McDaniel & Gates – Marketing Research, 9th Edition Instructor’s Manual
CHAPTER 6
Traditional Survey Research
LEARNING OBJECTIVES
1. To understand the reasons for the popularity of survey research.
3. To learn about the types of surveys.
4. To gain insight into the factors that determines the choice of particular survey methods.
KEY TERMS
Random error or random sampling error
Chance variation
Systematic error, or bias
Sample design error
Sampling frame
Frame error
Population specification error
Selection error
Nonresponse bias
Refusal rate
Response bias
Door-to-door interviews
Executive interviews
Mall-intercept interviews
Central-location telephone interviews
Computer-assisted telephone interviews
CHAPTER SCAN
This chapter explores the basics of survey research. In understanding survey research, it is
important to understand the types of errors within it. There is sampling error, systematic error,
and measurement error. Of these, systematic error and measurement error can be affected by the
researcher. The different types of surveys, there appropriate use and the advantages and
disadvantages of each type are discussed. The different types of surveys are door-to-door
McDaniel & Gates – Marketing Research, 9th Edition Instructor’s Manual
CHAPTER OUTLINE
1. Popularity of Survey Research
2. Types of Error in Survey Research
I. Sampling error
A. Random Sampling Error
B. Chance Variation
3. Types of Surveys
I. Door-to-Door Interviews
A. Door-to-Door Interviews
B. Advantages
C. Disadvantages
McDaniel & Gates – Marketing Research, 9th Edition Instructor’s Manual
D. In-Store Research
IV. Telephone Interviews
A. Most Popular Form of Surveys
B. Advantages
V. Self-administered Questionnaires
A. Self-administered Questionnaire
B. Advantages
VI. Mail Surveys
A. Two General Types of Mail Surveys
B. Mail Survey Problems
4. Determination of the Survey Method
I. Factors/Major Considerations That Affect the Choice of a Survey Method
A Sampling Precision
B. Budget
C. Requirements for Respondent Reactions
D. Quality of Data
E. Length of Questionnaire
F. Incidence Rate
G. Structure of the Questionnaire
1) Time Strapped
5. The Marketing Research Interviewer
McDaniel & Gates – Marketing Research, 9th Edition Instructor’s Manual
6. Summary
CHAPTER SUMMARY
1. POPULARITY OF SURVEY RESEARCH
I. Survey Research
A. Popularity–surveys have the highest rate of usage when compared to other means of
collecting data. There are 70 million people interviewed each year–some 126 million Americans
have been interviewed at some point in their lives
B. Reasons
1. The need to know why–why people do or do not do something
2. TYPES OF ERRORS IN SURVEY RESEARCH
See Exhibit 6.1 Types of Survey Error (p 153)
I. Sampling Error
A. Random Sampling Error–error that results from chance variation
B. Chance Variation
2. Error cannot be eliminated, but increasing sample size can reduce it
II. Systematic Error
A. Definition of Systematic Error and/or Bias–results from mistakes or problems in the
research design or from flaws in the execution of the sample design.
1. Exists in the results of a sample if those results show a consistent tendency to vary in one
2. All sources of error except for those created by the random sampling process
1. Sample design error–results from a problem in the sample design or sample procedures.
Types of sample design errors are as follows:
2. Measurement Error–systematic error that results from a variation between the information
being sought and what is actually obtained by the measurement process. Various types of error
may be caused by numerous deficiencies in the measurement process. These errors include:
1) Response rate of 5 percent or less are expected from mail surveys
2) Nonresponse error occurs when the following happens
a) A person cannot be reached at a particular time
1. Refusal up 60 percent from 52 percent in 1992
g. Response Bias–results from the tendency of people to answer a question incorrectly through
either deliberate falsification or unconscious misrepresentation
2. Unconscious misrepresentation–respondent is legitimately trying to be truthful and accurate
but gives an inaccurate response
See Exhibit 6.2 Types of Errors and Strategies for Minimizing Errors (p 157)
3. TYPES OF SURVEYS
1. Personal
3. Ability to explain complicated tasks
5. Ability to show the respondent product concepts and other stimuli for evaluation
6. Respondent is at ease in a familiar, comfortable, secure environment
C. Disadvantages–began a steep decline in the early 1970s and have virtually disappeared from
the U.S. Marketing Research scene
2. Ever-rising refusal rates
See Global Research: Conducting Marketing Research in China (p158)
Interviews in China, in consumer and B2B research alike, has been predominantly conducted
using face-to-face interviewing. In 2000, 90 percent of all research interviews were face-to-face,
however this proportion has since decreased to approximately 60 percent (by comparison,
McDaniel & Gates – Marketing Research, 9th Edition Instructor’s Manual
information on a one-to-one basis rather than in groups likely due to culture.
