question

Define marketing research

answer

- the function that links the consumer, the customer and the public to the marketer through information - used to identify and define market opportunities and problems - generate, refine and evaluate marketing performance and strategies - monitor marketing performance and make adjustments - improve understanding of marketing as a process - understand customers - FUNDAMENTAL to making business and marketing decisions, without research you are operating on assumptions and best guesses

question

Why is it important to define the marketing research problem appropriately?

answer

- problem definition is the most critical step in market research project - waste of time, money and effort if the problem is misunderstand or ill-defined - incorrect problem definition leads to irrelevant findings that lead to bias managerial decision making - have to understand the nature of the problem and the decision which management faces - only when the problem has been clearly defined can research be designed and conducted

question

What are the common types of errors encountered in defining a marketing research problem? What can be done to reduce the incidence of such errors?

answer

- defining the research problem too broadly makes it not actionable and does not provide clear guidelines for subsequent steps in the project - defining the research problem too narrowly - if too narrow it eliminates interesting options - how to avoid these: broad statement (provides perspective on the problem and acts as a safeguard against being too narrow) and specific components (focus on the key aspects of the problem and provide clear guidelines on how to proceed further, reducing likeilhood of being too broad)

question

Exploratory research

answer

- provides novel insights and understanding, clarifies issues - information needed is defined only loosely - research is flexible and unstructured - sample = small and non representative - analysis of primary data is qualitative - followed by further exploratory or conclusive research

question

Conclusive research

answer

- tests specific hypothesis and examine relationships - information needed is clearly defined - research process is formal and structured - sample is large and representative - data analysis is quantitative

question

Cross sectional design

answer

- at one moment in time - involves collection of information from any given sample of population elements only once - most common type of descriptive research - could be single or multiple

question

Longitudinal design

answer

- over time - type of research involving repeated measurements of the same variables from the same sample - unique benefit: detecting change

question

Why is it important to minimize total error rather than any particular source of error?

answer

It is important to minimize total error to rather than focusing on one because attempting to lessen one particular source often creates an even bigger error elsewhere

question

Example of minimizing total error:

answer

a researcher might try to minimize sampling error by using a bigger sample. While this could help, it creates more room for non sampling error such as interview error. non sampling errors are usually worse and harder to account for

question

Secondary data

answer

data is collected for purpose other than the problem at hand low cost, short collection time easily accessible can help identify, clarify of refine the problem might provide answers to a research problem might suggest research design for primary data collection can alert researcher to potential problems provides background info enhancing research credibility

question

Primary data

answer

data that is originated by a researcher for the SPECIFIC PURPOSE of addressing the problem at hand collected for the problem at hand involved and consuming collection process relatively high cost

question

Criteria for evaluating secondary data

answer

Who/what/what/when/how/are Who gathered the data? What was the purpose of the study? What information was collected? When was the information collected? How was the information collected? Are the data accurate?

question

Qualitative research

answer

gain understanding of the underlying reasons and motivations sample is a small number of non representative cases data collection = unstructured data analysis = non statistical

question

Quantitative research

answer

to quantify the data and generalize the results from the sample to the population of interest large number of representative cases data collection: structured data analysis: statistical recommend a final course of action

question

Depth interview

answer

detailed probing thoughts, beliefs, attitudes and feelings one on one structured, direct personal interview discussion of confidential, sensitive and embarrassing topics strong social norms exist and respondents might be easily swayed by the group complicated behavior professional interviewing (getting a large group at the same time is difficult) product consumption is experiential and sensory

question

Relevant factors for evaluating which survey method is best suited to a particular research project?

answer

task, situation, respondent

question

Task factors

answer

diversity of questions use of physical stimuli sample control quantity of data response rate

question

Situation factors

answer

data collection environment field force (interviewers/supervisors) interviewer bias speed (time to administer sample) cost

question

Respondent factors

answer

perceived anonymity social desirability sensitive information low incidence rate respondent control

question

requirements for inferring a CAUSAL RELATIONSHIP between 2 variables

answer

concomitant variation time order of occurrence of variables elimination of other possible causal factors

question

Concomitant variation

answer

two variables occur together, the extent to which a cause and an effect occur together or vary together in the way predicted by the hypothesis

question

Time order occurrence of variables

answer

cause has to happy before the effect, or with the effect, cant be afterwards

question

Elimination of other possible causal factors

answer

eliminate as many cases as possible, absence of other possible causal factors - the factor or variable being investigated should be the only possible causal explanation

question

Internal validity

answer

whether the manipulation of the independent variables or treatments caused the observed effects on dependent variables control of EXTRANEOUS VARIABLES is a necessary condition for establishing internal validity

question

External validity

answer

whether the cause and effect relationships found in the experiment can be generalized are findings generalizable to the outside population to what specific populations, settings, time, independent/dependent variables can the results be projected?

