Research Proposal

1

MARK977: Research for Marketing Decisions

Dr. Thomas Lee Trimester 1, 2018

2

Survey and Causal Research

WEEK 4 READING: CHAPTERS 5 & 6

2

Learning objectives

1. Discuss and classify survey methods available to marketing researchers, and describe the various telephone, personal, mail, and electronic interviewing methods.

2. Compare the different methods, and evaluate which is best suited for a particular research project.

3. Explain how survey response rates can be improved.

MARK977 Research for Marketing Decisions T1 20183

MARK977 Research for Marketing Decisions T1 20184

3

The survey method

• The survey method of obtaining information is based on questioning respondents.

• Questions regarding behaviour, intentions, attitudes, awareness, motivations, and demographic and lifestyle characteristics all lend themselves to survey research.

• A typical survey involves structured questioning. A formal questionnaire is prepared and the questions are asked in a prearranged order (e.g., general questions first, more specific questions next, demographic questions last)

• Most questions are fixed alternative questions, which require respondent to select from a predetermined set of responses.

MARK977 Research for Marketing Decisions T1 20185

Advantages of survey research • Ease. Questionnaires are

relatively easy to administer.

• Reliability. Using fixed- response (multiple-choice) questions reduces variability in the results that may be caused by differences in interviewers and enhances reliability of the responses.

• Simplicity. It also simplifies coding, analysis, and interpretation of data.

MARK977 Research for Marketing Decisions T1 20186

4

Disadvantages of survey research

• Respondents may be unable (e.g., question or alternative is not applicable or relevant) or unwilling (e.g., if information requested is sensitive or personal) to provide the desired information.

• Structured data collection involving a questionnaire with fixed-response choices may result in loss of validity for certain types of data, such as beliefs and feelings.

• Properly wording questions is not easy.

MARK977 Research for Marketing Decisions T1 20187

The survey approach is by far the most common method of primary data collection in marketing research.

Classification of survey methods

MARK977 Research for Marketing Decisions T1 20188

5

Traditional telephone interviews • Traditional telephone interviews involve phoning a

sample of respondents and asking them a series of questions.

• The interviewer uses a paper questionnaire and records the responses with a pencil.

• Telephone interviews are generally conducted from centrally located research facilities.

• Field service supervisors can closely monitor the telephone conversations.

– Helps to control interviewer bias that results from variation in the way questions are asked and responses recorded

MARK977 Research for Marketing Decisions T1 20189

Computer-assisted telephone interviewing • Computer-assisted telephone interviewing (CATI) uses a

computerized questionnaire administered to respondents over the telephone.

• The interviewer sits in front of a computer screen wearing a mini- headset.

– Computer screen replaces paper-and-pencil questionnaires, headset substitutes for a telephone

• When contact is made, the interviewer reads the questions posed on the screen and records the respondent's answers directly into the computer.

• Because responses are entered directly into the computer, interim and update reports can be compiled instantaneously, as the data are being collected.

• Uses a software that has built-in branching logic, which will skip questions that are not applicable or will probe for more detail when warranted.

MARK977 Research for Marketing Decisions T1 201810

6

Advantages and disadvantages of telephone interviewing • Advantages

– Interviews can be completed quickly because travel time associated with personal interviews is eliminated

– Easy to reach respondents if sampling frame is drawn correctly – Supervisors can monitor interviews without the interviewer or

respondent being aware – Response rate is high (easy, quick, cheap = more attempts) – Not very expensive

• Disadvantages – Questioning restricted to spoken words and respondent has no access

to questionnaire – Cannot use physical stimuli and ask complex questions

• This limits applicability for new product and advertising research – Lack of face-to-face interaction – Respondent can escape by hanging up the phone – Less tolerance for lengthy interviews

MARK977 Research for Marketing Decisions T1 201811

Personal in-home interviews

• In personal in-home interviews, respondents are interviewed face-to-face in their homes.

• The interviewer's task is to contact the respondents, ask the questions, and record the responses.

• In recent years, the use of personal in-home interviews has declined.

MARK977 Research for Marketing Decisions T1 201812

In-home interviews are still used, particularly by syndicated firms that need to collect large amounts of data.

7

Pros and cons of in-home interviewing • Advantages

– Can ask complex questions since interviewer can clarify – Can use physical stimuli and permit demonstration – Easy to reach respondents if location is specified and sampling

procedure defined (e.g., every 5th home) – Can collect large quantities of data since respondents are in their own

homes and more willing to participate – Good response rate if respondent is notified in advance

• Disadvantages – Interviewer supervision and control is difficult because interviews are

not undertaken same place same time – High social desirability and interviewer bias

• Interviewers can influence answers by facial expression or way of asking questions

– Very expensive MARK977 Research for Marketing Decisions T1 201813

Mall-intercept personal interviews • In mall-intercept interviews, respondents are intercepted

(approached and interviewed) in shopping in malls.

