1-1
OVERVIEW OF
MARKETING RESEARCH 450.305
1-2
Myths about MR ITS ABOUT COLLECTING DATA! No, its about transforming data into information to aid
business decisions.
ITS ALL ABOUT STATISTICS! No, a lot of important research is conducted without even
involving numbers!
ITS ALL ABOUT TELEMARKETING! Definitely not! MR does not involve selling!
ITS ALL ABOUT THOSE ANNOYING PHONE SURVEYS! No, that is just one or many techniques used!
1-3
Used to identify and define market opportunities and problems
Generate, refine, and evaluate marketing action
Monitor marketing performance
Improve understanding of marketing as a process
MR provides information to…
1-4
The MR Context
Where does MR fit within business operations?Essentially, MR is directly related to the marketing practices of a companyFeeds into the marketing plan – product, pricing, promotion and distribution strategiesE.g. product development and optimisationE.g., promotional value propositions
1-5
MR Suppliers & Services
LIMITED SERVICE
BrandedProducts
and Services
DataAnalysisServices
AnalyticalServices
Coding and Data Entry Services
Field Services
FULL SERVICE
SyndicateServices
StandardizedServices
Customized
Services
InternetServices
RESEARCHSUPPLIERS EXTERNALINTERNAL
1-6
EthicsMR involves 4 stakeholders:
(1) marketing researchers, (2) the clients, (3) the respondents, and (4) the public.
An ethical issue or dilemma arises when the interests of these stakeholders are in conflict and when one or more of the stakeholders are lacking in their responsibilities” (Malhotra, p 24)Code of ethics – MRSA
1-7
1-8
Marketing Research Determine the problem
Step 1:
Step 1: Determine the problem
PHASE I:Establish the research parameters
Definition of the decision problem Determine if problem is a symptom or a true problem, then precisely
specify the decision problem
Specification of the research question The most critical step in the marketing research process Reformulate in scientific terms and restate the initial variables (how,
what, where, when or why) Definition of the research objective
Provide the guidelines for determining which other marketing research steps must be undertaken
Evaluate the information benefits Assess the expected benefits to be derived
Step 1:
1-9
Management Decision Problem Vs. Marketing Research Problem
Management Decision ProblemShould a new product be introduced?
Should the advertising campaign be changed?
Should the price of the brand be increased?
Marketing Research Problem
To determine consumer preferences & purchase intentions for the proposed new product.
To determine the effectiveness of the current advertising campaign.
To determine the price elasticity of demand and the impact on sales and profits of various levels of price changes.
1-10
Task 2: Specify the Research Question
Once marketing research problem is identified – we need to develop specific research questions
How, when, where, who and why statements Exploratory applications
Or develop hypotheses Statements about possible relationships between two or more
market factors Includes the precise variables or constructs to be measured Generally based on already existing data – used to confirm!!
1-11
Marketing Research Assess the data needs
Step 2: Assess Data Needs
PHASE I:Establish the research parameters
Determine the data needs Determine the data needed to execute the research Assess what types of information sources would be most
appropriate Determine whether the data can be collected at all Evaluate data availability and quality
Can the specific research question be addressed with existing data? Secondary data
Does the question require new, firsthand data?Primary data
Step 2:
1-12
Uses of Secondary Data Save time and costs if relevant – e.g., case studies Often the starting point Identify the problem Better define the problem Develop an approach to the problem Formulate an appropriate research design (for example, by
identifying the key variables) Answer certain research questions and test some
hypotheses Interpret primary data more insightfully
MUST EVALUATE SECONDAR DATA – E.G., PURPOSE, ACCURACY, TIME, METHODOLOGY, ETC
1-13
Marketing Research Select the research design
Step 3: Select research design
PHASE II:Design the research
Step 3:
What is a research design?
A master plan of the methods and procedures that should be used A master plan of the methods and procedures that should be used to collect and analyse the data needed by the decision maker.to collect and analyse the data needed by the decision maker.
EXPLORATORY, DESCRIPTIVE AND CAUSAL DESIGNSEXPLORATORY, DESCRIPTIVE AND CAUSAL DESIGNS
Which research design is best?Which research design is best?Depends on the research objectives and the specific data Depends on the research objectives and the specific data requirements!requirements!
