Solutions to Assignments
MCO-03 -
Research Methodology and Statistical Analysis
Question No. 3
Briefly comment on the following:
(a) The recognition or existence of a problem motivates research.
Without a problem, research cannot proceed, because there is nothing to
proceed from and proceed towards. Therefore, the first step in research is to
perceive a problem - either practical or theoretical. The recognition or existence
of a problem motivates research. It may be noted that research is the process
of repeated search for truth/facts. Unless there is a problem to search for,
investigation cannot proceed. Thus, a problem sets the goal or direction of
research.
A problem in simple words is “some difficulty experienced by the researcher in
a theoretical or practical situation. Solving this difficulty is the task of
research”.
A problem exists when we do not have enough information to answer a
question (problem). The answer to the question or problem is what is sought in
the research.
By problem we mean “any condition or circumstance in which one does not
know how to act and what to accept as true”. In our common usage when we
are unable to assess a thing correctly, we often say ‘it is problematic’.
Thus
the researcher who selects a problem formulates a hypothesis or postulates a
theoretical assumption that this or that is true, this or that thing to do. He/she
collects proof (facts/data) of his/her hypothesis. Based on the analysis of the
data collected he/she asserts the truth or answers the question/solves the
problem.
A topic of study may be selected by some institution or by some researcher or
researchers having intellectual interests. In the former case there could be a
wide variety of problems in which institutions are interested. The institution
could be a local body, or government or corporate enterprises or a political
party. For example, the government may be interested in assessing the probable
consequences of various courses of action for solving a problem say rural
unemployment. A firm may be interested in assessing the demand for something
and predicting the future course of events so as to plan appropriate action
relating to marketing, production, consumer behaviour and so on.
The topic of study may be selected by some individual researcher having
intellectual or scientific interests. The researcher may be interested in exploring
some general subject matter about which relatively little is known. And its
purpose is just for scientific curiosity. Person may also be interested in a
phenomenon which has already been studied in the past, but now it appears
that conditions are different and, therefore, it requires further examination.
Person may also be interested in a field in which there is a highly developed
theoretical system but there is need for retesting the old theory on the basis of
new facts, so as to test its validity in the changed circumstances.
The topic of research may be of a general nature or specifically needed by
some institution, organization or government. It may be of intellectual interest or
of practical concern, “A wide variety of practical concerns may present topics
for research”. For example, one may want to study the impact of television on
children’s education, performance of regulated agricultural markets, profitability
of a firm, impact of imports on Indian economy, a comparative study of
accounting practices in public and private undertakings, etc.
If the researcher / research organization has a ready problem on hand, he/she
can proceed further in the research process or else you have to search for a
problem. Where can you search for research problems? Your own mind, where
else? You have to feel the problem and think about it. However, the following
sources may help you in identifying the problem / problem areas.
1) Business Problems: A research problem is a felt need, the need may be
an answer, or a solution or an improvement in facilities / technology eg. Cars
Business experiences, various types of problems. They may be business policy
problems, operational problems, general management problems, or functional
area problems. The functional areas are Financial Management, Marketing
Management, Production Management and Human Resources Management.
Every business research problem is expected to solve a management problem
by facilitating rational decision-making.
2) Day to Day Problems: A research problem can be from the day to day
experience of the researcher. Every day problems constantly present some thing
new and worthy of investigation and it depends on the keenness of observation
and sharpness of the intellect of the researcher to knit his daily experience into
a research problem. For example, a person who travels in city buses every day
finds it a problem to get in or get out of the bus. But a Q system (that is the
answer to the problem) facilitates boarding and alighting comfortably.
3) Technological Changes: Technological changes in a fast changing world
are constantly bringing forth new problems and thus new opportunities for
research. For example, what is the impact or implications of a new technique
or new process or new machine?
4) Unexplored Areas: Research problems can be both abstract and of applied
interest. The researcher may identify the areas in which much work has been
done and the areas in which little work has been done or areas in which no
work has been done. He may select those areas which have not been explored
so far/explored very little.
5) Theory of One’s Own Interest: A researcher may also select a problem
for investigation from a given theory in which he has considerable interest. In
such situations the researcher must have a thorough knowledge of that theory
and should be able to explore some unexplained aspects or assumptions of that
theory. His effort should revalidate, or modify or reject the theory.
6) Books, Theses, Dissertation Abstracts, Articles: Special assignments in
textbooks, research theses, investigative reports, research articles in research
journals etc., are rich sources for problem seekers. These sources may suggest
some additional areas of needed research. Many of the research theses and
articles suggest problems for further investigation which may prove fruitful.
