Professional Documents
Culture Documents
com/imspykan
Survey is a very popular branch of social science research. Survey research has developed as a
separate research activity alongwith the development and improvement of sampling procedures.
Sample surveys are very popular now a days. As a matter of fact sample survey has become
synonymous with survey. For example, see the following definitions: Survey research can be defined
as “Specification of procedures for gathering information about a large number of people by
collecting information from a few of them”. (Black and Champion). Survey research is “Studying
samples chosen from populations to discover the relative incidence, distribution, and inter relations
of sociological and psychological variables”. (Fred N. Kerlinger)
Survey research is not a clerical routine of gathering facts and figures. It requires a good deal of
research knowledge and sophistication. The competent survey investigator must know sampling
procedures, questionnaire / schedule / opionionaire construction, techniques of interviewing and
1|Page
For Classes Contact:
AGGARWAL ACADEMY (F-83, Vishnu Garden) | 7531933003
FOR MORE NOTES VISIT: http://spykan.com Like us on: http://fb.com/imspykan
other technical aspects of the survey. Ultimately the quality of the Survey results depends on the
imaginative planning, representative sampling, reliability of data, appropriate analysis and
interpretation of the data.
Observation Method
Observation means seeing or viewing. It is not a casual but systematic viewing. Observation may
therefore be defined as “a systematic viewing of a specific phenomenon in its proper setting for the
purpose of gathering information for the specific study”.
Observation is also useful in social and business sciences for gathering information and
conceptualizing the same. For example, What is the life style of tribals? How are the marketing
activities taking place in Regulated markets?
How will the investment activities be done in Stock Exchange Markets? How are proceedings taking
place in the Indian Parliament or Assemblies? How is a corporate office maintained in a public sector
or a private sector undertaking? What is the behaviour of political leaders? Traffic jams in Delhi
during peak hours?
i) It is not only seeing & viewing but also hearing and perceiving as well.
ii) It is both a physical and a mental activity. The observing eye catches many things which are
sighted, but attention is also focused on data that are relevant to the problem under study.
iii) It captures the natural social context in which the person’s behaviour occurs.
iv) Observation is selective: The investigator does not observe everything but selects the range of
things to be observed depending upon the nature, scope and objectives of the study.
v) Observation is not casual but with a purpose. It is made for the purpose of noting things relevant
to the study.
vi) The investigator first of all observes the phenomenon and then gathers and accumulates data.
Observation may be classified in different ways. According to the setting it can be (a) observation in
a natural setting, eg. Observing the live telecast of parliament proceedings or watching from the
visitors gallery, Electioneering in India through election meetings or (b) observation in an artificially
2|Page
For Classes Contact:
AGGARWAL ACADEMY (F-83, Vishnu Garden) | 7531933003
FOR MORE NOTES VISIT: http://spykan.com Like us on: http://fb.com/imspykan
stimulated setting, eg. business games, Tread Mill Test. According to the mode of observation it may
be classified as (a) direct or personal observation, and (b) indirect or mechanical observation. In
case of direct observation, the investigator personally observes the event when it takes place, where
as in case of indirect observation it is done through mechanical devices such as audio recordings,
audio visual aids, still photography, picturization etc. According to the participating role of the
observer, it can be classified as (a) participant observation and (b) non-participant observation. In
case of participant observation, the investigator takes part in the activity, i.e. he acts both as an
observer as well as a participant. For example, studying the customs and life style of tribals by living
/ staying with them. In case of non-participant observation, the investigator observes from outside,
merely as an on looker.
Observation method is suitable for a variety of research purposes such as a study of human
behaviours, behaviour of social groups, life styles, customs and traditions, inter personal relations,
group dynamics, crowd behaviour, leadership and management styles, dressing habits of different
social groups in different seasons, behaviour of living creatures like birds, animals, lay out of a
departmental stores, a factory or a residential locality, or conduct of an event like a meeting or a
conference or Afro- Asian Games.