Due to the relatively low Internet penetration in China, Chinese agencies tend to lag behind their
Western counterparts in their use of online data-collection techniques. Currently, online surveys
II. Executive interviews
A. Executive interviews–industrial equivalent of door-to-door interviewing
1. Businesspeople are interviewed at their offices.
3. Requires a highly skilled interviewers
4. Advantages and disadvantages–essentially the same advantages and disadvantages as door-to–
door interviews
III. Mall-Intercept Interviews
A. Mall-intercept Interviews–shoppers in malls are intercepted and interviewed.
B. Advantages:
2. Interviewers spend more time interviewing and less hunting for someone to interview
4. Mall-intercept has many of the advantages associated with door-to-door interviews in that the
respondents can try test products on the spot
C. Disadvantages
1. Not be representative of the population–malls draw shopper from a relatively small local area
3. Not always viewed as a comfortable place to conduct an interview
4. Not all malls permit marketing research interviewing
D. In-Store research–at the point-of-purchase. Get to the consumer as he or she reaches for the
product on the shelf
McDaniel & Gates – Marketing Research, 9th Edition Instructor’s Manual
IV. Telephone Interviews
A. Most Popular Form of Surveys–up to 1990 were the most popular single form of survey
B. Advantages
2. Produces a high-quality sample
3. Predictive Dialing–telephone numbers are generated via a random-number procedure
a. reaches people with unlisted numbers and those who have moved
C. Disadvantages
2. Inability to physically show anything to consumer
4. Must be shorter and less in-depth thus limits the quantity and types of information that can be
obtained
6. Potential for personality bias–people who agree in a telephone interview may be different than
those that do not.
D. Call Center Telephone Interviews–interviewers make calls from a company facility to reach
and interview respondents. Nearly all telephone interviews are conducted from this type of
environment today.
1. The main reason for the growing prominence of this method is control of the process through
supervisors.
3. Interviewer’s working hours are controlled
4. Computer-assisted telephone interviews (CATI)
a. Interviewer uses the computer and computer designed survey instrument to interview the
McDaniel & Gates – Marketing Research, 9th Edition Instructor’s Manual
d. The CATI tabulations can be run at any point in the study. Information can be used to change
questions or suggest further delving into certain behaviors
See Practicing Marketing Research: Presenting a Compelling Reason for Telephone Survey
Participation (p 162)
Your phone rings and you are asked to participate in a survey.
What would you do?
2. Make sure to say why you’re calling
4. Offer an incentive
6. Identify the client, if possible
8. Remind them that their opinions are valuable
Discussion Questions:
1. Can you think of any other ways to get people to participate?
2. Do you usually agree to be interviewed in telephone surveys? Why or why not?
V. Self-Administered Questionnaires
A. Self-Administered Questionnaire–filled out by respondents with no interviewer present
B. Advantages
2. Answers tend to be more honest than when a human interviewer is present
C. Disadvantages
2. Inability to ‘probe’ for a more definitive answer
See Exhibit 6.3 Customer Survey (p 165)
D. Kiosk-based Computer Interviewing
1. Have multimedia, touch-screen computers contained in freestanding cabinets
McDaniel & Gates – Marketing Research, 9th Edition Instructor’s Manual
3. Advantages–tends to be less expensive, people tend to give more honest answers than to a
human interviewer, and internal control is higher because the survey is preprogrammed
VI. Mail Surveys
A. Two General Types of Mail Survey:
1. Ad hoc mail surveys (one-shot mail surveys)–sent to selected individuals with no prior
contact. The sample is used only for the single project
2. Mail panels
a. Precontacted and prescreened participants who are periodically sent questionnaires and are
usually offered a gratuity.
