WEEK 5
CHAPTER 7
7.1 Foundations of survey research
Survey = a systematic way of asking people to volunteer information regarding their opinions
and behaviours
– One of the most important areas of measurement in applied social research
7.2 Types of survey research
Survey -> data collection tool used to gather information from people by asking questions
about one or more topics
(7.2a) Questionnaire
The respondent completes this instrument -> self-administered
Can be open-ended and long
● Mail survey = a paper-and-pencil survey that is sent to respondents through the mail
○ Inexpensive, can be sent to many people BUT response rates often low and untimely
● Group-administered questionnaire = a survey administered in a group setting (e.g. to all
students in a class) - sample brought together
○ Convenient, high response, relatively easy to assemble
● Household drop-off survey = a paper-and-pencil survey that is administered by dropping
it off at the respondent’s household and, either pickup it up later or having the
respondent to return it directly
○ Assures direct personal contact, convenient, higher willingness to respond BUT less
economical (cost of travel and time)
● Point-of-experience survey = a survey delivered at or immediately after the experience
that the respondent is being asked about (e.g. customer satisfaction survey)
○ Rapid response needed if experience can be forgotten, can give answer that are
socially desirable
● Electronic survey = a survey that is administer via a computer program, typically
distributed via email and/or a web site
○ Elimination of paper, postage, mail-out and data entry costs, encourages timely
responses, can reach out to international respondents
○ Email surveys are “pushed” directly to respondent’s computer - embedded in
message
◆ Easier to create but limited graphics and interaction
○ Web surveys have to “pull” respondent to website - web browser used
● Dual-media survey = a survey distributed simultaneously in two ways
○ Respondents can select preferred way
○ BUT someone can have multiple emails in a house so hard to sample individuals or
households and people an share emails so you don’t know who saw or replied to
survey
(7.2b) Interview
Researcher asks the participant questions and then goes on to complete the instrument based
on their answers
Usually includes instructions and space for interviewer to record observations about progress
,of interview
● Personal interview = one-on-one interview between an interviewer and a respondent
○ Interview guide usually used to provide script for asking questions and follow-up
prompts
○ Interviewer can ask follow-ups, easier for respondent especially if you are seeking
opinions or impressions
○ BUT time consuming and resource intensive, interviewer has to be trained well
● Group interview = interview administered to respondents in a group setting
○ Focus group (structured form of group int.) = a qualitative measurement method
where input on one or more focus topics is collected from participants in a small-
group setting where the discussion is structured and guided by facilitator
◆ Enable deeper consideration of complex issues
◆ BUT people might not say what they believe, ground rules needed
● Telephone interview = a personal interview that is conducted over the phone (e.g. most
major public opinion polls)
○ Researcher can gather info quickly, can ask follow-ups
○ BUT many people don’t have publicly listed telephone numbers, or phones in
general, some people don’t like intrusion of a call, also more expensive
7.3 SELECTING A SURVEY METHOD
(7.3a) Population issues
● Can the population units be identified?
○ For some populations, a list of units to be sample might be difficult or impossible to
compile
○ If list can’t be made you can’t use mail surveys or telephone interviews
● Is the population literate?
○ Questionnaires requires your respondents to read
● Are there language issues?
○ You might need to produce multiple versions of your questionnaire
○ For mails you need to know what language your respondent speaks before and send
multiple translations
○ Make sure that important things don’t get lost in translation and connotations in
your instrument are not culturally specific
○ Web-based interviews better than email if pictures are needed for easier
interpretation
● Will the population cooperate?
○ Research on illegal immigrants has a difficult methodological problem (speak with
them)
○ Those respondents are at risk legally if info they give out gets into the hands of
authorities
○ In general when target group engages in illegal or unpopular activities
● What are the geographic restrictions?
○ Is population of interest dispersed of a broad geographic range for you to study
feasibly with a personal interview?
○ Less visible to conduct research that requires direct visits with respondents that are
widely dispersed
○ Mails, phone interviews better
(7.3b) Sampling issues
, ● What data is available?
○ What info do you have about your sample? (Current address, phone number, contact
lists up to date)
● Can respondents be found?
