 When respondent receives questionnaire by mail, he/she is free to
complete questionnaire on his/her own time-table.
 One major disadvantage particularly with mailed questionnaires is
possibility of low response rates.
 Low response is curse of statistical analysis since it can
dramatically lower our confidence in results.
 Response rates vary widely from one questionnaire to another but
well-designed studies consistently produce high response rates.
 Another disadvantage of mailed questionnaires is inability to
probe(investigate) responses. Since questionnaires are structured
instruments they allow little flexibility to respondent.
 Cont’d
 Lack of personal contact in mail/online surveys will have
different effects depending on type of information being requested.
 Questionnaire requesting factual information will probably not be
affected by lack of personal contact.
 But, questionnaire probing sensitive issues or attitudes may be
severely affected.
 When returned questionnaires arrive in mail/e-mail, it's natural to
assume that respondent is same person you sent questionnaire to.
But, for variety of reasons, respondent may not be who you think
it is. Often business questionnaires get handed to other employees
for completion.
 The main Components of questionnaire
 Covering letter: brief purpose of survey, which is doing it, time
involved, etc.
 The cover letter provides your best chance to persuade
respondent to complete survey.
 Identification data: respondent’s name, address, time and date of
interview, code of interviewer, etc.
 Instruction: Include clear and concise instructions on how to
complete questionnaire.
 These must be very easy to understand, so use short sentences and
basic vocabulary.
 Information sought: major portion of questionnaire
 Designing of Questionnaire – general
considerations
 Questionnaire is developed to directly address goals of study.
 Well-defined goals are best ways to assure good questionnaire
design.
 When goals of study can be expressed in few clear and concise
sentences, design of questionnaire becomes considerably easier.
 Hence, ask only questions that directly address study goals.
 Avoid temptation (invitation) to ask questions because it would be
"interesting to know".
 As general rule, with only few exceptions, long questionnaires
get less response than short questionnaires.
 Cont’d
 Response rate is single most important indicator of how much
confidence you can place in results.
 You must do everything possible to maximize response rate.
 Hence, keep your questionnaire short to maximize response
rate.
 In developing survey instrument the following issues need to be
considered carefully:
i. Question content
ii. Question wording
iii. Response structure or format.
iv. Question sequence.
v. Physical characteristic
vi. Reproducing questionnaire
 Cont’d
 In other words, both subject and wording of each question as well
as psychological order of question needs to be considered.
 Questions that are more interesting, easier to answer, and less
threatening usually are placed early in sequence to encourage
response.
 Cont’d
1. Question Content
 Both questions and statements could be used in survey research.
 Using both in given questionnaire gives researcher more flexibility
 Minimizing number of questions is highly desirable, but we
should never try to ask two questions in one.
 Question content usually depends on respondent’s: ability, and
willingness to answer question accurately.
a) Is question of proper scope? Respondent must be competent
enough to answer questions.
 respondent information level should be assessed when determining
content and appropriateness of question.
 Questions that overtax respondent’s recall ability may not be
appropriate.
 Cont’d
b) Willingness of respondent to answer adequately
 Even if respondents have information, they may be unwilling to
give it.
 Some topics are also too sensitive to discuss with strangers.
Examples: the most sensitive topics concern money matters and
family life.
 If respondents consider topic to be irrelevant and uninteresting
they would be reluctant to give adequate answer.
 Some of main reasons for unwillingness:
i. situation is not appropriate for disclosing information
ii. Disclosure of information would be
embarrassing(uncomfortable)
iii. Disclosure of information is potential threat to respondent.
 Cont’d
 Some approaches that may help to secure more complete and truthful
information:
i. Use indirect statement i.e., “other people”,
ii. Motivate respondent to provide appropriate information
iii. Use methods other than questioning to secure data (observation,
Change design of questioning process)
iv. Apply appropriate questioning sequences that will lead respondent
from “safe” question gradually to those that are more sensitive. So,
begin with few non-threatening and interesting questions.
v. Provide incentives as motivation for properly completed questionnaire.
 What does respondent get for completing your questionnaire?
Altruism(selflessness) is rarely effective motivator.
 Attaching dollar bill to questionnaire works well.
 If you use mail, always include self-addressed postage-paid envelope.
 Cont’d
2. Question Wording: Using Shared Vocabulary
 In survey two parties must understand each other and this is
possible only if vocabulary used is common to both parties.
 So, don’t use uncommon words or long sentences or
abbreviations and make items as brief as possible.
 And, don’t use emotionally loaded or vaguely defined words.
 One way to eliminate misunderstandings is to emphasize crucial
words in each item by using bold, italics or underlining.