• The process involves

– Stopping the shoppers

– Screening them for appropriateness (screening questions to determine eligibility)

– Administering the survey on the spot or inviting them to a research facility located in the mall to complete the interview.

• While not representative of the population in general, shopping mall customers do constitute a major share of the market for many products.

MARK977 Research for Marketing Decisions T1 201814

8

Pros and cons of mall intercepts

• Advantages – Can ask complex questions because of face to face contact – Can provide physical stimuli (e.g., product display or demo,

see KFC case on p. 148) • Disadvantages

– May lead to social desirability and interviewer bias due to the face to face contact between interviewer and respondent (see in-home interviewing)

– Moderate quantities of data as people are generally in a hurry while shopping • Low response rate? • Lack of control of the environment in which the data are

being collected? E.g., online focus groups and distractions?

MARK977 Research for Marketing Decisions T1 201815

Computer-assisted personal interviewing (CAPI) • In computer-assisted personal interviewing (CAPI) the

respondent sits in front of a computer terminal and answers a questionnaire on the screen by using the keyboard or a mouse.

• CAPI, such as that using touch screens, is becoming more popular around the world.

• Help screens and courteous error messages are provided.

• The colorful screens and on- and off-screen stimuli add to the respondent's interest and involvement in the task.

• This method has been classified as a personal interview technique since an interviewer is usually present to serve as a host and to guide the respondent as needed.

• This approach is used in shopping malls, preceded by the intercept and screening process described earlier.

MARK977 Research for Marketing Decisions T1 201816

9

Pros and cons of CAPI

• Advantages – Can ask complex questions – Has built-in branching logic to perform skip patters and logic checks

(e.g., if no then skip to Q8) – Interviewer bias is reduced as computer administers interview – Permits the use of physical stimuli (e.g., pictures) – Can yield high response rate if highly interactive and respondent

effort and stress are reduced • Disadvantages

– High social desirability – Moderate quantities of data if deployed in busy malls and trade shows – High cost

MARK977 Research for Marketing Decisions T1 201817

Mail interviews • A typical mail interview package consists of the

outgoing envelope, cover letter, questionnaire, postage-paid return envelope, and possibly an incentive.

• Those individuals motivated to do so complete and return the questionnaire through the mail.

• There is no verbal interaction between the researcher and the respondent.

• Individuals are selected for cold surveys (respondents not contacted beforehand) through mailing lists the client maintains internally or has purchased commercially.

• The type of envelope, the cover letter, the length of the questionnaire, and the incentive (if one is offered) all affect response rates.

MARK977 Research for Marketing Decisions T1 201818

10

Pros and cons of mail surveys

• Advantages – An economical and efficient way to reach respondents – Low social desirability and no interviewer bias as there is no personal

contact – Moderate quantities of data for cold mail surveys, large quantities for

mail panels • Disadvantages

– Lack of control over the interviewing process • Who answers the questionnaire, how they answer it, how quickly they

return it – Low response speed – No control over the data collection environment – Non-response bias due to low response rate

• Characteristics of those who respond may differ from the characteristics of those who do not respond

MARK977 Research for Marketing Decisions T1 201819

Email surveys

• If the addresses are known, the e-mail survey can simply be sent electronically to respondents included in the sample.

• Respondents key in their answers and send an e-mail reply.

• Typically, a computer program is used to prepare the questionnaire and email address list, and to prepare the data for analysis.

• Respondent anonymity is difficult to maintain because a reply to an email message includes the sender’s address.

• E-mail surveys are especially suited to projects where the email lists are readily available, such as surveys of employees, institutional buyers, and consumers who frequently contact the organization via e-mail (e.g., frequent fliers of an airline).

MARK977 Research for Marketing Decisions T1 201820

11

Internet surveys • An Internet survey is a questionnaire

posted on a Web site that is self administered by the respondent.

• The questions are displayed on the screen and the respondents provide answers by clicking an icon, keying in an answer, or highlighting a phrase.

• Web survey systems are available for constructing and posting Internet surveys (e.g., Survey Monkey, Qualtrics)

• As compared to email surveys, Internet surveys offer more flexibility, greater interactivity, personalization, automatic skip patterns and visual appeal.

