8/8/2019 RM_ppt1
1/18
Research MethodologyResearch MethodologyTopics
y Introduction
y Research Theory
y Research Analysis
y
Library Researchy Literature Review
y Methods & Procedures of Conducting Research
y Methodology Procedures
y Research Designs: a. Quantitative b. Qualitative
y Method of Analysis
y Results: Conclusions, Implications & Recommendations
y Writing & Communicating Research
y Cue words or Cloud Words
8/8/2019 RM_ppt1
2/18
y Some Definitions
Research is the systematic process of collecting and analyzing information to
increase our understanding of the phenomenon under study. It is the function of the
researcher to contribute to the understanding of the phenomenon and to
communicate that understanding to others.
Alternatively, research is the seeking of answers to questions and the scientific
means of solving problems. A research could be fundamental/ basic research or an
applied research.
y Research Design: A detailed plan of research indicating the methods and
procedures to be used for collecting and analyzing data on a given subject andreporting results.
Research Design includes qualitative and quantitative designs, and are used to
answer a question or test a hypothesis presented in a study.
y Research Process: The series of stages or steps involved in a research project. A
Research Process consists of
What=>How=>Where=>Who=>When=>Why
y Methodology is the procedure of conducting research composed of systematic
directions of how the research is conducted. It consists of three basic parts: 1. the
sample or subjects, 2. the instrument or prototype, and 3. the method of analysis.
8/8/2019 RM_ppt1
3/18
8/8/2019 RM_ppt1
4/18
y Demographic study/research: data of vital statistics about the population
y Ethnographic study/research: is used in examining different groups.
y Psychographic study/research: is information about the lifestyle of a population
y Normal Distribution: A distribution of a continuous random variable where the
curve has a single peak, and which is bell-shaped and symmetrical around a vertical
line drawn at the mean, which is located at the centre. The two tails of the
distribution extend indefinitely and never touch the horizontal axis.
8/8/2019 RM_ppt1
5/18
ExamplesExamples ofResearch in MarketingofResearch in MarketingAs noted, marketing research is undertaken to support a wide variety ofmarketing decisions. The table below presents a small sampling of theresearch undertaken by marketing decision area. Many of the issues listedunder Types of Research are discussed in greater detail in other parts of thePrinciples of Marketing Tutorials.
Marketing Decision Types of Research
Target Markets
sales, market size; demand for product, customer
characteristics, purchase behavior, customer satisfaction,
website traffic
Product
product development; package protection, packaging
awareness; brand name selection; brand recognition, brand
preference, product positioning
Distributiondistributor interest; assessing shipping options; online
shopping, retail store site selection
Promotion
advertising recall; advertising copy testing, sales promotion
response rates, sales force compensation, traffic studies
(outdoor advertising), public relations media placement
Pricingprice elasticity analysis, optimal price setting, discount
options
External Factorscompetitive analysis, legal environment; social and cultural
trends
Other company image, test marketing
8/8/2019 RM_ppt1
6/18
When Research is unnecessaryWhen Research is unnecessary
y When cost of undertaking is higher than the benefit
y When project attempts to collect information relating to distant past.
y When information sought is of very personal nature
y When respondents find it very difficult to communicate their emotions
and sensations
y The nature of some product with very short lifecycle is such that there is
hardly any time to conduct research
y When a firm may have an apprehension that its new product is likely to be
copied by its competitors once they come to know about it.
8/8/2019 RM_ppt1
7/18
Need for information:
1. When one is unsure about what is to be done
2. Where extreme values are involved
Characteristics of a value information:
1. Relevant
2.Available
3. Accurate
4. Current
5. Adequate
The concept of Probability- is the basis of decision making under conditions
of uncertainty. The probability indicates the likelihood of occurrence of aparticular result or event.
So, n(P) = n(E)/n(S) where n(E) is occurrence of a particular event and n(S) is
the total sample size.
8/8/2019 RM_ppt1
8/18
Measurement and ScalingMeasurement and Scaling
Measurement means assigning numbers or other
symbols to characteristics of objects according to
certain prespecified rules.
One-to-one correspondence between the numbers
and the characteristics being measured.
The rules for assigning numbers should be
standardized and applied uniformly.
Rules must not change over objects or tim
8/8/2019 RM_ppt1
9/18
Measurement and ScalingMeasurement and Scaling
Scaling involves creating a continuum upon which
measured objects are located.
Consider an attitude scale from 1 to 100. Each
respondent is assigned a number from 1 to 100, with 1
= Extremely Unfavorable, and 100 = Extremely
Favorable. Measurement is the actual assignment of a
number from 1 to 100 to each respondent. Scaling is
the process of placing the respondents on a continuum
with respect to their attitude toward departmentstores.
8/8/2019 RM_ppt1
10/18
Primary Scales of MeasurementPrimary Scales of MeasurementScale
y Nominal Numbers
Assigned
to Runners
y Ordinal RankOrderof Winners
y Interval Performance
Rating on a
0 to 10 Scale
y Ratio Time to Finish, in
Seconds
8/8/2019 RM_ppt1
11/18
A Comparison of Scaling TechniquesA Comparison of Scaling Techniques
y Comparative scales involve the direct comparison of
stimulus objects. Comparative scale data must be
interpreted in relative terms and have only ordinal or rank
order properties.
y In non comparative scales, each object is scaled
independently of the others in the stimulus set. The
resulting data are generally assumed to be interval orratio scaled.