The following practical guidelines may be handy while editing the data:
1) The editor should have a copy of the instructions given to the interviewers.
2) The editor should not destroy or erase the original entry. Original entry should be crossed out in
such a manner that they are still legible.
3) All answers, which are modified or filled in afresh by the editor, have to be indicated.
4) All completed schedules should have the signature of the editor and the date.
For checking the quality of data collected, it is advisable to take a small sample of the questionnaire
and examine them thoroughly. This helps in understanding the following types of problems:
3|Page
For Classes Contact:
AGGARWAL ACADEMY (F-83, Vishnu Garden) | 7531933003
FOR MORE NOTES VISIT: http://spykan.com Like us on: http://fb.com/imspykan
At times, it may be worthwhile to group the same set of questionnaires according to the investigators
(whether any particular investigator has specific problems) or according to geographical regions
(whether any particular region has specific problems) or according to the sex or background of the
investigators, and corrective actions may be taken if any problem is observed.
Before tabulation of data it may be good to prepare an operation manual to decide the process for
identifying inconsistencies and errors and also the methods to edit and correct them. The following
broad rules may be helpful.
Incorrect answers: It is quite common to get incorrect answers to many of the questions. A person
with a thorough knowledge will be able to notice them. For example, against the question “Which
brand of biscuits do you purchase?” the answer may be “We purchase biscuits from ABC Stores”.
Now, this questionnaire can be corrected if ABC Stores stocks only one type of biscuits, otherwise
not. Answer to the question “How many days did you go for shopping in the last week?” would be a
number between 0 and 7. A number beyond this range indicates a mistake, and such a mistake
cannot be corrected.
The general rule is that changes may be made if one is absolutely sure, otherwise this question
should not be used. Usually a schedule has a number of questions and although answers to a few
questions are incorrect, it is advisable to use the other correct information from the schedule rather
than discarding the schedule entirely.
Inconsistent answers: When there are inconsistencies in the answers or when there are incomplete
or missing answers, the questionnaire should not be used. Suppose that in a survey, per capita
expenditure on various items are reported as follows: Food – Rs. 700, Clothing – Rs.300, Fuel and
Light – Rs. 200, other items – Rs. 550 and Total – Rs. 1600. The answers are obviously inconsistent
as the total of individual items of expenditure is exceeding the total expenditure.
Modified answers: Sometimes it may be necessary to modify or qualify the answers. They have to
be indicated for reference and checking. Numerical answers to be converted to same units: Against
the question “What is the plinth area of your house?” answers could be either in square feet or in
square metres. It will be convenient to convert all the answers to these questions in the same unit,
square metre for example.
4|Page
For Classes Contact:
AGGARWAL ACADEMY (F-83, Vishnu Garden) | 7531933003
FOR MORE NOTES VISIT: http://spykan.com Like us on: http://fb.com/imspykan
1. They relieve the dullness of the numerical data: Any list of figures becomes less
comprehensible and difficult to draw conclusions from as its length increases. Scanning of the
figures from tables causes undue strain on the mind. The data when presented in the form of
diagrams and graphs, gives a birds eye-view of the entire data and creates interest and leaves
an impression on the mind of readers for a long period.
2. They make comparison easy: This is one of the prime objectives of visual presentation of data.
Diagrams and graphs make quick comparison between two or more sets of data simpler, and
the direction of curves bring out hidden facts and associations of the statistical data.
3. They save time and effort: The characteristics of statistical data, through tables, can be
grasped only after a great strain on the mind. Diagrams and graphs reduce the strain and save
a lot of time in understanding the basic characteristics of the data.
4. They facilitate the location of various statistical measures and establish trends: Graph
makes it possible to locate several measures of central tendency such as Median, Quartiles,
Mode etc. They help in establishing trends of the past performance and are useful in interpolation
or extrapolation, line of best fit, establishing correlation etc. Thus, it helps in forecasting.
