Chapter 8: Primary Data Collection (Surveys) Flashcards
Types of surveys
- Door-to-door interviews
- Executive interviews
- Mall-intercept interviews
- Telephone interviews
- Self-administered questionnaires
- Mail surveys
Door-to-door interviews
Interviews conducted face to face with consumers in their homes
Advantages of door-to-door interviews
- Immediate feedback from respondent
- Ability to explain complicated tasks
- Ability to use special questionnaire techniques that require visual contact to improve data quality
- Ability to show the respondent product concepts and other stimuli for evaluation
- Participant is at ease in a familiar environment
Disadvantages of door-to-door interviews
- Cost of paying interview is high because of travel, mileage, survey time
- Ever-rising refusal rates
Executive interviews
The industrial equivalent of door-to-door interviewing
Advantages of executive interviews
- Immediate feedback from respondent
- Ability to explain complicated tasks
- Ability to use special questionnaire techniques that require visual contact to improve data quality
- Ability to show the respondent product concepts and other stimuli for evaluation
- Participant is at ease in a familiar environment
SAME AS DOOR TO DOOR
Disadvantages of executive interviews
- Expensive
- Interview must go to a particular place at the appointed time
- Requires highly skilled interviewer
Mall-intercept interviews
Interviews conducted by intercepting mall shoppers (or shoppers in other high-traffic locations) and interviewing them face to face
Advantages of mall-intercept interviews
- Relatively simple
- Less expensive than door-to-door
- Many of the same advantages as door-to-door
Disadvantages of mall-intercept interviews
- Sample does not represent target audience
- Attract certain type of people
- Ever-rising refusal rates
- Not the most comfortable environment
Types of telephone interviews
- Central-location telephone interviews
2. Computer-assisted telephone interviews (CATI)
Random-digit sampling/dialing
Instead of drawing a sample from the phone book or other directory, researchers use telephone numbers generated via a random-number procedure
Central-location telephone interviews
Interviews conducted by calling respondents from a centrally located marketing research facility.
Advantages of central-location telephone interviews
- Interview process is monitored normally through equipment
2. Interviewers’ working hours are controlled
Computer-assisted telephone interviews (CATI)
Central-location telephone interviews in which interviewers enter respondents’ answers directly into a computer
Advantages of CATI
- More control over direction of questions
- Computer helps customize questionnaires
- Computer tabulations can be run at any point in the study
- Management may find early reporting of survey results useful
Self-administered questionnaires
Questionnaires filled out by respondents with no interviewer present
Advantages of self-administered questionnaires
- No one present cant benefit data because it eliminates source of bias
- Used when researcher has access to a captive audience
Disadvantages of self-administered questionnaires
No one is present to explain things
Type of mail surveys
- Ad-hoc mail surveys
2. Mail panels
Ad-hoc mail surveys
Questionnaires sent to selected names and addresses without prior contact by the researcher, sometimes called one-shot mail surveys
Mail panels
Pre-contacted and pre-screened participants who are periodically sent questionnaires
Advantages of mail panels
- No interviewers to recruit, train, monitor, and pay
- Study can be sent out and administered from a single location
- Hard-to-reach respondents can be surveyed
- Convenient, efficient, and inexpensive
Disadvantages of mail panels
- No one there to probe responses to open-ended questions
- Number of questions and quantity of obtainable information is more limited in mail surveys than in surveys involving interviewers
Two category errors
- Sampling/random error
2. Systematic/human/bias error
Random error
An error that results from chance variation, the difference between the sample value and the true value of the population mean
Systematic error
Error that results from problems or flaws in the execution of the research design, sometimes called non-sampling error
Types of sample design error
- Frame error
- Population specification error
- Selection error
Types of measurement error
- Surrogate information error
- Interviewer error
- Measurement instrument bias
- Processing error
- Non-response bias
- Response bias
Sample design error
A systematic error that results from an error in the sample design or sampling procedures
Measurement error
A systematic error that results from a variation between the information being sought and what is actually obtained by the measurement process
Frame error
The error resulting from an inaccurate or incomplete sampling frame
Population specification error
An error that results from incorrectly defining the population or universe from which a sample is chosen
Selection error
An error that results from incomplete or improper sample selection procedures or not following appropriate procedures
Surrogate information error
An error that results from a discrepancy between the information needed to solve a problem and that sought by the researcher
Interviewer error/bias
An error that results from interviewers influencing - consciously or unconsciously - the answers of the respondent (caused by selection and/or training of interviewer)
Measurement instrument bias
An error that results from the design of the questionnaire or measurement instrument, also known as questionnaire bias
Processing error
An error that results from the incorrect transfer of information from a survey document to a computer
Non-response bias
An error that results from a systematic difference between those who do and those who do not respond to a measurement instrument (the higher the response rate, the less possible the impact of non-response bias)
Refusal rate
The percentage of people contact who refused to participate in a survey
Response bias
An error that results from the tendency of people to answer a question in a certain way through either deliberate falsification or unconscious misrepresentation
