Marketing Research Exam 2

Intentional Interviewer Errors

- Cheating: violating the sampling plan, simple random -> convenience sampling - Leading: suggesting answers, do you see?, don't you see?

Types of Observation

- Direct versus indirect - Overt versus covert - Structured versus unstructured - Human versus mechanical - In situ versus invented

Intentional Respondent Errors

- Falsehoolds - Non-response: almost 50% and increasing

Choice of Survey Methods

- How much time? - How much money? - What type of respondent interaction is required? - What is the incidence rate? - Are there any cultural and/or infrastructure considerations?

Key Survey Methods

- In-home interview - Mall-intercept - In-office interview - Telephone interview (CATI) - Online survey - Mail survey - Drop-off survey

Projective Techniques

- Indirect form of questioning - Word Association - Sentence Completion - Picture test - Cartoon/balloon test - Third-person technique - Role playing

Advantages of Observational Data

- Insight into actual, not reported, behaviors : covert - no chance for recall error, no survey to respondents - better accuracy and less cost : mechanical

Questionnaire Components

- Introduction - Screening questions - Warm-up questions - Transition statements and questions - Complicated and difficult to answer questions - Classification and demographic questions

Wording Error

- Leading - Loaded - Double-barreled - Overstated

Unintentional Respondent Errors

- Misunderstanding/guessing - Attention loss/fatigue - Distractions

Qualitative Research

- Non-numerical data - a small number of respondents - in-depth analysis of what people say and do - observation, in-depth interview, focus group, and projective techniques

Unintentional Interviewer Errors

- Personal characteristics - Fatigue

Projective Technique Cons

- Require highly-trained interviewers - Skilled interpreters are also required to analyze the responses - Tends to be expensive

Projection Technique Pros

- They may elicit responses that subjects would be unwilling or unable to give - Helpful when the issues to be addressed are personal, sensitive, or subject to strong social norms

Appropriate Conditions for the Use of Observation

- behaviors which occur in short time intervals - behaviors which occur in public settings - behaviors which consumers can't accurately recall : faulty recall

Focus Group Pros

- generates fresh ideas -allows clients to observe their participants - may be directed at understanding a wide variety of issues - allows fairly easy access to special respondent groups

Quantitative Research

- numerical information - a large number of respondents - statistically reliable and projectable - survey, experiment

In-Depth Interview

- private, face-to-face conversation (interviewer and informant) - useful when subject matter is confidential and extensive, detailed probing is required - laddering - product characteristics lead to user characteristics

Focus Group Cons

- representativeness of participants - interpretation is sometimes difficult - high cost per participant

Limitations of Observational Data

- small number of subjects - inability to pry beneath

Sample Size: TV/Radio/Print Advertising

200-300 per each commercial or ad tested

Sample Size: Customer Satisfaction

300-500 people

Sample Size: New Product/Service Test

300-500 people

Halo Effect

A general feeling about a store or brand that can bias a respondent's impression on its specific properties.

Cartoon/Balloon Test

A line drawing with an empty "balloon" above the head of one of the actors is provided to subjects who are instructed to write in the balloon what the actor is saying or thinking

Picture Test

A picture is provided to participants who are instructed to describe their reactions by writing a short story about the picture, useful for brochures, product packaging, and advertisements

Reliable Measure

A respondent responds in the same or very similar manner to an identical or near-identical question, consistency

Semantic Differential Scale

A specialized interval scale format that has sprung directly from the problem of translating a person's qualitative judgements into metric estimates (bipolar adjectives, measuring meaning of object, experience, person, concept)

Sample

A subset of the population that suitably represents that entire group

Systematic Sampling

A way to select a random sample from a directory or list that is much more efficient (uses less effort) than with simple random sampling, was the most prevalent type of sampling technique used.

Control Intentional Respondent Errors

Anonymity, confidentiality, third-person technique

Overt versus Covert

Awareness of Observation: - Overt: undisguised, known presence of an observer - Covert: disguised, unknown presence of an observer - preferred method but ethical dilemma, debriefing observers afterwards

Loaded Question

Buried in its wording are elements of a sneaky presupposition, or it might make reference to universal beliefs or rules of behavior (should people be allowed to protect themselves from harm by using a taser in self defense?)

Measurement

Determining a description or the amount of some property of an object that is of interest to the researcher

In Situ versus Invented

Devices of Recording: - In Situ: observing the behavior exactly as it happens, in-store observation - Invented: the researcher creates a situation - consumers are asked to make a video as they try out a new detergent

Human versus Mechanical

Devices of Recording: - Human: hand-written observation forms, hired by the researcher, the researcher - Mechanical: video-taped/machine recorded observations, lower cost, higher accuracy, events impossible for human observers to record

Planning: Timing

Early evening around 5:30-7:00 pm

Focus Group

Focused discussion of a group of participants led by a moderator, most common in qualitative research

Leading Question

Gives a strong cue or expectation as what answer to provide (aren't you, haven't you heard?)