MARK977 Research for Marketing Decisions T1 201821

Pros and cons of electronic methods • Advantages

– Cost effective (low incremental cost of reaching additional respondents) and quick (esp. internet survey which also permits data collected to be analysed speedily)

– Accommodates much larger samples – Can contact hard-to-reach respondents due to the convenience (time, place)

available to the respondent – Can be personalised to increase interactivity (esp. internet survey which also

allows for skipping patterns) – Can automatically generate and send reminders to respondents who have not

responded • Disadvantages

– Only people with email or internet access are included – Repeated attempts if no controls are in place – Email surveys may be considered to be a form of spam – Only simple questions can be asked – No control over data collection environment – Low response rate

MARK977 Research for Marketing Decisions T1 201822

12

Criteria for selecting a survey method

1. If complex and diverse questions have to be asked, one of the personal

methods (in-home, mall intercept, or CAPI) is preferable.

2. From the perspective of the use of physical stimuli, personal methods (in-

home, mall intercept, or CAPI) are preferable.

3. If sample control is an issue (i.e., who answers the questionnaire), cold mail

(but not mail panel), fax, and electronic methods might not be appropriate.

4. Control of the data collection environment favors the use of central location

(mall intercept and CAPI) interviewing.

5. Need for high quantity of data favours the use of in-home and mail panels,

and makes the use of telephone interviewing inappropriate (does not allow

for lengthy interviews).

MARK977 Research for Marketing Decisions T1 201823

Criteria for selecting a survey method

6. Low response rates make the use of cold mail and electronic

methods disadvantageous.

7. If social desirability is an issue, mail, mail-panel, fax, and Internet

surveys are best.

8. If interviewer bias is an issue, the use of mail (cold and panels), fax,

and electronic interviewing (e-mail and Internet) is favoured.

9. Speed favours Internet, e-mail, telephone, and fax methods.

10. Costs favour cold mail, fax, electronic (e-mail and Internet), mail

panels, telephone, mall intercept, CAPI, and in-home methods, in

that order (most favorable to least favorable).

MARK977 Research for Marketing Decisions T1 201824

13

Improving response rates

MARK977 Research for Marketing Decisions T1 201825

Improving survey response rates • Prior notification consists of sending a letter or e-mail, or

making a telephone call to potential respondents, thereby notifying them of the imminent mail, telephone, personal, or electronic survey.

– It increases response rate because it reduces surprise and uncertainty and creates a more cooperative atmosphere.

• Offering monetary as well as nonmonetary incentives to potential respondents can increase response rates.

– The prepaid incentive is included with the survey or questionnaire, and all potential respondents get it whether they respond or not (e.g., pens, pencils, $1).

– The promised incentive is sent to only those respondents who complete the survey (e.g., gift cards, summary of findings).

MARK977 Research for Marketing Decisions T1 201826

14

Improving survey response rates

• Follow-up, or contacting the non-respondents periodically after the initial contact, is particularly effective in decreasing refusals in mail surveys. Follow-up can be done by telephone, mail, e-mail, or personal contact.

• Personalization, or sending letters addressed to specific individuals, is effective in increasing response rates.

MARK977 Research for Marketing Decisions T1 201827

Multiple methods to improve survey response rates should be used. For example, prior notification, incentives, and follow-up can all be used in a survey.

Survey method considerations

• The feasibility and popularity of the different interviewing methods vary across countries, for example: – Access to telephones in the US, Canada vs. developing

countries – Personal interaction may be preferred in some countries – Literacy rate and reliability of postal systems may vary

between developed and developing countries – Email and internet access may be limited in some developing

countries, hence electronic surveys may not be appropriate – Non-monetary incentives (e.g., gifts) may be more appropriate

in Japan than cash

MARK977 Research for Marketing Decisions T1 201828

15

MARK977 Research for Marketing Decisions T1 201829

Learning objectives

1. Explain and classify the different observation methods used by marketing researchers and describe personal observation and mechanical observation.

2. Describe the relative advantages and disadvantages of observational methods.

MARK977 Research for Marketing Decisions T1 201830

16

Observation methods

Observation involves recording the behavioural patterns of people as well as data on objects and events in a systematic manner to obtain information about the phenomenon of interest. • The observer does not question or communicate with the

people being observed. • Information can be recorded as the events occur or from

records of past events.

MARK977 Research for Marketing Decisions T1 201831

Personal observation • In personal observation, a researcher observes actual

behaviour as it occurs (see Heinz example on p. 148). • The observer does not attempt to manipulate the phenomenon being observed

but merely records what takes place. • For example, a researcher might record traffic counts and observe traffic flows

in a department store. • Advantages:

– Highly flexible because the observer can record a wide variety of phenomena – Suitable for use in natural settings (see Heinz example)

• Disadvantages: – Observation form is not used and observer records phenomenon after

completing the observation, leading to observation and recording biases – Results are limited to surface indicators from which researcher must make

inferences (underlying motivation unknown) – Data interpretation is highly subjective, leading to analysis bias

MARK977 Research for Marketing Decisions T1 201832

17

Mechanical observation Involves the use of a mechanical device to record behaviour