○ Some people travel a lot, are busy, work the night shift
○ So even if data is available (accurate email etc.) you may not be able to locate or
contact your sample
● Who is the respondent?
○ Do you want to interview a specific individual or e.g. the head of the household
○ What if they are unwilling to be interviewed but someone else in the house is
willing?
○ Similar problems arise when you sample groups, agencies or companies
● Can all members of the population be sampled?
○ If you have an incomplete list of the population (sampling frame) you may not be
able to sample every member of the population
○ Some groups are hard to keep up to date (people move or change their names)
○ Even if they are on your list, you might not be able to get to them or they might not
even be on your list
● Are response rates likely to be a problem?
○ Some members of your sample may refuse to respond, others might not have the
time (e.g. to send in your questionnaire by the due date)
○ Some might misplace the instrument or forget about the appointment for an
interview
○ Low response rates are among the most difficult problems in survey research and
can ruin a well-designed survey effort
○ Electronic surveys can improve response rates
● Will incentives for participation help?
○ Way of increasing motivation of your respondents to complete the survey
○ e.g. money, gift cards or lottery chances
○ Carefully consider your population and what is meaningful to them
(7.3c) Question issues
● What types of questions can you ask?
○ Personal questions? -> group interviews not appropriate
○ Lots of detail in responses? Complex or technical question? -> interview better
○ Can you anticipate for frequent or important types of responses and develop
reasonable close-ended questions?
● Will filter questions be needed?
○ Needed to determine whether the respondent is qualified to answer your questions
of interest - e.g. you wouldn’t want them to answer about something they haven’t
seen or experienced
○ You might need to filter on several variables e.g. age, gender, experience
○ The more complicated the filtering, the less likely it is that you can rely on paper-
and-pencil instruments without confusing the respondent
● Can question sequence be controlled?
○ Can you construct a reasonable sequence of questions in advance?
○ Or are you doing an initial exploratory study in which you may need to ask follow-
up questions that you can’t easily anticipate? - interviews better than surveys
● Will lengthy questions be asked?
○ If your subject matter is complicated, you may need to give the respondent some
CHAPTER 7
7.1 Foundations of survey research
Survey = a systematic way of asking people to volunteer information regarding their opinions
and behaviours
– One of the most important areas of measurement in applied social research
7.2 Types of survey research
Survey -> data collection tool used to gather information from people by asking questions
about one or more topics
(7.2a) Questionnaire
The respondent completes this instrument -> self-administered
Can be open-ended and long
● Mail survey = a paper-and-pencil survey that is sent to respondents through the mail
○ Inexpensive, can be sent to many people BUT response rates often low and untimely
● Group-administered questionnaire = a survey administered in a group setting (e.g. to all
students in a class) - sample brought together
○ Convenient, high response, relatively easy to assemble
● Household drop-off survey = a paper-and-pencil survey that is administered by dropping
it off at the respondent’s household and, either pickup it up later or having the
respondent to return it directly
○ Assures direct personal contact, convenient, higher willingness to respond BUT less
economical (cost of travel and time)
● Point-of-experience survey = a survey delivered at or immediately after the experience
that the respondent is being asked about (e.g. customer satisfaction survey)
○ Rapid response needed if experience can be forgotten, can give answer that are
socially desirable
● Electronic survey = a survey that is administer via a computer program, typically
distributed via email and/or a web site
○ Elimination of paper, postage, mail-out and data entry costs, encourages timely
responses, can reach out to international respondents
○ Email surveys are “pushed” directly to respondent’s computer - embedded in
message
◆ Easier to create but limited graphics and interaction
○ Web surveys have to “pull” respondent to website - web browser used
● Dual-media survey = a survey distributed simultaneously in two ways
○ Respondents can select preferred way
○ BUT someone can have multiple emails in a house so hard to sample individuals or
households and people an share emails so you don’t know who saw or replied to
survey
(7.2b) Interview
Researcher asks the participant questions and then goes on to complete the instrument based
on their answers
Usually includes instructions and space for interviewer to record observations about progress
,of interview
● Personal interview = one-on-one interview between an interviewer and a respondent
○ Interview guide usually used to provide script for asking questions and follow-up
prompts
○ Interviewer can ask follow-ups, easier for respondent especially if you are seeking
opinions or impressions
○ BUT time consuming and resource intensive, interviewer has to be trained well
● Group interview = interview administered to respondents in a group setting
○ Focus group (structured form of group int.) = a qualitative measurement method
where input on one or more focus topics is collected from participants in a small-
group setting where the discussion is structured and guided by facilitator
◆ Enable deeper consideration of complex issues
◆ BUT people might not say what they believe, ground rules needed
● Telephone interview = a personal interview that is conducted over the phone (e.g. most
major public opinion polls)
○ Researcher can gather info quickly, can ask follow-ups
○ BUT many people don’t have publicly listed telephone numbers, or phones in
general, some people don’t like intrusion of a call, also more expensive
7.3 SELECTING A SURVEY METHOD
(7.3a) Population issues
● Can the population units be identified?
