Chapter 7 Survey Research
coverage bias
Misrepresentation of a population by survey results that disproportionately represent one group over another
interviewer error
Mistakes made by interviewers failing to record survey responses correctly.
No Contacts
Potential respondents in the sense that they are members of the sampling frame but who do not receive the request to participate in the research.
precall
A phone call notifying potential respondents that an interview request is on the way as a tool to increase participation rates
self-selection bias
A bias that occurs because people who feel strongly about a subject are more likely to respond to survey questions than people who feel indifferent about it
response bias
A bias that occurs when respondents either consciously or unconsciously answer questions with a certain slant that misrepresents the truth.
data processing error
A category of administrative error that occurs because of incorrect data entry, incorrect computer programming, or other procedural errors during data analysis.
extremity bias
A category of response bias that results because some individuals tend to use extremes when responding to question
Respondent error
A category of sample bias resulting from some respondent action such as lying or inaction such as not responding.
sample survey
A more formal term for a survey emphasizing that respondents' expressed answers presumably represent a sample of the larger target population's opinion
sample bias
A persistent tendency for the results of a sample to deviate in one direction from the true value of the population parameter
Robocalls
A phone call conducted by an autodialer and using a recorded voice message system
interviewer bias
A response bias that occurs because the presence of the interviewer influences respondents' answers.
mail survey
A self-administered questionnaire sent to respondents through the mail.
Internet survey
A self-administered survey administered using a Web-based questionnaire.
drop-off method
A survey method that requires the interviewer to travel to the respondent's location to drop off questionnaires that will be picked up later.
1. Know what a survey is and how it can provide insight into explaining human behavior.
A survey represents a way of describing public opinion by collecting primary data through com-municating directly with individual sampling units. Surveys provide a snapshot at a given point in time. More precisely, this is a sample survey because the respondents' opinions presumably represent a sample of the larger target population's opinion. Members of the sample are known as respondents. Surveys gather information to assess consumer knowledge and awareness of products, brands, or issues and to measure consumer attitudes, feelings, and behaviors. Additionally, surveys describe consumer characteristics, including purchasing patterns, brand usage, and descriptive characteristics including demographics and lifestyle. Surveys provide a quick, efficient, and accurate means of assessing information about a population. Students often confuse the term survey and questionnaire. A questionnaire is a tool that can be used in implementing a survey
CATI
Acronym for computer-assisted telephone interviews where a computer routine automatically selects numbers from a sampling frame and schedules calls and callbacks
sample selection error
An administrative error caused by improper sample design or sampling procedure execution
administrative error
An error caused by the improper administration or execution of the research task
3. Summarize the ways researchers gather information through personal interviews.
An interactive survey approach facilitates two-way communication where the respondent and the interviewer truly have a personal dialog. A face-to-face personal interview typifies this approach, but other media, including mobile phones and landline phones, allow two-way communication. Face-to-face interviews can be conducted door-to-door, although this mode is used less and less these days. Mall intercepts provide another alternative for personal interviews. They give the advantage of allowing respondents to interact with actual products or marketing stimuli. Landline telephone interviews are still widely used when a representative sample becomes a priority. Mobile phone surveys have potential, but legal restrictions like the Telephone Consumer Protection Act (TCPA) make using them more difficult and expensive than landline surveys
Callbacks
Attempts to try and contact those sample members missed in the initial attempt
social desirability bias
Bias in responses caused by respondents' desire, either conscious or unconscious, to gain prestige or appear in a different social role.
Noninteractive Survey Approaches
Communication approach by which respondents give answers to static questions that does not allow a two-way or dynamic dialog
interactive survey approaches
Communication that allows spontaneous two-way interaction between the interviewer and the respondent.
Sampling error
Error arising because of inadequacies of the actual respondents to represent the population of interest
systematic error
Error resulting from some imperfect aspect of the research design that causes respondent error or from a mistake in the execution of the research
item nonresponse
Failure of a respondent to provide an answer to a survey question.
crowdsourcing
Inviting many, many people to participate (by opting in) in a project via the Internet and/or social networks so that even a small percentage of completer can generate a large sample.
personal interview
Interactive face-to-face communication in which an interviewer asks a respondent to answer questions.
cover letter
Letter that accompanies a questionnaire to induce the reader to complete and return the questionnaire.
