Data collection

analysis and
interpretation
Chapter – 5
 Introduction to data
collection

DATA COLLECTION IS THE IT DIFFERS ACCORDING TO THE

METHOD OF OBTAINING THE NATURE OF THE DATA WHICH
DATA DEPENDS ON OUR RESEARCH
Collection of secondary data

• In the world of research, there are two main types of data sources: primary
and secondary. While primary research involves collecting new data directly
from individuals or sources, secondary research involves analyzing existing
data already collected by someone else. Today we’ll discuss secondary
research.
• Secondary research is a research method that involves using already
existing data. Existing data is summarized and collated to increase the
overall effectiveness of the research.
• One of the key advantages of secondary research is that it allows us to gain
insights and draw conclusions without having to collect new data ourselves.
This can save time and resources and also allow us to build upon existing
knowledge and expertise.
Sources of secondary data
• When conducting secondary research, it’s important to be thorough
and thoughtful in our approach. This means carefully selecting the
sources and ensuring that the data we’re analyzing is reliable and
relevant to the research question. It also means being critical and
analytical in the analysis and recognizing any potential biases or
limitations in the data.
• Secondary research is much more cost-effective than primary research, as it
uses already existing data, unlike primary research, where data is collected
firsthand by organizations or businesses or they can employ a third party to
collect data on their behalf.
Common secondary research
methods
• Data available on internet
• Government and non-government agencies
• Public libraries
• Educational institutions
• Commercial information sources
1. Data Available on The Internet

• One of the most popular ways to collect secondary data is the

internet. Data is readily available on the internet and can be
downloaded at the click of a button.
• This data is practically free of cost, or one may have to pay a
negligible amount to download the already existing data.
Websites have a lot of information that businesses or
organizations can use to suit their research needs. However,
organizations need to consider only authentic and trusted
website to collect information.
2. Government and Non-
Government Agencies

• Data for secondary research can also be collected from some

government and non-government agencies. For example, US
Government Printing Office, US Census Bureau, and Small
Business Development Centers have valuable and relevant
data that businesses or organizations can use.
• There is a certain cost applicable to download or use data
available with these agencies. Data obtained from these
agencies are authentic and trustworthy.
. Public Libraries

• Public libraries are another good source to search for data for this
research. Public libraries have copies of important research that were
conducted earlier. They are a storehouse of important information
and documents from which information can be extracted.
• The services provided in these public libraries vary from one library to
another. More often, libraries have a huge collection of government
publications with market statistics, large collection of business
directories and newsletters.
4. Educational Institutions

• Importance of collecting data from educational institutions

for secondary research is often overlooked. However, more
research is conducted in colleges and universities than any
other business sector.
• The data that is collected by universities is mainly for primary
research. However, businesses or organizations can approach
educational institutions and request for data from them.
5. Commercial Information
Sources

• Local newspapers, journals, magazines, radio and TV stations

are a great source to obtain data for secondary research.
These commercial information sources have first-hand
information on economic developments, political agenda,
market research, demographic segmentation and similar
subjects.
• Businesses or organizations can request to obtain data that is
most relevant to their study. Businesses not only have the
opportunity to identify their prospective clients but can also
know about the avenues to promote their products or
services through these sources as they have a wider reach.
Difference between
Primary Research Secondary Research

Research is conducted first hand to obtain data. Researcher “owns” the data
Research is based on data collected from previous researches.
collected.

Secondary research is based on tried and tested data which is previously

Primary research is based on raw data.
analyzed and filtered.

The data collected fits the needs of a researcher, it is customized. Data is

Data may or may not be according to the requirement of a researcher.
collected based on the absolute needs of organizations or businesses.

As opposed to primary research, secondary research is fast and easy. It aims at

Researcher is deeply involved in research to collect data in primary research.
gaining a broader understanding of subject matter.

