Research: An Overview (ii) External criteria

External criteria consist of the following:

• Potential for research: Very narrow or extremely vague problems should
NOTES be avoided. In order to be researched, a problem must be one for which
observation or other data collection in real world can provide the answer.
• Importance and urgency: Issues that require investigation are unlimited
but available research efforts are very limited. Therefore, relative importance
and significance of the problem is required. Important and urgent issues
should be given priority over an unimportant one.
• Novelty of the problem: A problem on which a lot of research work has
been done should not be considered for research as there are fewer chances
of throwing light on any new factor.
• Feasibility: Novelty of the problem is not sufficient if it is not feasible to
conduct the study on problem in real world, i.e., it should contain facts
which can be analysed. Even if the problem is novel we should make a
small feasibility study first and proceed only after this if study allows.
• Facilities: A well-equipped library, proper guidance in data analysis, etc.,
are basic facilities which are required to carry on any research.
• Research personnel: Availability of adequate research personnel like
investigators and research officers is very important for data collection,
which is a major issue in many developing countries like India.
Techniques involved in formulating the problem
Defining a research problem properly and clearly is a crucial part of the research
study and must, in no case, be done hurriedly. The technique for this purpose
involves undertaking the following steps, generally one after the other:
• Statement of the problem in a general way: The problem should be
carefully worded. The problem statement should indicate nature of the
problem and intention of researcher.
• Understanding the nature of the problem: The best way to understand
the nature of the problem is to discuss with those who have prior experience
in the same kind of research. This will ensure that the origination of problem
and the objectives in view are correct. If the marketer has stated the problem
himself, he should consider all the facts that induced him to make a general
statement concerning the problem.
• Developing ideas through discussions: Many new ideas are developed
by discussing them with others. This discussion provides useful information
for research. Discussion is done with those people who have enough
experience in the concerned field.
• Rephrasing the research problem: After going through the given four
steps, the researcher gets a clear idea about the environment in which the
10 Self-Instructional Material
 problem is to be studied. Now rephrasing the problem into analytical or Research: An Overview
operational terms is not a difficult task. Through rephrasing, the researcher
puts the research problem in as specific terms as possible so that it may
become operationally viable and may help in the development of working
hypothesis. NOTES

2. Developing Data Source

Finding the answers to questions for a research study is called data collection.
Data is the collection of facts and other relevant materials, from which we can
draw conclusions. Data source is developed for ensuring the availability of data
for decision-making.
3. Data Collection
The following are the various methods of data collection:
(a) Interviewing
Interviews are generally classified into the following two categories:
(i) Structured or directive interview
In this type of interview, the investigator goes to the respondent with a detailed
schedule. Some questions are asked from all the respondents in the same sequence.
The style of asking every question is the same in all the interviews as it generates
more reliability. It is used for large sample size.
Merits
The following are the advantages of structured or directive interviews:
• Data can be easily compared.
• Recording and coding of data is done easily.
• There is no wastage of time.
Demerits
The following are the limitations of structured or directive interviews:
• There is no natural conversation.
• Researcher’s bias may be reflected in the answers.
• There is no scope for exploring the data.
(ii) Unstructured or non-directive interview
The respondent is encouraged to give his honest opinion on the given topic without
or with minimum help from others. In this interview, the pre-planned schedule is
not used. The investigator uses only major guidelines for the interview. No particular
sequence of questions is followed in the interview. When the path of investigation
in exploratory research is not clearly defined, unstructured interview is very useful
to get the direction of research study.
Self-Instructional Material 11
Research: An Overview Merits
The following are the advantages of unstructured or non-directive interviews:
• There is natural conversation.
NOTES • Researcher’s biasness is not reflected in the answers.
• There is a lot of scope for exploring the data.
Demerits
The following are the limitations of unstructured or non-directive interviews:
• It is not easy to compare the data.
• The suitability of the data for research study needs to be checked.
• There is excessive unproductive conversation.
• There excessive of time consumption.
(b) Observation
Observation may be defined as specific viewing with the purpose of gathering the
data for a specific research study. Observation is a classical method of scientific
study. It has high importance in any research study as it is an effective method for
data collection. Following are the characteristics of the observation method of
data collection:
• Physical and mental activity: Eyes observe many things in our surroundings
but our focus or attention is only on data which is relevant to the research
study.
• Observation is selective: It is very difficult for a researcher to observe
everything in the surroundings. He only observes the data which is useful for
his research study and meets the scope of the study. The researcher ignores
all the data which is not relevant to the study.
• Observation is purposive and not casual: Observation is purposive as
it is relevant to a particular study. The purpose of observation is to collect
data for the research study. It focuses on human behaviour, which occurs in
a social setup. It analyses the relationship of different variables in a specific
context.
• Accuracy and standardization: Observation of pertinent data should be
accurate and standardized for its applications.
Different concepts define the classification of observations.
With respect to the investigator’s role, observation may be classified as:
• Participant observation
• Non-participant observation