 Words like usually, often, sometimes, occasionally, seldom, etc.,
are "commonly" used in questionnaires, although it is clear that
they do not mean same to all people.
 Cont’d
3. Response structure or format.
 A third major decision area is degree and form of structure
imposed on responses.
 The options range from open (free choice of words) to closed
(specified alternatives).
a) Open Ended Questions
 An open-ended question (free response) question asks questions to
which respondents can give any answer.
 Open ended (free response) in turn range from those in which
respondents express themselves extensively to those in which
freedom is to choose one word in “fill in” question.
 Cont’d
Advantages
i. Permit unlimited number of possible answers
ii. Respondents can answer in detail and can qualify and clarify
responses
iii. Permit creativity, self expression, etc.
Limitations
iv. Different respondents give different answers – responses may
not be consistent. Some responses may be irrelevant.
v. Comparison and statistical analysis become very difficult.
vi. Requires greater amount of respondent time, thought and
effort.
 Cont’d
b) Closed Questions
 Although open response question may have many advantages
closed questions are generally preferable in large surveys.
 Closed questions are often categorized as dichotomous or
multiple-choice questions.
Advantages
1. Easier and quicker for respondents to answer,
2. Easier to compare answers of different respondents,
3. Easier to code and statistically analyze
4. less costly to administer
5. reduce variability of responses
6. make fewer demands on interviewer skill, etc.
 Cont’d
Limitations
i. Can suggest ideas that respondents would not otherwise have.
ii. Respondents can be confused because of too many choices.
During construction of closed ended questions: response
categories provided should be exhaustive.
 They should include all possible responses that might be expected.
 In multiple choice type questions, answer categories must be
mutually exclusive.
iii. Respondent may not be compelled to select more than one
answer.
 Cont’d
4) Question Sequence – order of questions
 The order in which questions are asked can affect response as
well as overall data collection activity.
 Grouping questions that are similar will make questionnaire
easier to complete, and respondent will feel more comfortable.
 Items on questionnaire should be grouped into logically coherent
sections.
 Questions that use the same response formats, or those that cover
specific topic, should appear together.
 Cont’d
 Each question should follow comfortably from previous
question.
 Transitions between questions should be smooth.
 Questions that jump from one unrelated topic to another are not
likely to produce high response rates.
 It may be necessary to present general questions before specific
ones in order to avoid response contamination.
 At the same time, it is important to group items into coherent
categories.
 All items should flow smoothly from one to the next.
 Cont’d
5) Physical Characteristics of Questionnaire
 The physical appearance of questionnaire is important as
wording of questions asked.
 An improperly laid out questionnaire can lead respondents to
miss questions, can confuse them.
 So, questionnaire should be spread out properly.
 Putting more than one question on a line will result in some
respondents skipping the second question.
 Abbreviating questions will result in misinterpretation of the
question.
 Cont’d
Formats for Responses
 A variety of methods are available for presenting series of
response categories: Boxes, Blank spaces
Providing Instructions
 Every questionnaire whether to be self administered by
respondent or administered by interviewer should contain clear
instructions.
 Cont’d
6) Reproducing questionnaire
 Having constructed questionnaire it is necessary to provide
enough copies for actual data collection.
 A neatly reproduced instrument will encourage higher response
rate, thereby providing better data.
 Use professional production methods for questionnaire.
 The final test of questionnaire is to try it on representatives of
target audience. If there are problems with questionnaire, they
almost always show up here.
 Qualities of Good Questionnaire
 There are good and bad questions and qualities of good question
are as follows:
1. Evokes truth: Questions must be non-threatening.
 When respondent is concerned about consequences of answering
question there is good possibility that answer will not be truthful.
 Anonymous questionnaires that contain no identifying
information are more likely to produce honest responses than
those identifying respondent
 If your questionnaire does contain sensitive items, be sure to
clearly state your policy on confidentiality.
2. Asks for answer on only one dimension.
 The purpose of survey is to find out information.
 Cont’d
 A question that asks for response on more than one dimension
will not provide information you are seeking.
 Example: a researcher investigating new food snack asks "Do you
like texture and flavor of snack?" If respondent answers "no",
then researcher will not know if respondent dislikes texture or
flavor, or both.
 Another questionnaire asks, “Were you satisfied with quality of our
food and service?” Again, if the respondent answers "no", there is
no way to know whether quality of food, service, or both were
unsatisfactory.
 A good question asks for only one "bit" of information.
 Cont’d
3. Can accommodate all possible answers.
 Multiple choice items are most popular type of survey questions
because they are generally easiest for respondent to answer and
easiest to analyze.
 Asking question that does not accommodate all possible responses
can confuse and frustrate respondent.