d. Longitudinal study–the same respondents are resampled over time
B. Mail Survey Problems–both suffer from not having an interviewer present
C. High Rate of Nonresponse to Ad hoc Mail Surveys–high rate of nonresponse and attendant
systematic error–not a problem if everyone has an equal probability of not responding.
1. Types of people with a greater probability of not responding are
a. those with more education
D. Strategies To Enhance Response Rate–a question that must be asked “Is the cost of the
particular strategy worth the increased response rate generated?”
See Exhibit 6.4 Tactics Employed to Increase Mail Survey Response Rates (p 166)
See Exhibit 6.5 Non-Internet Forms of Survey Research (p 167)
4. DETERMINATION OF THE SURVEY METHOD
McDaniel & Gates – Marketing Research, 9th Edition Instructor’s Manual
See Exhibit 6.6 Factors That Determine the Selection of a Particular Survey Method (p
167)
I. Factors That Affect the Choice of a Survey Method
A. Major Considerations in the Selection of a Survey Method
1. Sampling Precision–required level of sampling precision is an important factor in
determining which survey method is appropriate in a given situation
2. Budget–has a strong influence on the survey method used
4. Quality of Data–measured in terms of validity and reliability
a. Validity–provides an accurate reading of whatever the researcher is trying to measure
b. Reliability–provides the consistency with which a measure produces the same results with the
same or comparable populations
See Exhibit 6.7 Strengths and Weaknesses of Selected Data-Collection Methods in Terms of
Quality of Data Produced (p 169)
5. Length of Questionnaire
1) Important determinant of the appropriate survey method to use
3) Need to match the survey technique to the length of the questionnaire
6. Incidence Rate
a. Incidence Rate–percentage of people or households in the general population that would
qualifications to be sampled
7. Structure of the questionnaire
1) Structure—to the extent to which the questionnaire follows a set sequence or order, has a
2) Unstructured–deviates from the set patterns mentioned above and it would require a face-to–
face interview
8. Time available to Complete the Survey
a. Time Strapped
5. MARKETING RESEARCH INTERVIEWER
I. Interviewers
A. Requirements
1. Marketing research interviewing–done under the direct supervision of a field service firms
3. Interviewers have only a minimum of training. There is a high failure rate among first-time
1. Interviewers–main interface with the consumers and are a vital link to consumer cooperation
2. Suggestions for developing and strengthening interviewers’ consumer interaction skills
a. Good training programs that cover ways to establish consumer rapport
6. SUMMARY
QUESTIONS FOR REVIEW AND CRITICAL THINKING
1. The owner of a hardware store in Eureka, California, is interested in determining the
demographic characteristics of people who shop at his store versus those of people who
shop at competing stores. He also wants to know what his image is relative to the
competition. He would like to have the information within three weeks and is working on a
limited budget. Which survey method would you recommend? Why?
2. Discuss the statement: “A mall intercept interview is representative only of people who
shop in that particular mall. Therefore, only surveys that relate to shopping patterns of
consumers within that mall should be conducted in a mall intercept interview.”
If all of the persons shopping at a mall were very similar, this statement would be true. However,
shopping malls are located in urban areas in densely populated regions. One needs only to visit a
3. A colleague is arguing that the best way to conduct a study of attitudes toward city
government in your community is through a mail survey because it is cheapest method.
How would you respond to your colleague? If time were not a critical factor in your
decision, would your response change? Why?
This method could be the best, although a mail survey is not always the cheapest.