12 Self-Instructional Material
With respect to observation, it can be classified into: Research: An Overview

• Direct observation
• Indirect observation
With reference to the rigour of system adopted, observation can be classified into: NOTES
• Controlled observation
• Uncontrolled observation
Prerequisites of observation
The following are some of the prerequisites of observation:
• Conditions of observation must provide accurate results. The observer should
be in a position to observe the object clearly.
• The right number of respondents as sample size is essential to ensure that
observation produces the desired results.
• There should be accurate and completed recording of an event.
• If it is possible, two separate observers and sets of instruments can be used
in all or some observations. Then result can be compared to measure
accuracy and completeness.
Advantages of observation
The following are the advantages of observation:
• It ensures that behaviour is studied in accordance with the occurrence of
events. The observer does not ask anything from the representatives. He
just watches what the sample does and says.
• The data collected by observation defines the observed phenomenon as
they occur in their natural settings.
• When object itself is not able to define the meaning of its behaviour,
observation is best method for analysis; for instance, animals, birds, children,
etc.
• Observation covers the entire happenings of an event.
• Observation is less biased than questioning.
• It is easy to conduct disguised observation studies than disguised questioning.
• Use of mechanical devices can generate more accuracy and completeness.
Demerits of observation
The following are the limitations of observation:
• Past studies and events are of no use to observation as the researcher has
to personally go through narrations, people and the related documents.
• Difficult to understand attitudes with the help of observation.

Self-Instructional Material 13
Research: An Overview • Observations cannot be performed by the choice of observer. He has to
wait for an event to occur.
• It is difficult to predict when and where the event will occur. Thus, it may
not be possible for the observer to reach every event.
NOTES
• Observation requires more time and more money.
(c) Sampling procedure
Different types of sampling are also used to collect data. The term ‘universe’
refers to the complete population that is to be studied or measured. A part of the
population is called sample. Selecting a part of the universe with a view to draw
conclusions about the ‘universe’ or ‘population’ for a study is known as sampling.
Researchers use sampling for saving time and cost, as the selected sample represents
the whole population. The following are the different types of sampling used:
• Probability or random sampling
• Simple random sampling
• Stratified random sampling
• Systematic random sampling
• Non-probability or non-random sampling
• Purposive or (judgment) sampling
4. Data Analysis
Processing of data refers to the preparation of data for research analysis. On the
basis of the results of this data processing, further selection of the tools for analysis
would be done. Data processing is an intermediary stage of work between data
collection and data interpretation. The data gathered in the form of questionnaires,
interview, schedules, field notes and data sheets, is mostly in the form of large
volume of research variables.
The following are some of the methods for data analysis:
Spearman’s Rank Correlation Method
Charles Edward Spearman, a British psychologist, devised a method for measuring
the correlation between two variables based on ranks given to the observations.
This method is adopted when the variables are not capable of quantitative
measurements like intelligence, beauty, etc., and in such cases, they are variables.
It is in such cases that rank correlation is useful.
Concurrent Deviation Method
In this method, correlation is calculated between the direction of deviations and
not their magnitudes. As such, only the direction of deviations is taken into account
in the calculation of this coefficient and their magnitude is ignored.

14 Self-Instructional Material