5. They have universal applicability: It is a universal practice to present the numerical data in
the form of diagrams and graphs. In these days, it is an extensively used technique in the field
of economics, business, education, health, agriculture etc.
6. They have become an integral part of research: In fact, now a days it is difficult to find any
research work without visual support. The reason is that this is the most convincing and
appealing way of presenting the data. You can find diagrammatic and graphic presentation of
data in journals, magazines, television, reports, advertisements etc. After having understood
about the importance of visual presentation, we shall move on to discuss about the Diagrams
and graphs which are more frequently used in the area of business research
5|Page
For Classes Contact:
AGGARWAL ACADEMY (F-83, Vishnu Garden) | 7531933003
FOR MORE NOTES VISIT: http://spykan.com Like us on: http://fb.com/imspykan
Real income in 1980 = Actual income in 1980 ÷ Consumer price index of 1980
Therefore, the consumer’s real income in the year 1980 is Rs. 75/- as compared to his income of
Rs. 100/- in the year 1970. We can also say that because of price increase, even though his income
has increased, his purchasing power has decreased.
It is obvious that we should take into account both types of errors and must try to reduce them.Since
committing these two types of errors may be regarded as random events, we may modify our earlier
statement and suggest that an appropriate test of hypothesis should aim at reducing the probabilities
of both types of errors.
Surely, our objective would be to reduce both type-I and type-II errors. But since we have taken
recourse to sampling, it is not possible to reduce both types of errors simultaneously for a fixed
sample size.
ii) Sources of Data: From where to collect data? It is an important and difficult issue. The source
depends on the information requirement. For example, one may need to collect prices and quantities
consumed related to certain commodities for a consumer price index. However, there may be a large
number of retailers and wholesalers, selling the commodities, and quoting different prices. To get
the details, only a few representative shops (which represent the typical purchasing points of the
people under question) need to be selected. Thus, based on a representative sample survey,
sources should be from where accurate, adequate, and timely data can be available.
7|Page
For Classes Contact:
AGGARWAL ACADEMY (F-83, Vishnu Garden) | 7531933003
FOR MORE NOTES VISIT: http://spykan.com Like us on: http://fb.com/imspykan
iii) Timings of Data Collection: It is also equally important to collect the data at an appropriate time.
Referring to the example of consumer price index, prices are likely to vary on different days of the
month. For certain commodities prices may vary at different times of the same day. For each
commodity, individual judgement needs to be exercised to represent reality and to serve the purpose
for which an index is to be used.
A large number of one dimensional diagrams are available for presenting data. Such as line diagram,
simple bar diagram, multiple bar diagram, sub-divided bar diagram, percentage bar diagram,
deviation bar diagram etc. In a Simple bar diagram, the data related to one variable is depicted. Such
as, profits, investments, exports, sales, production etc. The technique of preparing Multiple bar
diagram is the same as that of simple bar diagram. Multiple bar diagram, on the one hand, facilitates
comparison of the values of different variables in a set and on the other, it facilitates the comparison
of the values of the same variable over a period of time or phenomenon. Sub-divided bar diagram
shows the total of the variables as well as the total of its various components in a single bar.
8|Page
For Classes Contact:
AGGARWAL ACADEMY (F-83, Vishnu Garden) | 7531933003
FOR MORE NOTES VISIT: http://spykan.com Like us on: http://fb.com/imspykan
The shape of a graph offers easy and appropriate answers to several questions, such as:
➢ The direction of curves on the graph makes it very easy to draw comparisons.
➢ The presentation of time series data on a graph makes it possible to interpolate or
extrapotrate the values, which helps in forecasting.
➢ The graph of frequency distribution helps us to determine the values of Mode, Median,
Quartiles, percentiles, etc.
➢ The shape of the graph helps in demonstrating the degree of inequality and direction of
correlation
For all such advantages it is necessary for a researcher to have an understanding of different types
of graphic presentation of data. In practice, there are a variety of graphs which can be used to depict
the data. However, here we will discuss only a few graphs which are more frequently used in
business research. Broadly, the graphs of statistical data may be classified into two types, one is
graphs of time series, another is graphs of frequency distribution.
