MK0013-Marketing Research
1 Write about research(R):Definition b)Characteristics
a)R is a systematic and intensive study undertaken to:
Address the fundamental questions or
Find a solution to the existing problems.
It is an art of scientific investigation. It is also a systematic design collection
analysis and reporting of the findings and solutions for the existing problems
of a company.
As per,e Chambers 20th Century Dictionary,it is “Systematic investigation towards increasing the sum of knowledge." As per,Concise Oxford Dictionary, it is endeavour to discover new or collate old facts etc. by the scientific study of a subject or by a course of critical investigation."
b)R Characteristics are as:
originates with a question or problem
requires the clear articulation of a goal
often divides the main problem into sub- problems
guided by specific problem, question, or hypothesis
Page No. 4
accepts certain critical assumptions
follows a specific plan or procedure
requires systematic collection and interpretation of data
cyclical in nature; meaning that the answers we get from research often
leads to more questions, which leads to more research for answers and
this process continues.
2 Write on criteria of choosing a good research design.
Criteria of Good RD are:
Feasibility: Designs should be implemented in a correct form. The
duration and sequence of events should be designed in a proper way.
Problems should be anticipated in measurement, adherence to
assignment and database construction. Additional groups should be
included in the design to explicitly correct such problems.
Theory-grounded issue: Theory is the base for every solution to the
problem. Good research studies should be based/ grounded on the
theory. For example, where theory predicts a specific treatment effect on
one measure but not on another, the inclusion of both in the design
improves discriminant validity and demonstrates the predictive power of
the theory.
Flexible: Good RD should be flexible enough. This
flexibility further helps in removing duplications of the design features.
For example multiple replication of a treatment helps you to ensure that
failure to one setting of a treatment does not mean entire study is
invalid.
Situational: As per situations, design should be moulded
enough to reflect the correct step properly. For example, need of
teachers, lecturers and an administrator is different according to their
capability. Similarly, intergroup rivalry team and demoralisation
assessment is done through the use of additional comparison groups
who are not in direct contact with the original group.
Efficient: RD should work efficiently. A proper balance
between redundancy and tendency to over-design must be achieved.
As per need of the situation,RD changes must be made
over the period of time.
This is not a thorough list by which you can choose a strategy. However, it
can assist us toward a final RD choice.
3 Explain comparative scales and its types.
Attitude Measurement Scales are employed in marketing research can be 2: (a) comparative scaling and (b) non-comparative scaling.
Here is direct comparison of stimulus objects with one another.
Example of Comparative Scale: Managers are generally interested in knowing consumer preference regarding their brand in comparison to competitor’s brand and ask the consumer to rank different brands in order of preference.
Its Types are:
i) Paired comparison:It is used to find out key factors in determining, say, the demand or determining factors affecting the consumer adoption of a product.
Example: The response to the first design of a battery-driven car.Combination of exploratory R & observation suggested that below factors played a role in the shaping of the attitudes of those
consumers who felt negatively towards the car design.
1. Exterior not impressive,
2. Does not work on Indian highways,
3. Far too expensive,
4. New technology too risky, and
5. Too difficult to maintain.
It is the questioning technique which helps rank ordering the objections from most to least important.
Here we pairs up each of the objections as in this example &comes up with 10 pairs.
In 'it' every factor has to be paired with every other factor
in turn. However, only one pair is ever put to the consumer at a time. The
question might be put as follows:
Which of the following was more important in making you decide not to buy
the car?
1. The car was too expensive
2. It proved too difficult to maintain.
Questions,& alternatives, are put verbally to the consumer in most of the cases. He then indicates which one of the two was more important and the researcher ticks the box on his questionnaire. Then the
question is repeated with a second set of factors and the appropriate box is
ticked again.
This process continues until all possible combinations are exhausted (in this
case 10 pairs). It is a good practice to mix the pairs of factors so that there
may not be systematic bias.We would never, for example, take
the first factor and systematically compare it to each of the others in
succession because that will cause systematic bias.
Below, labels have been given to the factors in the example. The letters
A - E have been allocated as follows:
A = Exterior not impressive
B = Far too expensive
C = New technology too risky
D = Does not work on Indian highways
E = Too difficult to maintain.
The data are then arranged into a matrix as shown in table 6.4. Assume that
200 consumers have been interviewed and their responses are arranged in
the grid below. Further assume that the matrix is so arranged that we read
from top to side.
This means, for example, that 164 out of 200 consumers mentioned the fact
that the ‘battery-driven car was too expensive’, was a greater deterrent than
the fact that ‘its exterior was not impressive'. Similarly, 174 consumers said
that car's inability to run on Indian highways was more key than the exteriors when deciding not to buy the car.
ii) Constant sum scale requires respondents(rspn) to divide a fixed number of
points among several attributes corresponding to their relative importance or
weight. Suppose United Parcel Service (UPS) wishes to determine the
importance of the attributes of accurate invoicing, delivery, and price to
firms that use its service in business-to-business settings.