Ordinal Mesures

Indicate relative size differences between objects (preferences, ranking)

Direct versus Indirect

Information Recency: - Direct: currently occurring behavior - Indirect: past behavior - archives, physical traces

Telephone Interview (CATI)

Interview is conducted through the phone Pros: inexpensive, quick turnaround times, good quality control Cons: restricted to telephone communication, CATI setup costs can be high

Nominal Measures

Labels and describes objects (male/female, yes/no)

Planning: Duration

Minimum of 1 hour and maximum of 2 hours

Pluralistic Research

Mix of both qualitative and quantitative research

Faulty Recall

Occurs when actions or activities are so repetitive or automatic that the observed person cannot recall specifics about the behavior under question

Planning: Group Size

Optimal size is 6-12 participants

Overstated Question

Places undue emphasis on some aspect of the topic, dramatic

Drop-off Survey

Questionnaires are left with the respondent to fill out. The administrator may return at a later time to pick up the completed questionnaire, or it may be mailed in. Pros: cost of interviewer is eliminated, appropriate for local market survey Cons: generally not appropriate for large-scale, national surveys

Mail Survey

Questionnaires are mailed to prospective respondents who are asked to fill them out and return them by mail Pros: low cost per respondent Cons: slow process, suffered from non-response and self selection, least used data collection method

Scale Measures: Interval Scale

Rating scaled for subjective properties (scales from 1-5 usually on feelings)

Word Association

Reading words to a respondent who then answers with the first word that comes to his or her mind

Purposive Sampling

Requires a judgement or "educated guess" as to who should represent the population (focus groups)

Referral Sampling

Requires respondents to provide the names of prospective respondents

Online Survey

Respondents answer a questionnaire that resides on the internet Pros: ease of creating and posting, quick turnaround time Cons: respondent must have access to internet

Indirect Form of Questioning

Respondents are asked to describe the behavior of others, in describing the behavior of others, respondents project their own motivations, beliefs, attitudes, or feelings into the situation

Likert Scale

Respondents are asked to indicate their degree of agreement or disagreement on a symmetric agree-disagree scale for each of a series of statements (flat statements)

Role Playing

Respondents are asked to pretend to be a third person and describe how they would act in a certain situation or statement, useful for sensitive questions, respondents project their own attitudes and feelings onto the third person

Sentence Completion

Respondents are given incomplete sentences and asked to complete then in their own words, better than word association

Third-Person Technique

Respondents are presented with a situation and asked how a third person (friend, colleague, or typical person) would respond to that situation, useful for sensitive questions, respondents project their own feeling and attitudes onto the third person

Structured versus Unstructured

Restriction on Observation: - Structured: predetermine what you are going to observe - Unstructured: monitor all behavior in the episode under study

Sample vs. Census

Sample is cheaper and quicker, but less accurate since they are not asking everyone

Convenience Sampling

Samples drawn at the convenience of the interviewer (friends, family)

Probability Samples

Samples in which members of the population have a known chance of being selected into the sample

Non-probability Samples

Samples where the chances of selecting members from the population into the sample are unknown

Scale Measures: Ratio Scale

Scales where a true zero origin exists ( # of purchases, money spent, miles traveled)

Planning: Participants

Selected based on their suitability and ability to provide information, screener/screening questionnaire

Control Unintentional Interviewer Errors

Selection and training, taking breaks

Stratified Sampling

Separates the population into different subgroups and then samples all of these subgroups

Mall-intercept Interview

Shoppers in a mall are approached and asked to take part in the survey. Questions may be asked in the mall or in the mall-intercept company's facilities located in the mall Pros: fast and convenient Cons: only mall participants are surveyed

General Rules of Focus Groups

Simple, broad questions to complex, specific questions

Quota Sampling

Specified percentages of the total sample for various types of individuals to be interviewed

Valid Measure

The degree to which a respondent is truthful and accurate in his or her responses

Population

The entire group under study as specified by the objectives of the research project

What were the differences between the female only and male only focus groups?

The females talked a lot more and talked a lot more with each other with going off of other people's answers and laughing and also a lot more people participated while the males weren't as open and the same people gave responses and that group who did respond was smaller than the group who didn't respond

In-home Interview

The interviewer conducts that interview in the respondent's home. Appointments may be made ahead by telephone. Pros: conducted in privacy of respondent's home Cons: high cost per interview

In-office Interview

The interviewer makes an appointment with business executives or managers to conduct the interview at the respondent's place of work Pros: useful for interviewing busy managers and executives Cons: incurs high costs, long waits, and cancellations

Cluster Sampling

The population is divided into subgroups, called "clusters", each of which could represent the entire population.

Simple Random Sampling

The probability of being selected into the sample is equal for all members of the population

Self-selection Bias

Those who do respond to the surveys are probably different from those who do not fill out the questionnaire and return it; non-representative sample of the general population

Double-barreled Question

Two different questions posed in one question (were you satisfied with the restaurants food and service?)