question

Steps to implement a post-test only group design

answer

Sample of respondents selected at random, sample is split randomly with half of the subject forming the experiment group and the other half form the control group, only respondents in the experiment group would be exposed to the variable, both groups would be tested to see how the variable affected did not affect the experiment group

question

Symbol of post-test only group

answer

EG: R X 01 CG: R 02

question

Primary scales of measurement (INOR)

answer

interval, nominal, ordinal, ratio,

question

Interval

answer

scales that have characteristics of ordinal + equal intervals between points equal distances on the scale represent equal values in the characteristic being measured permits comparison between 2 objects location of zero point is not fixed in statistics you use arithmetic mean, standard deviation, correlation, etc. used to measure attitudes, motivations, emotions

question

Nominal

answer

partition data into mutually exclusive and collectively exhaustive categories numbers are labels/tags identifying and classifying objects numbers don't reflect the amount of the characteristics possessed by the objects statistics is limited based on frequency counts, percentage of objectives in each category used for DEMOGRAPHICS (gender, income, occupation)

question

Ordinal

answer

maintains labeling characteristics of nominal scales and has ability to order data can determine whether an object has more or less of a characteristic than some other object (but not specifically how much more or less) Numbers dont indicate absolute quantities ordinal numbers don't imply equal interval between the numbers Example: measure order of consumer preferences ranking 5 department stores in order of preferences (45 percent of respondents choose Target)

question

Ratio

answer

Have the characteristics of interval + meaningful zero point

question

Difference between nominal and ordinal scale

answer

ordinal scales have the same characteristics of nominal scales BUT have the ability to order data, can determine whether an object has more or less of a characteristic

question

Advantages of a ratio scale over an interval scale?

answer

Ratio scales - all statistical techniques can be applied, has an absolute zero point Can measure sales, costs, market share and number of customers on a ratio scale Knowing scale type informs us what stat analysis to perform in data analysis have characteristics of interval + absolute zero point

question

Likert scale

answer

respondents identify degree of agreement of disagreement with a series of statements respondents readily understand how to use the scale (mail, phone, personal interview, online survey) takes longer to complete because respondents have to read each statement analysis can be conducted on an item by item basis or total score reverse scores are needed for negative statements

question

Example of Likert Scale

answer

"Sarah sells a high quality product" Indicate your degree of agreement or disagreement Strongly disagree --> strongly agree

question

True score model

answer

true score theory maintains that every measurement in an additive composite of two components: true ability of the respondent on that measure and random error

question

What is reliability?

answer

Is the measure consistent? If we measured personality today and tomorrow how close would the two results be? It is necessary but not sufficient condition for validity Example of a type of reliability: measurement reliability

question

What is validity?

answer

Are we measuring what we think were measuring? Do our personality scale actually measure personality?

question

Different types of validity

answer

face, content, criterion, construct

question

Face validity

answer

degree to which a measurement seems to measure what it is supposed to measure on its face, do the items seem to represent the construct

question

Example of face validity

answer

dressing up for a job interview

question

Content validity

answer

How well the content of a scale represents the measurement task efforts including literature review, focus groups, expert panels to determine content validity

question

Example of content validity

answer

of a math professor: educational degree, research experience, published papers, teaching experiences

question

Criterion validity

answer

Reflects whether a scale performs as expected in relation to other variables selected as meaningful criteria

question

Example:

answer

criterion of a math professor: lets both take a college level math test, person who is a real math professor is more likely to perform better than the person who is not

question

Construct validity

answer

extent to what the researcher was trying to measure was actually measured how do your results relate to the theory?

question

What is the relationship between validity and reliability?

answer

if the measure is perfectly valid than it is also perfectly reliable. if there is no case of random or systematic error if the measure is unreliable it cant be perfectly valid, since at minimum there is random error present if a measure is perfectly reliable it may or may not be perfectly valid because systematic may still be present

question

How can the model of administration affect questionnaire design?

answer

interviewer administered - can be lengthy and complex - visual aids can be incorporated in a face to face interview self administered - questions must be short and simple - instructions must be thorough computer assisted - can incorporate multi media stimuli - complex skip patterns - customization - randomization of questions

question

Reasons respondents are unable to answer the question being asked?

answer

are not informed on the topic of interest market researchers should consider using filter questions or an "i dont know" option many common experiences are difficult to remember, consumers dramatically overestimate usage when estimating consumption levels unable to articulate certain types of respondents (give aids like descriptions to help them)

question

Reasons respondents are unwilling to answer specific questions?

answer

effort required of the respondent - most respondents are unwilling to devote a lot of effort to provide information legitimate purpose - respondents object to questions that do not seem to service a legit purpose sensitive information - unwilling to disclose accurately sensitive information because this may cause embarrassent or threaten their self image

question

What conditions would a sample be preferable to a census?

answer

if you want selected members of the population to be sampled a properly designed sample provides reliable information to infer about the population without actually having to ask everyone (unlike a census)

question

What are incidence rates?

answer

number of respondents that qualify for a study based on certain screening criteria vary depending on who we are targeting to study

question

How do probability sampling techniques differ from non probability techniques?

answer

Probability sampling = conclusive research, high variability in the population, favorable statistical considerations Non-probability sampling - sample is not representative of any definable target population, generalizations cannot be made, statistical inference from sample to the population of interest is problematic, low cost, easy implementation

question

What is the least expensive and least time consuming of all sampling techniques? Limitations of this technique?

answer

Non probability sampling - low cost and easy implementations Limitations - chance of being selected into the sample isnt precisely known, generalizations cannot be made, statistical inference from sample to the population of interest is problematic

question

Stratified sampling

answer

Two step process 1. divide the original population into mutually exclusive and exhaustive subsets 2. elements of each stratum are then randomly selected can acquire information about the whole population and individual strata can lead to increased precision information necessary to properly stratify the sample isnt usually available

question

Describe the cluster sampling procedure

answer

three step process: 1. Divide the target population into mutually exclusive and collectively exhaustive clusters (neighborhoods) 2. select a random sample of clusters based on probability sampling 3. for each selected cluster, either include all elements or a random sample of elements

question

Key distinction between cluster and stratified sampling

answer

Cluster is a sample of clusters chosen and the objective is to increase sampling efficiency to decrease costs Stratified sampling are all subpopulations are used, and objective is to increase precision

Essay Questions – Market Research – Flashcards

Unlock all answers in this set

Haven't found what you were looking for?

Search for samples, answers to your questions and flashcards