Rspn might be asked to divide a constant sum of 100 points to
indicate the relative importance of those attributes.
Example: Divide 100 points among the following characteristics of a
delivery service according to how important each characteristic is to you
when selecting a delivery company.
______Accurate invoicing
______Package not damaged
______Delivery as promised
______Lower price
______
100 points
It works best with rspn who have high educational levels. If rspn follow the instructions correctly, results will approximate interval measures. As the number of stimuli
increases, this technique becomes increasingly complex.It may be used for measuring brand preference. It is similar to paired-comparison method, is as follows:
Divide 100 points among the following brands according to your preference
for each brand:
______Brand A
______Brand B
______Brand C
______
100 points
However, it has minor modifications, it can be classified as a sorting technique. Although the
it is widely used, strictly speaking, it is flawed as last response is completely determined by the way rspn has scored the other choices. Although this is probably
somewhat complex to understand, the fact is that practical reasons often
outweigh this concern.
iii) Rank order scale
In it, several objects are being presented to r rspn simultaneously and they are asked to rank or order them according to some
criterion. The order is often a simple ordinal structure (A is higher than B). It
can also be done by relative position (A scores 10 whilst B scores 6).
Example: Please write a letter next to the four evening activities below to
show your preference. Use A for your most preferred activity, B for the next
preferred, then C for the next and then D for the least preferred.
………………….. Staying in and watching television
………………….. Going bowling
………………….. Going out for a meal
………………….. Going to a bar with a friend
iv) Q-sort scale is generally used to compare individuals.It was developed to discriminate among a relatively large number of objects quickly.It uses a rank order procedure in which objects are sorted into scale based on similarity with respect to the attitude being
measured.Rspn are given a large number of items and are asked to place
them in eleven scales from most favourable to least favourable. It requires rspn to express his degree of agreement or disagreement with the item. If rspn agrees most favourably the item is placed in one extreme. Rspn should place a reassigned
number in each scale usually preset so as to result in an approximately
normal distribution over the whole range. Each scale is given a score value.
Interest centres not on total subject scores but the degree of similarity
among various subjects. The similarity may be determined by correlation
analysis. Its procedure is used to classify subjects in terms of
similarity with regard to the attitude being measured.
Example: Here we are taking nine brands. On the basis of taste we classify
the brands into tasty, moderate and non-tasty. We can classify on the basis
of price also-Low, medium, high. Then we can attain the perception of
people with respect to the nine brands by asking them to classify them on
taste or price. This classification helps to know which brands are similar and
which are not on taste and price parameters.
4 Explain various types of probability sampling techniques with suitable examples.
sample designs used may be probability method & non-probability method(NPM). In PM, populationunder study is finite & one can calculate probability of a person beingselected.In probability method , populationunder study is finite & one can calculate probability of a person beingselected.
Selection of one or the other relies on nature of R, degree of accuracy needed (PM reveal more accurate results)&time &financial resources available for R.
e.g, to see if defects are present, we see event as mutually exclusive or equally likely etc.
5 Analyse the steps involved in hypothesis testing.
Steps Involved in Hypothesis Testing(HT) are as:
1. Setting-up of H : Specify nullH (H0)& alternative H (H).
2. Selecting a significance level(SL): A criterion used for rejecting H0 is SL.SL is used in
HT as: i)difference between H0 results of experiment is determined. Then, assuming H0 true;
the probability is computed and then probability is compared to SL . If the probability is < or =SL , H0 is rejected and the outcome is said to be statistically significant.
3. Deciding test statistic to be used: See if what to use probability distribution test as: Z -test, t-Test, F-test and Chi-square test.
4. Calculating the probability value from the data: The calculations are
made assuming that H0 is true.
5. Decision-making: See if accept or reject H0which is made on the basis of information collected from the sample data i.e., the probability value computed in Step 4 is
compared with SL chosen in Step 2. H0is rejected If the probability is > or= SL, if the probability is > than SL, H0 is not rejected.But there is always a chance of making errors as:
Type I Error: Rejection of H0 when it is true.
Type II Error: Acceptance of H0 when it is false.
6 Write short notes on:
a) Media planning
b) Copy Testing
a)Media Planning is quite essential in establishing the best way to disperse
advertisers’ message across to the consumer market through various media
channels. In short, the main goal of the media plan is to find such
combination of media resources, which facilitate the marketer to
communicate their message effectively to the majority of potential clients or
customers, at the lowest possible cost.
Below are the list of activities carried out in association with it:
Identifying the media objectives.
Selecting media group, for example, print media or electronic media, or
both, etc.
Page No. 339
Selecting the media within the group, for example in case of print media,
newspapers or magazines, then specific newspaper/ magazine etc.
b)Copy testing ensures that advertising(ad) is well recognised and that no shockers will occur after releasing the ads. It decreases the chances of risk on brand or company
image by an ineffective ad.It is generally carried out on a large scale as a quantitative
research study in which the target audience(TA) is shown ad.
Advertisers use it as a technique to check the effectiveness of an ad after its production.It has different types but all types have 3 identical elements