7) Policy Problems: Government policy measures give rise to both positive
and negative impact. The researcher may identify these aspects for his
research. For example, what is the impact of the Government’s new industrial
policy on industrial development? What is the impact of Export - Import policy
on balance of payments? What is the impact of Securities Exchange Board of
India Regulations on stock markets?
8) Discussions with Supervisor and Other Knowledgeable Persons: The
researcher may find it fruitful to have discussions with his/her proposed
supervisor or other knowledgeable persons in the area of the topic.
The selection of a topic for research is only half-a-step forward. This general
topic does not help a researcher to see what data are relevant to his/her
purpose. What are the methods would he/she employ in securing them? And
how to organize these? Before he/she can consider all these aspects, he/she
has to formulate a specific problem by making the various components of it (as
explained above) explicit.
A research problem is nothing but a basic question for which an answer or a
solution is sought through research. The basic question may be further broken
down into specifying questions. These “simple, pointed, limited, empirically
verifiable questions are the final result of the phased process, we designate as
the formulation of a research problem”. Specification or definition of the
problem is therefore a process that involves a progressive narrowing of the
scope and sharpening of focus of questions till the specific challenging questions
are finally posed. If you can answer the following questions, you have clearly
specified/defined the problem.
(b) Quantitative data has to be condensed in a meaningful manner, so that it can be easily understood and interpreted.
Quantitative data has to be condensed in a
meaningful manner, so that it can be easily understood and interpreted. One of
the common methods for condensing the quantitative data is to compute
statistical derivatives, such as Percentages, Ratios, Rates, etc. These are simple
derivatives. Further, it is necessary to summarise and analyse the data. The first
step in that direction is the computation of Central Tendency or Average, which
gives a bird's-eye view of the entire data. In this Unit, we will discuss computation
of statistical derivatives based on simple calculations. Further, numerical methods
for summarizing and describing data ñ measures of Central Tendency ñ are
discussed. The purpose is to identify one value, which can be obtained from the
data, to represent the entire data set.
Statistical derivatives are the quantities obtained by simple computation from the
given data. Though very easy to compute, they often give meaningful insight to
the data. Here we discuss three often-used measures: percentage, ratio and
rate. These measures point out an existing relationship among factors and
thereby help in better interpretation.
1. Percentage
As we have noted earlier, the frequency distribution may be regarded as simple
counting and checking as to how many cases are in each group or class. The
relative frequency distribution gives the proportion of cases in individual classes.
On multiplication by 100, the percentage frequencies are obtained. Converting to
percentages has some advantages - it is now more easily understood and
comparison becomes simpler because it standardizes data. Percentages are quite
useful in other tables also, and are particularly important in case of bivariate
tables.
2. Ratio
Another descriptive measure that is commonly used with frequency distribution
(it may be used elsewhere also) is the ratio. It expresses the relative value of
frequencies in the same way as proportion or percentages but it does so by
comparing any one group to either total number of cases or any other group.
For instance, in table 6.3, Unit 6, the ratio of all labourers to their daily wages between Rs 30ñ35 is 70:14 or 5:1. Where ever possible, it is convenient to
reduce the ratios in the form of n1: n2, the most preferred value of n2 being 1.
Thus, representation in the form of ratio also reduces the size of the number
which facilitates easy comparison and quick grasp. As the number of categories
increases, the ratio is a better derivative for presentation as it will be easy and
less confusing.
There are several types of ratios used in statistical work. Let us discuss them.
a. The Distribution Ratio: It is defined as the ratio of a part to a total which
includes that part also. For example, in an University there are 600 girls out of
2,000 students. Than the distribution ratio of girls to the total number of
students is 3:10. We can say 30% of the total students are girls in that
University.
b. Interpret ratio: It is a ratio of a part in a total to another part in the same
total. For example, sex ratio is usually expressed as number of females per
1,000 males (not against population).
c. Time ratio: This ratio is a measure which expresses the changes in a series
of values arranged in a time sequence and is typically shown as percentage.
Mainly, there are two types of time ratios :
i) Those employing a fixed base period: Under this method, for instance, if you are interested in studying the sales of a product in the current year, you would select a particular past year, say 1990 as the base year and compare the current yearís production with the production of 1990.
ii) Those employing a moving base: For example, for computation of the current year's sales, last year's sales would be assumed as the base (for 1991, 1990 is the base. For 1992, 1991 is the base and so on.
Ratios are more often used in financial economics to indicate the financial status of an organization.