Primary research is an expensive process and consumes a lot of time to collect Secondary research is a quick process as data is already available. Researcher
and analyze data. should know where to explore to get most appropriate data.
Problems used in
secondary data
• Although data is readily available, credibility evaluation
must be performed to understand the authenticity of the
information available.
• Not all secondary data resources offer the latest reports
and statistics. Even when the data is accurate, it may not
be updated enough to accommodate recent timelines.
• Secondary research derives its conclusion from collective
primary research data. The success of your research will
depend, to a greater extent, on the quality of research
already conducted by primary research.
 Collection of primary data

OBSERVATION QUESTIONNAIRE EXPERIMENT WITH

SURVEY MERITS AND
DEMERITS
Questionnaire meaning and
types
Questionnaire development
process
ANALYSIS AND INTERPRETATION OF DATA

The data may be adequate, valid and reliable to any extent, but without
its proper management it can not be directly used for analysis.

The data, after collection, has to be processed and analyzed in

accordance with purpose set in research design.
Processing the Data

• Data processing is an intermediate state between

the collection of data and their analysis and
interpretation.
• It includes editing, coding, classification and
tabulation

• Editing of data is a process of examining the

collected raw data and field schedules to detect
errors and omissions and to correct these when
possible.
1. Editing for Consistency:

They should see whether answers to questions supplied by informants are consistent or not.

2. Editing of Completeness:
Examine whether all questions in the schedule or questionnaire are answered or not.

3. Editing for Accuracy:

examine whether all questions are answered correctly or not. In case, any doubt develops seek
clarification from the informants
• 4. Editing for Uniformity:
• whether all questions are interpreted in the same sense by all
informants or not.
• 5. Editors in Make Computations:
• some question response require computation from the part of
editor.
• 6. Editing for Deciphering: The editor should edit the filled schedules to
decipher unreadable entries.
Coding

• It is the process of assigning symbols, usually

numbers, to each answer which falls in a
predetermined class.
• It is the classification process necessary for
subsequent tabulation.
• through coding, the raw data are transformed
into symbols that may be tabulated and counted.
Example
Suppose the question is,

Q: Are you? Married [ ] 0

Unmarried [ ] 1
Divorcee [ ] 2
Widow [ ] 3
Others [ ] 4

Q: What is your monthly income

below 5000 5000–10,000 10000 – 15000 15000-20000

[ ] [ ] [ ] [
]
0 1 2 3
Above 20,000
[ ]
4
Classification
Classification is the process of arranging data into sequences and
groups according to their common characteristics, or separating them
into different but related parts.

For example, classification of the data relating to the family budget may be;

Food and Education and Recreation and others

clothing health entertainment
The aim of classification are given below:
§ to present the facts in a simple form by eliminating
unnecessary details. The masses of complex data will be
made simple, brief, logical and understandable;
§ to bring out clearly points of similarity and dissimilarity;
§ to facilitate comparison;
§ to bring out relationship;
§ to present a mental picture of objects or perception and
conception;
§ to prepare the basis for tabulation.
Characteristics
of good
classification
• 1. Exhaustive: The classification system must be
exhaustive.

• 2. Mutually Exclusive: The classes must not overlap

each other.

3. Stability: Classification must proceed at every stage

in accordance with one principle, and that principle
should be maintained throughout.

4. Homogeneity: The terms included in one class should be

homogenous.

5. Suitability: The classification should be suitable

according to the aim of inquiry.
 Tabulation
"

• Tabulation involves the orderly and systematic presentation of numerical

data in a form designed to elucidate the problem under investigation" (L.
R. Conner).

• Tabulation is an intermediate process between the collection of data on the

one hand and statistical analysis on the other.