Respondents
People who answer an interviewer's questions verbally or provide answers to written questions through any media delivery (paper or electronic).
Refusals
People who are unwilling to participate in a research project
door-to-door interviews
Personal interviews conducted at respondents' doorsteps in an effort to increase the participation rate in the survey
mall intercept interview
Personal interviews conducted in a shopping center or similar public area.
5. Appreciate the importance of pretesting questionnaires.
Pretesting a questionnaire is a useful way to discover problems while they can still be corrected. Pretests may involve screening the questionnaire with other research professionals and/or conducting a trial run with a relatively small set of respondents. Despite their obvious value, researchers too often move forward without adequately pretesting survey instruments and sampling frames.
6. Describe ethical issues that arise in survey research.
Researchers must protect the public from misrepresentation and exploitation. This obligation includes honesty about the purpose of a research project and protection of subjects' right to refuse to participate or to answer particular questions. Researchers also should protect the confidentiality of participants and record responses honestly. If a survey cannot be administered in a way that prohibits any unique identification of respondents, researchers should not promise anonymity. Lastly, as technology evolves, researchers should be mindful of ways that good ethics can be breeched in sometimes subtle ways, including adding volumes of spam and breeches of confidentialit
nonresponse error
The statistical differences between a survey that includes only those who responded and a perfect survey that would also include those who failed to respond.
Nonrespondents
Sample members who are mistakenly not contacted or who refuse to provide input in the research.
pretesting
Screening procedure that involves a trial run with a group of respondents to iron out fundamental problems in the survey design.
4. Know the advantages and disadvantages of conducting surveys using self-administered questionnaires.
Self-administered questionnaires provide less interactivity than personal inter-views but provide increased efficiency. Self-administered surveys can be administered through snail mail-delivered paper questionnaires or e-mail and Internet-based survey approaches. They typi-cally are less expensive than personal interviews although gathering representative data generally is expensive through any means. Self-administered questionnaires also can provide for faster data collection. The structured response, though, provides little flexibility to stray beyond the questions written on the survey. Internet-based surveys display equal validity to standard mail or telephone interviews. Text-message surveys can be useful for very short questionnaires including only 2 or 3 items and few response points.
e-mail surveys
Survey requests distributed through electronic mail.
self-administered questionnaires
Surveys in which the respon-dent takes the responsibility for reading and answering the questions without having them stated orally by an interviewer
central location interviewing
Telephone interviews conducted from a central location, allowing firms to hire a staff of professional interviewers and to supervise and control the quality of interviewing more effectively.
acquiescence bias
Tendency of a respondent to maintain a consistent response style often tending to try to go along and agree with the view-point of a survey.
mixed-mode survey
Term used to refer to a survey approach that uses more than one survey medium to reach potential respondents.
response rate
The number of questionnaires returned and completed divided by the number of sample members provided a chance to participate in the survey
click-through response rate
The portion of potential respondents exposed to a hyperlink to a survey who actually click through to view the questionnaire.
interviewer cheating
The practice of filling in fake answers or falsifying questionnaires while working as an interviewer
2. Identify sources of error in survey research.
Two major forms of error are common in survey research.The first, sampling error is inadequacy of respondents to represent a population of interest even if other survey aspects are valid. Sampling error results from random sampling error, chance variation given that a sample is some fraction of the entire population, and systematic sampling error that results from a flawed sampling frame. The second major category of error, systematic error, takes several forms. Nonresponse error is caused by sampling units that fail to respond to a survey. This type of error can be detected by comparing the demographics of the sample popula-tion with those of the target population and making a special effort to contact underrepresented groups. In addition, response bias occurs when a response to a questionnaire is falsified or misrepresented, either intentionally or inadvertently. Administrative error also contributes to nonsampling, systematic error. Administrative error represents a flaw in the execution of the survey or sample plan. Exhibit 7.1 summarizes the sources of error
random digit dialing
Use of telephone exchanges and random numbers to develop a sample of respondents in a landline phone survey.
population parameter
refers to some true value of a phenomenon within a population