Do not require respondents' direct participation

 the Nielsen peoplemeter (see Research in Practice p. 167)

 turnstiles that record the number of people entering or leaving a building.

 on-site cameras (still, motion picture, or video)

 optical scanners in supermarkets

 Number of webpage visits, time spent, links accessed, cookies

Do require respondent involvement

 eye-tracking monitors, pupilometers

 Specialised equipment to monitor heart and breathing rates, skin

temperature, other physiological changes

Advantage – low observation bias (behaviour recorded mechanically)

Disadvantage – devices can be intrusive and expensive

MARK977 Research for Marketing Decisions T1 201833

Relative advantages of observation

• They permit measurement of actual behavior rather than reports of intended or preferred behavior.

• There is no reporting bias, and potential bias caused by the interviewer and the interviewing process is eliminated or reduced.

• Certain types of data can be collected only by observation.

• If the observed phenomenon occurs frequently or is of short duration, observational methods may be cheaper and faster than survey methods.

MARK977 Research for Marketing Decisions T1 201834

18

Relative disadvantages of observation

• The reasons for the observed behavior may not be determined, since little is known about the underlying motives, beliefs, attitudes, and preferences (i.e., why it is occurring).

• Selective perception (bias in the researcher's perception) can bias the data.

• Observational data are often time-consuming and expensive, and it is difficult to observe certain forms of behaviour.

• In some cases, the use of observational methods may be unethical, as in observing people without their knowledge or consent.

MARK977 Research for Marketing Decisions T1 201835

Experimentation as Conclusive Research

MARK977 Research for Marketing Decisions T1 201836

19

Conditions for causality • Concomitant variation is the extent to which a cause, X,

and an effect, Y, occur together or vary together in the way predicted by the hypothesis under consideration (e.g., in- store service and sales).

• The time order of occurrence condition states that the causing event must occur either before or simultaneously with the effect; it cannot occur afterwards (e.g., in-store service [before] and sales [after]). IV and DV need to be clearly identified.

• The absence of other possible causal factors means that the factor or variable being investigated should be the only possible causal explanation. Control for other possible causes such as pricing, distribution intensity, etc.

MARK977 Research for Marketing Decisions T1 201837

Role of evidence • Evidence of concomitant variation, time order of occurrence of

variables, and elimination of other possible causal factors, even if combined, still does not demonstrate conclusively that a causal relationship exists. Think of the notion of correlation where a cause can also be an effect (e.g., attitude and loyalty).

• However, if all the evidence is strong and consistent, it may be reasonable to conclude that there is a causal relationship (e.g., test and re-test over multiple studies).

• Accumulated evidence from several investigations increases our confidence that there is a causal relationship

MARK977 Research for Marketing Decisions T1 201838

We can never prove causality. At best we can infer that a causal relationship exists.

20

What is an experiment?

MARK977 Research for Marketing Decisions T1 201839

What is experimentation?

• Technique used in causal research to establish cause-and- effect relationships

• Field experiment – Measurement of behaviour, attitudes or perceptions in the

environment in which they occur (i.e., the natural setting) – See Rite Aid example, p. 180 where the experiment

examined the effectiveness of in-store radio ads in inducing point-of-purchase (POP) buys

• Laboratory experiment – Conducted in an artificial environment – See additional reading

MARK977 Research for Marketing Decisions T1 201840

21

Definitions and concepts

• Independent variables are variables or alternatives that are manipulated and whose effects are measured and compared, e.g., in the Rite Aid example, in-store radio ads were manipulated as either present or absent

• Test units are individuals, organizations, or other entities whose response to the independent variables or treatments is being examined, e.g., consumers or stores.

• Dependent variables are the variables which measure the effect of the independent variables on the test units, e.g., sales, profits, and market shares.

MARK977 Research for Marketing Decisions T1 201841

Definitions and concepts

• Extraneous variables are all variables other than the independent variables that affect the response of the test units, e.g., control variables such as store size, store location, and brand preference

• Random assignment to experimental and control groups – Randomly assign respondents to different conditions of the

manipulated independent variable – Experimental groups (e.g., helpful vs. unhelpful service employees,

high vs. low positive emotions) – Control groups are not exposed to the independent variable

manipulation (e.g., in the Rite Aid example, the experimental group was exposed to radio advertising while the control group received no radio advertising) • Control groups provide a point of comparison

MARK977 Research for Marketing Decisions T1 201842

22

Experimental design

An experimental design is a set of procedures specifying

 the test units and how these units are to be divided into homogeneous subsamples;

 what independent variables or treatments are to be manipulated and how;

 what dependent variables are to be measured; and

 how the extraneous variables are to be controlled.

MARK977 Research for Marketing Decisions T1 201843