• Thus tabulation is the process of summarizing raw data and displaying the
same in compact form for further analysis.
•
The purpose of tabulation is to summarize a mass of numerical information
and to present it in the simplest form consistent with the purpose.
It is a medium of communication with economy and effectiveness. Tabulation
has the following objectives to fulfill:
• to clarify the object of investigation;
•to clarify the characteristic of data;
•to present facts in the minimum of space; and
•to facilitate statistical process.
 Data analysis

Data Analysis is the process of systematically applying

statistical and/or logical techniques to describe and illustrate,
condense and recap, and evaluate data. According to Shamoo
and Resnik (2003) various analytic procedures “provide a way
of drawing inductive inferences from data and distinguishing
the signal (the phenomenon of interest) from the noise
(statistical fluctuations) present in the data”..
Concept and methods of data
analysis
• Data collected from primary and secondary
sources are evaluated and interpreted to
achieve the objectives set in the research
process
• Process of gathering, arranging ,analyzing
,modelling and transforming data with the goal
of highlighting useful information,
suggestions, conclusions and supporting
decision making.
•
Issues in Data Analysis
• Having the necessary skills to analyze
• Concurrently selecting data collection methods and appropriate analysis
• Drawing unbiased inference
• Inappropriate subgroup analysis
• Following acceptable norms for disciplines
• Determining statistical significance
• Lack of clearly defined and objective outcome measurements
• Extent of analysis
• Providing honest and accurate analysis
• Manner of presenting data
• Environmental/contextual issues
• Data recording method
• Partitioning ‘text’ when analyzing qualitative data
• Training of staff conducting analyses
• Reliability and Validity
Editing the data
• This process detects errors in the raw data and
rectifies the errors and simplifies to the act of
coding is known as editing
• Especially the data collected from the interview,
observation and questionnaire should be edited
• field editing and central editing
• Field editing refers to the editing done by the
supervisor at the field itself on the basis of
experience and observation. Codes are used and
data is edited after the completion of data
collection process
• Central editing is when data are edited before the
analysis of such data in office by the editor
alone
• It removes the wrong and incomplete data and makes
Objectives of editing
• Accuracy
• Consistent with intent of question and other
information in survey
• Data is uniformly entered
• It is complete
• Arrange to simplify coding and tabulation
Some rules to follow while
editing
• Be familiar with instructions given
• Do not destroy or erase the original entry
• Make all the edited entries on an instrument in
some distinctive color and in a standard form
• Put initial to signalize in all changed or
amended answers
• Place initial signature and date of editing
each instrument completed
Coding
• The act of assigning numbers or other symbols
to the responses of respondents so that it can
be grouped into a limited number of categories
is known as coding
• Single code should be provided to similar
information or data
• Coding is essential for analysis of data as
researchers cannot develop his/her concepts
until the data is systematized
Rules that should be followed
while coding
• Avoid unclarity and duality
• Should be defined
• Should be designed while developing data
collection techniques
• Should be recorded in code book
• Should be appropriate to research problem and
purpose
• It should be exhaustive
• It should be mutually exclusive
• It should be derived from one of the
Classification
• Classification means separating items according
to similar characteristics and grouping them
into various classes
• Some things to consider includes that data must
be collected as per research objective and then
they must be systematically arranged and
understood.
• Classification can be done on following bases
• Geographical classification
• Chronological classification
• Qualitative classification
• Quantative classification
Tabulation

• Process of arranging the data in a systematic

manner into rows and columns
• Rows are horizontal arrangements whereas
columns are vertical arrangements
• It is the final step in collection and
compilation of data
• It is done to simplify the presentation of data
• It facilitates comparison between related
information and facts \
Advantages of tabulation
• Helps to make data easily understandable
• Facilitates the comparision
• Saves time and energy
• Avoids repetition
• Can easily remember
Summarizing the data
• Researcher first of all collects the raw data .
Such raw data are edited, coded and classified
into different groups . After that , researcher
presents the data in precise form so as to make
easier for describing, analyzing , and
interpreting the data , also known as
summarizing the data
• Summary of data can be presented in the form of
table chart or in other form
Data can be presented in
• Presenting data in tables
• Presenting data in Graphs and Charts
Statistical techniques
• Analysis of data is generally classified into
two groups
• Descriptive Statistics
• Inferential Statistics
Descriptive statistics

• Statistical tools used to explain the activites

or fundamental characteristics or behavior of a
group or data is known as descriptive
statistics
• Helps to get the summarized information of
sample units
• Frequency, mean, median and mode are taken as
descriptive statistics
• Descriptive statistical tools are Frequency,
Mean, Median, Mode, Range, variation standard
deviation, inter-quartile range , perentile etc
•
Inferential statistics