1-14
Marketing Research Select the research design
PHASE II:Design the research
Step 3:
Exploratory Descriptive Causal
Qualitative Quantitative Quantitative
Focus groups
Depth interviews
Projective techniques
Surveys
Observation
Experimental;
field vs. lab
Research design
Research method
Research technique
1-15
Marketing Research Select the research design
PHASE II:Design the research
Descriptive/causal Quantitative research methods: Conclusive, structured approach Emphasis is on measurement and quantification of numbers Surveys, observation (can be qual) and experiments (causal only)
Exploratory Qualitative research methods: Open-ended, unstructured flexible approach Emphasis on understanding Focus groups, IDIs, projective techniques
Step 3:
1-16
Marketing Research Select the research design
Step 3: Select research design
PHASE II:Design the research
Step 3:
Qualitative Research
To gain a qualitative understanding of the underlying reasons and motivations
Small number of non-representative cases
Unstructured
Non-statistical
Develop an initial understanding
Objective
Sample
Data Collection
Data Analysis
Outcome
Quantitative Research
To quantify the data and generalize the results from the sample to the population of interest
Large number of representative cases
Structured
Statistical
Recommend a final course of action
1-17
When to Use Qualitative Research Method
Interested in obtaining some preliminary insights into the motivational, emotional, attitudinal and personality factors that influence marketplace behaviours
E.g., identifying drivers/barriers of acquisition and choice of custom license plates In the process of correctly identifying a business problem or opportunity situation or
establishing information requirements
E.g., identifying issues of customer dissatisfaction in telecommunication services In the process of building theories and models to explain marketplace behaviours or
relationships between two or more marketing constructs
e.g., identifying those factors influencing brand loyalty in the shoe retail environment
Developing reliable & valid scale measurements for investigating specific market factors, consumer qualities and behavioural outcomes
E.g., important service quality or store attributes to include as items in a questionnaire Trying to determine the preliminary effectiveness of their marketing strategies on actual
marketplace behaviours
e.g., reactions to new advertising campaign or repositioning strategy. E.g Betts & Betts Betts Interested in new-product or service development or repositioning current product
images E.g., understanding attitudes and behaviour of grocery purchases and identifying interest in
buying groceries over the internet
…When decision makers or researchers are:
1-18
When to use Quantitative Research
Quantitative research is often used for the following outputs for this study:
Describing market characteristics (e.g., attitudes, usage, etc)
Relative importance of factors on some dependent variable such as satisfaction, take-up
Demand/preference estimates for existing and potential products
Demand/preference changes at various price points (price elasticity)
Identification of key target segments
Market sizing
1-19
A Classification of Qualitative Research Procedures
Malhotra, Fig. 5.2
Direct (Non disguised)
Indirect (Disguised)
Focus Groups Depth Interviews
Projective Techniques
Qualitative Research Procedures
i.e., the purpose of the project is not disguised
i.e., the purpose of the project is disguised
1-20
A Classification of Observation Methods by Mode of Administration
Observation Methods
Personal Observation
Mechanical Observation
Trace Analysis
Content Analysis
Audit
Malhotra Fig. 6.3
1-21
A Classification of Survey Methods
Traditional Telephone
Computer-Assisted Telephone Interviewing
Mail Interview
Mail Panel
Malhotra, Fig. 6.1
In-Home Mall Intercept
CAPI and Executive
E-mail Internet
Survey Methods
Telephone Personal Mail Electronic
1-22
Types of Errors in Survey Research Methods
Sampling errorSampling error
Error associated with the sampled data results due to some form of natural random chance or random fluctuations in the data estimates.The statistically measured difference between the actual sampled results and the estimated true population results.
Error associated with the sampled data results due to some form of natural random chance or random fluctuations in the data estimates.The statistically measured difference between the actual sampled results and the estimated true population results.
Random sampling errors versus Non-sampling errors
Random sampling errors versus Non-sampling errors
Non-sampling or systematic error
Non-sampling or systematic error
All errors that enter survey research design that are not related to the sampling method or sample size.
All errors that enter survey research design that are not related to the sampling method or sample size.
1-23
A Classification of Experimental Designs
Pre-experimental
One-Shot Case Study
One Group Pretest-Posttest
Static Group
True Experiment
alPretest-Posttest Control Group
Posttest: Only Control Group
Solomon Four-Group
Quasi Experimental
Time Series
Multiple Time Series
Statistical
Randomized Blocks
Latin Square
Factorial Design
Figure 7.1
Experimental Designs
1-24
A Classification of Experimental Designs
Pre-experimental
One-Shot Case Study
One Group Pretest-Posttest
Static Group
True Experiment
alPretest-Posttest Control Group
Posttest: Only Control Group
Solomon Four-Group
Quasi Experimental
Time Series
Multiple Time Series
Statistical
Randomized Blocks
Latin Square
Factorial Design
Figure 7.1
Experimental Designs
1-25
Marketing Research Determine the sampling plan
Step 4: Determine samplingPHASE II:Design the research
If secondary data is relevant, no sampling is necessary If primary data is sought, sampling is important Consideration must be given to:
The defined target population, a subset of the population selected for investigation, using either:
A census—includes every element A sample—a randomly selected sub-group of elements
If a sample is used, then the researcher must consider:
Probability sampling—a known, non-zero chance of selection Non-probability sampling—no known sampling error
Step 4:
1-26
Classification of Sampling TechniquesMalhotra 2004, Fig. 11.2
Sampling Techniques
NonprobabilitySampling
Techniques
ProbabilitySampling
Techniques
ConvenienceSampling
JudgmentalSampling
QuotaSampling
SnowballSampling
SystematicSampling
StratifiedSampling
ClusterSampling
Other SamplingTechniques
Simple RandomSampling
1-27
Determining Appropriate Sample Sizes
Three factors play a role in determining the ‘right’ sample size: The variability of the population
characteristic. The level of confidence desired in the
estimate. The degree of precision desired.