Parts of a Graph
The foremost requirement for a researcher is to be aware of the basic principles for using the graph
paper for presentation of statistical data graphically. Conventionally, graphs are drawn on a graph
paper. Two perpendiculars are drawn which intersect each other at right angles. This intersecting
point is called the origin point or the ‘zero’ point. The horizontal line is known as ‘X’ axis (ordinate)
on which independent variables are shown while the vertical line is known as ‘Y’ axis (abscissa) on
which dependent variables are shown. The graph paper is thus divided into four parts, termed as
“quadrants”. These quadrants are meant to depict the positive values and negative values of X
variable and Y variable. By observing the following Chart we will understand clearly about the
purpose of quadrants of a graph.
9|Page
For Classes Contact:
AGGARWAL ACADEMY (F-83, Vishnu Garden) | 7531933003
FOR MORE NOTES VISIT: http://spykan.com Like us on: http://fb.com/imspykan
One of the fundamental rules while constructing graphs is that the scale on the Y-axis should begin
from zero. Where the lowest value to be plotted on the Y scale is relatively high and a detailed scale
is required to bring out he variations in all the data, starting the Y scale with zero introduces
difficulties. For example, if we have a series of production figures over a number of years ranging
from 15000 units to 25000 units, then starting with a zero origin would have one of two undesirable
consequences: either (i) the necessarily large intervals (say 5000 units) on the Y scale would make
us lose sight of the extent of fluctuations in the curve : (ii) a necessarily large graph to permit small
intervals (say 1000 units) would entail a waste of a large part of the graph, in addition to poor visual
communication.
The solution is to break the Y scale : If the zero origin is the shown then the scale is broken by
drawing a horizontal wavy line (also called kinked or zig-zag line) or a vertical wavy line between
zero and the first unit on the Y scale which in our illustration would be 15000 units. The following
diagrams would clarify the point:
The X-axis can also be broken in a similar manner as shown by the following diagram:
These lines are drawn to make the reader aware of the fact that false base has been used. Three
important objects of false base line are:
10 | P a g e
For Classes Contact:
AGGARWAL ACADEMY (F-83, Vishnu Garden) | 7531933003
FOR MORE NOTES VISIT: http://spykan.com Like us on: http://fb.com/imspykan
2. A large part of the graph is not wasted or space is saved by using false base.
3. The graph provides a better visual communication.
The graph usually drawn to represent a frequency distribution is called a Histogram. A histogram is
a set of rectangles (vertical bars) each proportionate in width to the magnitude of a class interval and
proportionate in area to the number of frequencies concerning the classes’ intervals. In a histogram,
the variables (class-intervals) are always shown on X-axis and the frequencies are taken on the Y-
axis. In constructing a histogram there should not be any gap between two successive rectangles,
and the data must be in exclusive form of classes. However, we cannot construct histogram for
distribution with open-end classes and it can be quite misleading if the distribution has unequal class
intervals.
The value of mode can be determined from the histogram. The procedure for locating the mode is
to draw a straight line from the top right corner of the highest rectangle (Modal Class) to the top right
corner of the preceding rectangle (Pre Modal Class). Similarly, draw a straight line from the top left
corner of the highest rectangle to top left corner of the succeeding rectangle (Post Modal Class).
Draw a perpendicular from the point of intersection of these two straight lines to X-axis. The point
where it meets the X-axis gives the value of mode.
working in that company are the source. On the other hand, if you have decided to use secondary
data, you have to identify the secondary source who have already collected the related data for their
study purpose.
With the above discussion, we can understand that the difference between primary and secondary
data is only in terms of degree. That is that the data which is primary in the hands of one becomes
secondary in the hands of another.
Parametric tests can provide trustworthy results with distributions that are skewed and non-normal
and also provide trustworthy results when the groups have different amounts of variability.