• Research doesnot limit to presentation and

explanation of data
• It should be able to estimate the population
from the analysis of data collected from sample
• Thus the statistical method that helps to
estimate the population from the analysis of
sample data is known as inferential statistic.
• Census study is not possible in social science
Types

• It includes
• Estimation statistics
• Hypothesis testing
Estimation statistics
• A statistic that is used to estimate the
population parameter from the analysis of
sample is known as estimation statistic
• Estimation is made using the following two
methods
*Confidence interval or estimate
* Parameter estimation
Confidence interval or
estimate
• It helps to establish difference between two
points. It is a range of value within ,which
the analyst can declare with some confidence
of, the population parameter lies in sample.
• It helps to estimate the value or
characteristics of population analyzing the
sample
• If the campus estimates that the admission of
300-350 students and the admission fall within
these two figures then it is the estimation of
confidence interval
Parameter estimation
• It is a statistical method that helps to
estimate the relationship of variables that are
in the population is known as parameter
estimation. Liner regression, mode ,
correlation are some examples of parameter
estimation.
• Such statistic helps to estimate the
relationship of variables that are in the
population by the analysis of sample .
Hypothesis testing
• Inference on population characteristics or
parameters are often made based on sample
observations , especially when population is
large and it may not be able to enumerate all
the sampling units belonging to the population
• In doing so one has to take the help of certain
assumption about the characteristics of the
population which are known as hypothesis.
Procedure for testing
hypothesis
1. State the null and alternative hypothesis :
researcher should set the hypothesis based on
the literature . Researcher should set both
null and hypothesis
2. Establish a level of significance : the level
of significance signifies the probability of
committing errors that is accepted . It is
setup at the discretion of the researcher
depending on the sensitivity of the issue . If
5% level of significance is accepted , the
researcher is willing to take 5 % risk of
rejecting the null hypothesis even if its true
3. Choose a suitable test statistics
For the purpose of rejecting or accepting null
hypothesis , asuitable statistical tool is
chosen which is known as test statistics. If the
tabulated p-value is greater than level of
significance then null hypothesis is rejected,
otherwise accepted