1-28
Marketing Research Determine the measurement issues
Step 5: Determine measurementPHASE II:Design the research
Determine the dimensions of the factors being investigated and measure the variables The second most important step in the research process Key aspects include:
Operationalise – determine dimensions and then elements What level of information is needed from a variable?
scales required, rate or rank/compare? Validity and reliability required – face? Construct?
Content? Questionnaire design
Step 5:
1-29
Levels of Scales There are four levels of scales of interest to
a research team: Nominal Ordinal Interval Ratio
These scales differ in terms of 4 properties: Assignment/naming Order Distance Origin
1-30
Principles of Questionnaire Design
Content & purpose of question
SequencingWording & language
Type & form of question
Biases in question Classification
dataWording
Administration TestingQuestionnaire
Ch 9Principles of measurement
General Appearance
Cavana et al 2001
1-31
Marketing Research Design the data collection forms
Step 6: Design data collectionPHASE II:Design the research
Determine whether to use questioning or observation techniques Questioning allows the researcher to collect a wider
array of data Pertains to current behaviour and state of mind Questionnaires are the preferred collection method
Observation Pertains to observable or measurable actions Professional observers or mechanical devices are used
Step 6:
1-32
Marketing Research Prepare the data
Step 7: Prepare data
PHASE III:Execute the research
Perform procedural activities that occur before data analysis: Code the data Editing Enter the data Clean the data
Step 7:
1-33
Marketing Research Analyse the data
Step 8: Analyse dataPHASE III:Execute the research
Select the data analysis technique most suited to the task Refer to your objectives Differing procedures allow the researcher to:
Tests of differences Tests of associations Refer to summary sheets for when to use each
technique and interpretation of output
Step 8:
1-34
Marketing Research Transform the analysis results into information
Step 9: Communicate resultsPHASE IV:Communicate the research results
Create and communicate information Transform the results and findings into a narrative
interpretation A research report and presentation:
Integrates several pieces of the results into an understandable report The decision maker can then create an actionable plan to address
the initial decision problem The report might include:
Executive summary Introduction Problem definition and objectives Methodology, results and findings Limitations of the study
Step 9:
1-35
Example short-answer exam questions Draw a diagram which shows the tasks involved in the first stage of the marketing research process?
Task 1: Define the decision problem Task 2: Specify the research question Task 3: Establish the research objectives Task 4: Evaluate the benefits of the expected information
What is the difference between a marketing research question and a hypothesis? Provide an example of each?MR questions are statements of how, who, what, when and why, typically used in exploratory applications – e.g., What are the key factors influencing satisfaction? Hypotheses are testable and “if-then” statements about possible relationships between two or more variables/constructs – e.g., H1: the higher the service quality, the higher the satisfaction.
Provide an example of an open-ended question? Develop a close-ended question.E.g., How would you describe your experience at UWA so far? (open-ended)Overall, has your experience at UWA been positive – yes/no/don’t know response. (closed-ended)
Offer a clearly focussed problem statement in the broad area of pricingE.g., do we increase our prices? Do we decrease our prices? What is the optimum price we can set before demand drops? What is the price-elasticity of our product?
1-36
Example short-answer exam questions What is one situation when it may be more appropriate to use qualitative rather than quantitative research?
When there is a need to understand the reasons behind people’s behaviour (e.g., car choices) and little is known in the area. The findings can then be used as items in a questionnaire to quantify.
What is one difference between qualitative and quantitative research?Qualitative research relies on unstructured questioning with the human-as-an instrument, whereas quantitative research typically relies on precise measurement and structured questions.
What kind of analysis should be done when a researcher is interested in comparing male and female attitudes towards UWA and why?Independent sample t-test, because the DV is metric (assuming attitudes is measured on an interval scale) and there are two independent categorical groups (males and females). A t-test would compare the mean attitude ratings between males and females.
Long answer:
1-37
Example long-answer exam questions For the following scenarios, recommend whether you would use observation or a survey
technique? Justify your answer. For the following scenarios, recommend whether you would use qualitative or quantitative
research is more appropriate. What technique would you use and justify your answers. For the following scenarios, would you recommend a probability or non-probability sampling
technique? Justify your answer. Management wants to know whether awareness and attitude towards Nike impacts on
purchase. Interpret the analytical findings below and write down what it means. Below are the outputs of bivariate regression analysis where purchase intentions is the
dependent variable and income is the independent variable. Interpret the analytical findings below and write down what it means.
Critique the following set of questions and make suggestions for improvements.
1-38
Example long-answer exam questions For the following scenarios, recommend whether you would use observation or a survey
technique? Justify your answer. For the following scenarios, recommend whether you would use qualitative or quantitative
research is more appropriate. What technique would you use and justify your answers. For the following scenarios, would you recommend a probability or non-probability sampling
technique? Justify your answer. Management wants to know whether awareness and attitude towards Nike impacts on
purchase. Interpret the analytical findings below and write down what it means. Below are the outputs of bivariate regression analysis where purchase intentions is the
dependent variable and income is the independent variable. Interpret the analytical findings below and write down what it means.
Critique the following set of questions and make suggestions for improvements.