Parametric tests have greater statistical power. While on the other hand Nonparametric tests assess
the median which can be better for some study areas. Nonparametric tests are valid when our
sample size is small and your data are potentially nonnormal. Nonparametric tests can analyze
ordinal data, ranked data, and outliers
Many people believe that the decision between using parametric or nonparametric tests depends on
whether your data are normally distributed. If you have a small dataset, the distribution can be a
deciding factor. However, in many cases, this issue is not the critical issue because of the following:
The answer is often contingent upon whether the mean or median is a better measure of central
tendency for the distribution of your data.
• If the mean is a better measure and you have a sufficiently large sample size, a parametric
test usually is the better, more powerful choice.
• If the median is a better measure, consider a nonparametric test regardless of your sample
size.
12 | P a g e
For Classes Contact:
AGGARWAL ACADEMY (F-83, Vishnu Garden) | 7531933003
FOR MORE NOTES VISIT: http://spykan.com Like us on: http://fb.com/imspykan
. For practical purposes, you can think of "parametric" as referring to tests, such as t-tests and the
analysis of variance, that assume the underlying source population(s) to be normally distributed; they
generally also assume that one's measures derive from an equal-interval scale. And you can think
of "non-parametric" as referring to tests that do not make on these particular assumptions.
1. Open-ended questions are questions that have unlimited response options while Close-
ended questions are questions that have limited response options.
2. Open-ended questions allow the individual providing the response to answer however he
chooses while close-ended questions lend themselves to “yes” or “no” responses.
3. Close-ended questions are more specific, while open-ended ones are much more “open.”
4. an open-ended question is a question that does not expect a specific, narrow answer while a
close-ended question is a question that expects a specific answer and does not give leeway
outside of that answer.
5. Open-ended questions are best used when you are trying to learn about a particular subject
while Close-ended questions are best used when you want a short, direct answer to a very
specific question.
6. Open ended questions are best when engaging in a meaningful conversation however close
ended questions are less personal in nature and are best used when the person asking wants
a quick answer.
A pie chart is also a very common two-dimensional data visualization where categories and their
values are represented. But in this case the values are proportions of a total and they are visualized
as slices of a circle (a pie)
13 | P a g e
For Classes Contact:
AGGARWAL ACADEMY (F-83, Vishnu Garden) | 7531933003
FOR MORE NOTES VISIT: http://spykan.com Like us on: http://fb.com/imspykan
In the world of data visualizations, pie charts get a lot of hate. The primary goal of data visualizations
is to clearly and concisely communicate information. The main criticism against pie charts is that it
is very difficult for the human eye to estimate the magnitude of angles, thus making visualization not
very clear. To compensate, pie charts require more labels to get the measurements across, making
them not very concise. In short, often they defeat the main purpose of a data visualization.
A great number of chart users hold the view that bar charts are much more flexible than pie charts,
because they can chart multiple categories during multiple periods. It's an ideal choice to use bar
charts if you need to make comparisons of subjects during the same period, especially when there
is a big gap between values of the segments. However, on a pie chart, instead of concrete values,
what you can see are percentages that a subject takes up of the whole. The pie stands for the overall
100%. Pie charts are not as prevalent as bar charts, because they can't display concrete data of
each segment such as values directly at a glance. Besides, readers can make comparisons of
arbitrary data segments quickly on a bar chart, but are not able to compare two slices that are not
neighbors at once.
SPYKAN.COM
By AGGARWAL ACADEMY
14 | P a g e
For Classes Contact:
AGGARWAL ACADEMY (F-83, Vishnu Garden) | 7531933003
FOR MORE NOTES VISIT: http://spykan.com Like us on: http://fb.com/imspykan
SCAN WITH
YOUR
SMARTPHONE
Note: Do not print this page. You can still write your assignment directly from
your phone or ipad or desktop or laptop.
15 | P a g e
For Classes Contact:
AGGARWAL ACADEMY (F-83, Vishnu Garden) | 7531933003