4. Obtain the critical value

We shall consult the appropriate table like Z
table or t table for finding the critical value
. It defines the region of rejection from the
region of acceptance
• Conclusions
by comparing the tabulated and calculated value
researcher draws the conclusions. If calculated
value is less than or equals to tabulated value
at a certain level of significance, then null
hypothesis is accepted . It means there is no
significant difference between sample and
population parameter otherwise, alternative
hypothesis is accepted.
Parametric test for Testing
Hypothesis
• The test of hypothesis assuming that the
samples are taken from normally distributed
population is known as parametric test/
statistics
• Non- parametric tools are used when data are
collected using nominal and ordinal scale.
Important parametric tests in
Testing hypothesis
• Z- test
• T-test
• Two independent sample test
• Two related sample test
• K- independent sample test
Analysis of Variance (ANOVA)
• To study over more than two sample at a time,
analysis of variance (ANOVA) method is used.
• This method helps to study the area of variance
and degree of variance
Important Non-parametric tests
for testing hypothesis
• Chi-square test: Chi-square test is rigorously
used as non-parametric test in the research.
Generally, chi-square test is used to check the
dependency of two or more than two groups.
• Correlation : A Pearson correlation matrix
indicates the direction, strength and
significance of relationship between two
variables among the variables in the study.
The correlation is derived by assessing the
variations in one variable to another variable.
Various methods of correlation
• Product-moment correlation
• Rank order correlation
• Partial correlation
• Multiple correlation
• Regression analysis : A statistical technique
that is used to see the degree of relationship
between dependent and independent variable is
known as regression analysis
• Time series analysis : A statistical technique
that is used to study the variation in the
variables based on time is known as time series
analysis.
• Multi-variate analysis: It is concerned with
statistical methods designed to elicit
information from these kinds of data sets
because the data include simultaneous
measurements on many variables . The body of
methodology is called multi-variate analysis.
Analysis of Qualitative Data
• Data , which is expressed in subjective way or
in language but not in numbers and collected
through observations, is known as qualitative
data . Analysis of such data to known the
trends of activities or events or get in-depth
knowledge
Methods of analyzing
Qualitative Data
• Content Analysis : Content analysis is a
research technique for the systematic
,objective and quantitative description of the
content of data collected through interviews,
questionnaires, schedules and other expression
in written or verbal form.
• Narrative Analysis : A technique of recording
and analyzing the information and subject based
on the story of the respondents or people
related to an event or subject matter is known
as narrative analysis
• Thematic analysis : A technique of qualitative
data analysis that is used to identify the
major points of data ,analyze them and prepare
Use of statistical and
mathematical tools in
marketing research
• https://www.slideshare.net/murathotirajendranat
hbabu/statistical-tools-in-research-231169355
Types of scale
• https://www.britannica.com/topic/measurement-
scale
Types of scale
• Likert scale: most widely used scale to measure
the attitude, norms values and behavior of
individuals or groups . In this scale ,
respondents are asked to give their opinion
limiting with given scales , and respondents
show their opinion limiting with given scales ,
and respondents show their agreement or
disagreement on the statement provided in
questionnaires. It shows not only the agreement
or disagreement but also shows the degree of
agreement and disagreement. It can be made
clear from the following example
I am happy with the customer
service of Worldlink
Communications
1. Strongly disagree
2. Disagree
3. Neutral
4. Agree
5. Strongly agree
• Previous example is trying to know whether the
employees are committed towards organization or
not. Respondents are asked to select any one
alternative that present their opinion. Such
opinion are analyzed using
statistical/mathematical tools and researcher
finds out whether they are committed towards
organization or not.
2. Graphic rating scale
• In this scale the respondents are asked to
indicate the response to a particular question
by placing a mark at a appropriate point to
express their opinions. Such marketing helps to
understand the opinion of respondents. It is
also commonly used in business research.
• On the scale of 1 to 10, how do you rate your
departmental head?

• Ask the respondents to mark at one point

ranging from 0 to 10.
• Such selection presents the opinion of
respondent. On the basis of the opinion of
employees ,a researcher finds out whether
employees take positively or negatively to
his/her departmental head.
3. Itemized rating scale
• In this scale researcher provides a category
of responses out of which the respondent
selects one that is most relevant for answering
the questions under study. It is popular in
business research because of its adaptability
in many situations where variables are to be
measured. The following examples illustrate the
use of this scale :

• How do you rate your interest in changing

organizational policies ?
• Extremely poor, not at all, some what well very
• Respondents are asked to select most relevant
option to know the opinion of the respondents
4. Rank order rating scale
• In this scale, respondents are asked to rank
the given items or product on the basis of
their priority. They arrange them ranging from
top most priority to lowest priority.
• It is a comparative method. It is used to
measure the priority of the organization
towards any subject. It compels to the
respondents to segregate the product or issues
from one group to next group on the basis of
priority. It only develops ordinal data.
• For example, a researcher asked to the
customers to identify the rank on the basis of
5. Semantic differential scale
• The semantic differential is a seven point
rating scale with endpoint associated with
bipolar levels that have implied meanings. In
an application, respondents rate objects or
issues on one of two bipolar objectives, such
as beautiful or ugly .
• the semantic differential scale is based on
the assumption that an object can have several
dimensions on an implied meaning . The meanings
are located in multi-disciplinary property
space called sematic space. Implied meanings
are suggested in addition to the explicit
Other simple scales
• Simple category questions
• Multiple choice questions
• Open-ended questions
Meaning and significance of
interpretation of facts
• https://ebooks.inflibnet.ac.in/hsp16/chapter/in
terpretation/#:~:text=Through%20interpretation%
2C%20the%20investigator%20can,significance%20of
%20his%20research%20findings.
THANK YOU