○ For some populations, a list of units to be sample might be difficult or impossible to
compile
○ If list can’t be made you can’t use mail surveys or telephone interviews
● Is the population literate?
○ Questionnaires requires your respondents to read
● Are there language issues?
○ You might need to produce multiple versions of your questionnaire
○ For mails you need to know what language your respondent speaks before and send
multiple translations
○ Make sure that important things don’t get lost in translation and connotations in
your instrument are not culturally specific
○ Web-based interviews better than email if pictures are needed for easier
interpretation
● Will the population cooperate?
○ Research on illegal immigrants has a difficult methodological problem (speak with
them)
○ Those respondents are at risk legally if info they give out gets into the hands of
authorities
○ In general when target group engages in illegal or unpopular activities
● What are the geographic restrictions?
○ Is population of interest dispersed of a broad geographic range for you to study
feasibly with a personal interview?
○ Less visible to conduct research that requires direct visits with respondents that are
widely dispersed
○ Mails, phone interviews better
(7.3b) Sampling issues
, ● What data is available?
○ What info do you have about your sample? (Current address, phone number, contact
lists up to date)
● Can respondents be found?
○ Some people travel a lot, are busy, work the night shift
○ So even if data is available (accurate email etc.) you may not be able to locate or
contact your sample
● Who is the respondent?
○ Do you want to interview a specific individual or e.g. the head of the household
○ What if they are unwilling to be interviewed but someone else in the house is
willing?
○ Similar problems arise when you sample groups, agencies or companies
● Can all members of the population be sampled?
○ If you have an incomplete list of the population (sampling frame) you may not be
able to sample every member of the population
○ Some groups are hard to keep up to date (people move or change their names)
○ Even if they are on your list, you might not be able to get to them or they might not
even be on your list
● Are response rates likely to be a problem?
○ Some members of your sample may refuse to respond, others might not have the
time (e.g. to send in your questionnaire by the due date)
○ Some might misplace the instrument or forget about the appointment for an
interview
○ Low response rates are among the most difficult problems in survey research and
can ruin a well-designed survey effort
○ Electronic surveys can improve response rates
● Will incentives for participation help?
○ Way of increasing motivation of your respondents to complete the survey
○ e.g. money, gift cards or lottery chances
○ Carefully consider your population and what is meaningful to them
(7.3c) Question issues
● What types of questions can you ask?
○ Personal questions? -> group interviews not appropriate
○ Lots of detail in responses? Complex or technical question? -> interview better
○ Can you anticipate for frequent or important types of responses and develop
reasonable close-ended questions?
● Will filter questions be needed?
○ Needed to determine whether the respondent is qualified to answer your questions
of interest - e.g. you wouldn’t want them to answer about something they haven’t
seen or experienced
○ You might need to filter on several variables e.g. age, gender, experience
○ The more complicated the filtering, the less likely it is that you can rely on paper-
and-pencil instruments without confusing the respondent
● Can question sequence be controlled?
○ Can you construct a reasonable sequence of questions in advance?
○ Or are you doing an initial exploratory study in which you may need to ask follow-
up questions that you can’t easily anticipate? - interviews better than surveys
● Will lengthy questions be asked?
○ If your subject matter is complicated, you may need to give the respondent some