Nonrespondents and the high cost of postage can drive up the cost of conducting an adequate
4. Discuss the various sources of sample design error and give examples of each.
The first type of sampling error is random error. This error occurs because of chance variation in
the sample. To reduce the influence of random error, a larger sample should be employed. The
larger the sample, other things being equal, the more it represents the population from which it
came. For example, perhaps you interviewed fifty people in a population of 50,000 on the merits
McDaniel & Gates – Marketing Research, 9th Edition Instructor’s Manual
chance, because the sample was so small. Given a larger sample, the results may be more closely
aligned with expectations.
The second type of sampling error is systematic error which includes three types of biases. The
first is frame error, which results because of using an incomplete or inaccurate sampling frame.
5. Why is it important to consider measurement error in survey research? Why is this
typically not discussed in professional market research reports?
Measurement error occurs when there is a variation between the information being sought and
the information obtained by the measurement process. Measurement error is very important in
6. What types of error might be associated with the following situations?
McDaniel & Gates – Marketing Research, 9th Edition Instructor’s Manual
Sample frame error.
b. Interviewing respondents only between 8:00 a.m. and 5:00 p.m. on features they
would like to see in a new condominium development.
Sample selection error.
c. Asking people if they have visited the public library in the past two months.
Response bias.
d. Asking people how many tubes of toothpaste they used in the past year.
Response bias.
e. Telling interviewers they can probe using any particular example they wish to
make up.
Interviewer error.
REAL LIFE RESEARCH
Case 6.1 – Yes, Teens Love Their Mobile Phones! (p 173)
Key Points
• Cell phone texting has become the preferred channel of basic communication between
teens and their friends, and cell calling is a close second.
• Some 75 percent of 12- to 17-year olds own cell phones, up from 45 percent in 2004.
Those phones have become indispensable tools in teen communication patterns. Fully 72
Questions
1. How might Verizon use this information?
2. This study was conducted by the Pew Research Center. What would you want to ask the
Pew researchers about the data and the methods used to collect the data before purchasing
the complete report?
3. What are the various survey methods that could have been used to collect this data?
What are the advantages and disadvantages of each?
Case 6.2 – The NFL is King! (p 175)
Key Points
• Results of a nationwide survey conducted online by Harris Interactive, among 1,961 U.S.
adults, of whom 1,402 follow at least one sport indicate the following:
o Professional football continues to surge in popularity as one-third (33 percent— up
under $50,000 (40 percent),
o among Generation X—those aged 28 to 39—(30 percent). Those with a
postgraduate education are least likely (23 percent) to call professional football
their favorite sport.
McDaniel & Gates – Marketing Research, 9th Edition Instructor’s Manual
o Baseball does best among Hispanics (20 percent) and Echo Boomers—those aged
18 to 27—(21 percent). African Americans are least likely to say baseball is their
favorite sport (6 percent).
Questions
1. This survey was conducted online, which is covered in detail in Chapter 7. Suggest three
ways that these data might have been gathered and the advantages and disadvantages of
each.
Answers may vary (see Exhibit 6.5, p 186)
1. Mall-intercept Interviews–shoppers in malls are intercepted and interviewed.
Advantages:
• Interviewers spend more time interviewing and less hunting for someone to interview
• No substantial travel time and mileage expenses
Disadvantages
• Not be representative of the population–malls draw shoppers from a relatively small local
area
2. Telephone Interviews
Advantages
• Include low costs
• Produce a high-quality sample
McDaniel & Gates – Marketing Research, 9th Edition Instructor’s Manual
• Random-digit dialing techniques–telephone numbers are generated via a random-
number procedure that reaches people with unlisted numbers and those who have moved
Disadvantages
• 12.8 percent of U.S. households cannot be reached because they have a cell phone only
and no landline. Cell phone-only adults tend to be a different demographic.
• Inability to physically show anything to consumer
3. Self-Administered Questionnaires–filled out by respondents with no interviewer present
Advantages:
• Eliminates on source of bias
• Answers tend to be more honest than when a human interviewer is present
Disadvantages:
2. Assume that we are interested in a detailed understanding of why GenXers are so
enthralled with pro football. How might we gather the data?
Answers may vary. Interviews are the best way to get greater detail especially because they
3. What are four types of errors that could be present in this survey? What can be done to
minimize each?