3. Rate
The concept of ratio may be extended to the rate. The rate is also a
comparison of two figures, but not of the same variable, and it is usually
expressed in percentage. It is a measure of the number of times a value occurs
in relation to the number of times the value could occur, i.e. number of actual
occurrences divided by number of possible occurrences. Unemployment rate in
a country is given by total number of unemployed person divided by total
number of employable persons. It is clear now that a rate is different from a
ratio. For example, we may say that in a town the ratio of the number of
unemployed persons to that of all persons is 0.05: 1. The same message would
be conveyed if we say that unemployment rate in the town is 0.05, or more
commonly, 5 per cent. Sometimes rate is defined as number of units of a
variable corresponding to a single unit of another variable; the two variables could be in different units. For example, seed rate refers to amount of seed
required per unit area of land. The following table gives some examples of
rates.
(c) Decomposition and analysis of a time series is one and the same thing.
Decomposition and analysis of a time series are one and the same thing. The
original data or observed data ‘O’ is the result of the effects generated by the
long-term and short-term causes, namely, (1) Trend = T, (2) cyclical = C, (3)
seasonal = S, and (4) Irregular = I. Finding out the values for each of the
components is called decomposition of a time series. Decomposition is done
either by the Additive model or the Multiplicative model of analysis. Which of
these two models is to be used in analysis of time series depends on the
assumption that we might make about the nature and relationship among the
four components.
Additive Model: It is based on the assumption that the four components are
independent of one another. Under this assumption, the pattern of occurrence
and the magnitude of movements in any particular component are not affected
by the other components. In this model the values of the four components are
expressed in the original units of measurement. Thus, the original data or
observed data, ‘Y’ is the total of the four component values,
that is,
Y = T + S + C + I
where, T, S, C and I represent the trend variations, seasonal variations cyclical
variations, and erratic variations, respectively.
Multiplicative Model: It is based on the assumption that the causes giving
rise to the four components are interdependent. Thus, the original data or
observed data ‘Y’ is the product of four component values,
that is :
Y = T × S × C × I
In this model the values of all the components, except trend values, are
expressed as percentages.
In business research, normally, the multiplicative model is more suited and used
more frequently for the purpose of analysis of time series. Because, the data
related to business and economic time series is the result of interaction of a
number of factors which individually cannot be held responsible for generating
any specific type of variations.
(d) Research reports are the product of slow, painstaking and accurate work.
Reporting simply means communicating or informing through reports. The
researcher has collected some facts and figures, analyzed the same and arrived
at certain conclusions. He has to inform or report the same to the parties
interested. Therefore “reporting is communicating the facts, data and information
through reports to the persons for whom such facts and data are collected and
compiled”.
A report is not a complete description of what has been done during the period
of survey/research. It is only a statement of the most significant facts that are
necessary for understanding the conclusions drawn by the investigator. Thus, “
a report by definition, is simply an account”. The report thus is an account
describing the procedure adopted, the findings arrived at and the conclusions
drawn by the investigator of a problem.
Research report is a channel of communicating the research findings to the
readers of the report. A good report is one which does this task efficiently and
effectively. As such it should have the following characteristics/qualities.
i) It must be clear in informing the what, why, who, whom, when, where and how
of the research study.
ii) It should be neither too short nor too long. One should keep in mind the fact
that it should be long enough to cover the subject matter but short enough to
sustain the reader’s interest.
iii) It should be written in an objective style and simple language, correctness,
precision and clarity should be the watchwords of the scholar. Wordiness,
indirection and pompous language are barriers to communication.
iv) A good report must combine clear thinking, logical organization and sound
interpretation.
v) It should not be dull. It should be such as to sustain the reader’s interest.
vi) It must be accurate. Accuracy is one of the requirements of a report. It should
be factual with objective presentation. Exaggerations and superlatives should
be avoided.
vii) Clarity is another requirement of presentation. It is achieved by using familiar
words and unambiguous statements, explicitly defining new concepts and
unusual terms.
viii) Coherence is an essential part of clarity. There should be logical flow of ideas
(i.e. continuity of thought), sequence of sentences. Each sentence must be so
linked with other sentences so as to move the thoughts smoothly.
ix) Readability is an important requirement of good communication. Even a
technical report should be easily understandable. Technicalities should be
translated into language understandable by the readers.
x) A research report should be prepared according to the best composition
practices. Ensure readability through proper paragraphing, short sentences,
illustrations, examples, section headings, use of charts, graphs and diagrams.
xi) Draw sound inferences/conclusions from the statistical tables. But don’t repeat
the tables in text (verbal) form.
xii) Footnote references should be in proper form. The bibliography should be
reasonably complete and in proper form.
xiii) The report must be attractive in appearance, neat and clean whether typed or
printed.
xiv) The report should be free from mistakes of all types viz. language mistakes,
factual mistakes, spelling mistakes, calculation mistakes etc.,
The researcher should try to achieve these qualities in his report as far as possible