 For example, consider the following question: What brand of
computer do you own? A. IBM PC B. Apple
 Clearly, there are many problems with this question.
 What if respondent doesn't own computer? What if he owns
different brand of computer? What if he owns both IBM PC and
Apple? There are two ways to correct this kind of problem.
 Cont’d
 The first way is to make each response separate dichotomous item
on questionnaire.
 For example: Do you own IBM PC? (Circle: Yes or No).
 Do you own Apple computer? (circle: Yes or No).
 Another way to correct problem is to add necessary response
categories and allow multiple responses.
 This is preferable method because it provides more information
than previous method.
 What brand of computer do you own? (Check all that apply)
__ do not own computer __ IBM PC __ Apple __ other
 Cont’d
4. Has mutually exclusive options.
 A good question leaves no ambiguity in mind of respondent.
 There should be only one correct or appropriate choice for
respondent to make.
 obvious example is: Where did you grow up? A. country B. farm
C. city
 A person who grew up on farm in -country would not know
whether to select choice A or B.
 This question would not provide meaningful information.
 Worse than that, it could frustrate respondent and questionnaire
might find its way to trash.
 Cont’d
5. Produces variability of responses.
 When question produces no variability in responses, we are left with
considerable uncertainty about why we asked question and what we learned
from information.
 If question does not produce variability in responses, it will not be possible to
perform any statistical analyses on item.
For example: What do you think about this report? _
 It's worst report I've read
 It's somewhere between worst and best
 It's best report I've read
 Since almost all responses would be choice B, very little information is learned.
 Design your questions so they are sensitive to differences between
respondents
 As another example: Are you against drug abuse? (Circle: Yes or No).
 Again, there would be very little variability in responses and we'd be left
wondering why we asked question in first place.
 Cont’d
6. Follows comfortably from previous question.
 Transitions between questions should be smooth.
 Grouping questions that are similar will make questionnaire easier
to complete, and respondent will feel more comfortable.
 Questionnaires that jump from one unrelated topic to another
feel disjointed and are not likely to produce high response rates.
7. Does not presuppose certain state of affairs.
 Among most subtle(indirect) mistakes in questionnaire design are
questions that make unwarranted(unnecessary) assumption.
 An example of this type of mistake is: Are you satisfied with your
current auto insurance? (Yes or No).
 This question will present problem for someone who does not
currently have auto insurance.
 Cont’d
 Write your questions so they apply to everyone.
 This often means simply adding additional response category.
 Are you satisfied with your current auto insurance?
A) Yes

B) No

C) Don't have auto insurance

 One of most common mistaken assumptions is that respondent
knows correct answer to question.
 Industry surveys often contain very specific questions that
respondent may not know the answer to.
 Cont’d
8. Does not imply desired answer.
 Wording of question is extremely important.
 We are striving for objectivity in our surveys and, therefore, must be careful
not to lead respondent into giving answer we would like to receive.
 Leading questions are usually easily spotted(covered) because they use negative
phraseology.
 As examples: Wouldn't you like to receive our free brochure?, Don't you think
Congress is spending too much money?
9. Does not use emotionally loaded or vaguely defined words.
 This is one of areas overlooked by both beginners and experienced researchers.
 Quantifying adjectives (e.g., most, least, majority) are frequently used in
questions.
 It is important to understand that these adjectives mean different things to
different people.
 Cont’d
10. Does not use unfamiliar words or abbreviations.
 Remember who your audience is and write your questionnaire for
them.
 Do not use uncommon words or compound sentences.
Abbreviations are okay if you are absolutely certain that every
single respondent will understand their meanings.
 The following question might be okay if all respondents are
accountants, but it would not be good question for general public.
What was your AGI (Adjusted gross income)last year? ______
 Cont’d
11. Does not ask respondent to order or rank series of more than
five items.
 Questions asking respondents to rank items by importance should
be avoided.
 This becomes increasingly difficult as number of items increases,
and answers become less reliable.
 In order to successfully complete this task, respondent must
mentally continue to re-adjust his answers until they total one
hundred percent.
 Limiting number of items to five will make it easier for respondent
to answer
 Cont’d
For example: What percent of your budget do you spend on direct
mail advertising? ____ Very few people would know answer to this
question without looking it up, and very few respondents will take
time and effort to look it up.
 It is important to look at each question and decide if all
respondents will be able to answer it.
12. Be careful not to assume anything.
 For example: the following question assumes respondent knows
what Proposition 13 is about.
 Are you in favor of Proposition 13 ?
A) Yes B) No C) Undecided
 If there is any possibility that respondent may not know answer to
your question, include "don't know" response category.
 R 6
P T E
H A
F C
D O
EN