Control Unintentional Respondent Errors

Using existing scales, pretesting and revisiting new scales, reversal of scale endpoints (semantic differential scales), prompters

Control Intentional Interviewer Errors

Validation

Indicate how a focus group moderator should handle each of the following cases: a) a participant is loud and dominates the conversation; b) a participant is obviously suffering from a cold and goes into a coughing fit every few minutes; c) two participants who, it turns out, are acquaintances persist in a private conversation about their children; and d) the only minority representative participant in the focus group loss uncomfortable with the group and fails to make any comments.

a) Ask others by name to respond before the offensive person can, tell the person to let others have a say b) Make sure the person has a glass of water handy, excuse the person to go outside until the coughing spell subsides c) Separate the two by placing them at opposite ends of the table, ask them to postpone their chatting until the break d) Making eye contact, smiling and nodding at the person, asking him or her direct questions

Discuss the feasibility of each type of survey mode for each of the following cases: a. Faberge wants to test a new fragrance called "Lime Brut." b. Kelly Services needs to determine how many businesses expect to hire temporary secretaries for those who go on vacation in the summer c. The Britannica Online for Kids requires information on the degree to which parents of elementary school-aged children see encyclopedias as worth-while purchases for their children d. AT&T is considering a television screen phone system and wants to know people's reaction to it.

a) Mall-intercept interview: works and reasonable in cost, Computer-assisted telephone interview: cannot use smell, Online survey: cannot use smell, Mail survey: works but low response rate b) Mall-intercept interview: incidence rate too low, Computer-assisted telephone interview: works but not economical unless national survey, Online survey: works if there is a list of individuals at businesses to contact to take part, Mail survey: works but response rate will be low c) Mall-intercept interview: appropriate and low in cost, Computer-assisted telephone interview: works unless examples and materials must be viewed by respondent, Online survey: works best with an online panel, but could work if there were a list of qualified respondents to contact via e-mail, Mail survey: could work with proper incentives to increase response rate d) Mall-intercept interview: appropriate assuming mall intercept company has space to set up equipment and allow respondents to view and/or use it, Computer-assisted telephone interview: would work only as a "concept" test, Online survey: would work if graphics and even video can be embedded in an online survey, Mail survey: would work only as a "concept" test but subject to nonresponse

Honda USA is interested in learning what its 550 U.S. dealers think about a new service program Honda provided to the dealers at the beginning of last year. Honda USA wants to know if the dealers are using the program and, if so, what they like and dislike about the program. Honda USA does not want to survey all 550 dealers but wants to ensure that the results are representative of all the dealers. a) What sampling plan should be used? b) Why?

a) Simple random sampling b) Simple random sampling is used when we have either a small population or a sample frame that in available in electronic format, the population is 550 dealers, and this is a small population; Honda USA certainly has an electronic list of the dealers, for example, an Excel spreadsheet of the dealers.

A researcher has the task of estimating how many units of a new, revolutionary photocopy machine (it does not require ink cartridges and is guaranteed not to jam) will be purchased by business firms in Cleveland, Ohio for the upcoming annual sales forecast. She is going to ask about their likelihood of purchasing the new device, and for those "very likely" to purchase, she wants respondents to estimate how many machines their company will buy. She has data that will allow her to divide the companies into small, medium, and large firms based on number of employees at the Cleveland office. a) What sampling plan should be used? b) Why?

a) Stratified sampling b) Stratified sampling is used when there are different subgroups in the population, the subgroups in the population are small, medium, and large firms, and these three subgroups differ in size and consequently differ in their demand for photocopy machines,

Applebee's Restaurants has spent several thousand dollars advertising the restaurant during the last 2 years. The company wishes to get some information about what effect the advertising has had and decides to measure TOMA (Top of Mind Awareness). A TOMA "score" for such a restaurant is the ranking a firm has as a result of asking a representative sample of consumers in the service area to "name a non-fast-food restaurant." The restaurant named by the most persons has the #1 TOMA score and so on. It is important that Applebee's management conduct the TOMA survey with a representative sample in the metropolitan area. a) What sampling plan should be used? b) Why?

a) Systematic sampling b) Systematic sampling is used when the population is likely to be all consumer households living in a metropolitan area, the population therefore is all consumer households in the metropolitan area. The closest sample frame for this population is the telephone directory of the metropolitan area, and systematic sampling is used to select phone numbers from the directory for sampling purpose.

Mike, the owner of the convenience store Mike's Market, is concerned about low sales. He reads in a marketing textbook that the image of a store often has an impact on its ability to attract its target market. He contacts the All-Right Research Company and commissions it to conduct a study that will shape his store's image. You are charged with the responsibility of developing the store image part of the questionnaire. Design a semantic differential scale that will measure the relevant aspects of Mike's Market's image. In your work on this scale, you must do the following: a) brainstorm the properties to be measured, b) determine the appropriate bipolar adjectives, c) decide on the number of scale points, and d) indicate how the scale controls for the halo effect

a) prices, location, variety of merchandise, friendliness, value b) Rate Mike's Market: High prices _ _ Low Prices, Inconvenient location _ _ Convenient location, Much merchandise variety _ _Little merchandise variety, Unfriendly salespeople _ _ Friendly salespeople, Poor value for the price _ _ Good value for the price c) A 7-point scale is used d) The "merchandise variety" row is flipped to get rid of the halo effect.

The Moderator's Guide

not the same as a questionnaire, moderator is allowed to add, drop, skip, and modify any questions based on the group discussion