8/8/2019 RM_ppt1
12/18
The Research Process
y Identify & formulate the problem
y Choose the research design
y Determine the information needs
y
Design data collection formsy Determine sample design & sample size
y Organize and conduct the field survey
y Analyze and interpret the collected data
y Prepare the research reporty What=>How=>Where=>Who=>When=>Why
8/8/2019 RM_ppt1
13/18
y Acomplete problem must specify
1. Sample and sampling units
2. Time & space boundaries
3. Product feature and consumer preferences
4. Specific environmental conditions
5. Hypothesis development
y Choice ofResearch Design
1. Exploratory Studies: generally based on secondary data e.g. literature search,Experience survey, Focus Group, Analysis of selected cases
2. Descriptive studies: to study characteristic of certain group e.g. sex, education level,income, occupations etc. this can be Longitudinal-Panel or cross-sectional-sample
3. Causal Studies: to study cause and effect relationship between two or morevariables. This can be done thru Natural experiments and Controlled experiments.
The main criterion of a design that it must answer the research questions andhence a formulation of a proper hypothesis. Second criterion relates to control ofindependent variables, so the subject selection should be random. Thirdcriterion is generalisability. This is more true in the case of applied research.
8/8/2019 RM_ppt1
14/18
y Determining source of Data
1. Primary Data: Collected by Survey,Observation ( Structured/unstructured,
Dis/undisguised, Setting un/natural, Direct/Indirect, Human/Mechanical),
Questionnaire (Open-ended, Dichotomous, Multiple-choice & pre test for any
ambiguity)
2. Secondary Data: Selection criteria Availability, relevance, accuracy & data
sufficiency
Advantage: Economical, Time saving, Helps to collect primary data, helps in
validating
Sources of secondary data:
i. Internal: accounting records, sales force reports, internal experts
ii. External: Govt. publication-census, annual reports, journals & bulletins;Non-govt.
publications-industry & trade associations, universities, syndicate services, consumer
research services, international publications
y Designing Data collection Forms
1. Observational method: unobtrusive & collected without the direct participation ofthe respondents
2. Survey method: i. Personal ii. Telephonic iii. By mail iv. By diary
y Determining Sampling Design & Sampling Size
1. Ad hoc or practical
2. Statistical approach
8/8/2019 RM_ppt1
15/18
y Sampling DesignCensus survey => Population
Sampling/sample survey => Sample
y Objectives of a sample Survey
1. To estimate certain population parameters
2. To test a hypothesis
y Advantage of a sample survey
1. Cheaper2. Faster
3. Easier to handle data
4. Amenable to a more detailed information
5. Quality of supervision better than census survey
y The Sampling ProcessDefine the population -> Indentify sampling frame -> Specify sampling units -> Specify
sample design -> Determine sample size -> Select the sample units -> Collect the data
from the designated sample units
8/8/2019 RM_ppt1
16/18
y Types of Sample Design
i. Probability Sampling: a sampling technique in which sampling units are selected by chance and
for which there is known, non-zero probability of selection
1. Random Sampling
2. Systematic Sampling
3. Stratified Random sampling
4. Cluster Sampling
5. Multi stage Sampling
6. Area sampling
7. Multi Phase Sampling
8. Replicated Sampling
9. Sequential Sampling
10. Master Samples
ii.Non Probability Samples: any sampling method which is not based on the random selection of
elements in the population.
1. Quota Sampling: If some prior knowledge about the population is there
2. Judgment Sampling: Researcher puts his judgment as to whether to include a study object or not
3. Convenience sampling: Selecting a sample of study objects based on convenience
4. Snowball Sampling: A judgmental sample design in which respondents selected earlier are
asked to identify other sample members
8/8/2019 RM_ppt1
17/18
y Characteristics of a good Sample design
1. GoalOrientation
2. Measurability
3. Practicality
4. Economy
Testing of a Hypothesis: Steps
1. Formulate a hypothesis
2. Set up a suitable significance level
3. Choose a test criterion
4. Compute
5. Make decisions
Types of error in testing of a hypothesis
Decision State of Nature
Ho is true Ho is false
Accept Ho Correct Decision Type II error
Reject Ho Type I error Correct Decision
8/8/2019 RM_ppt1
18/18
There are two types of statistical tests:
1. ParametricTest: assumes that parameters such as mean, std. deviation etc. exist
and are used in testing a hypothesis. The underlying assumptions in such tests is
that the source of data is:i. normally distributed
ii. Sample is large
iii. Measurement scale is not defined
Commonly used parametric tests are a. Z-test; b. t-test c. F-test and d. ANOVA
Z= (sample mean-pop. mean)/ sam S.D.
2. Non-ParametricTest: In all Non Parametric Tests, it is assumed that
i.No prior distribution is assumed about the population from which the sample is
drawn
ii. Sample size < 20
iii. Measurement of the variables is at the most ordinal or nominal
e.g. chi-square test 2 = (Oi Ei)2/Ei