MULTIVARIATE ANALYSIS

Multivariate analysis (MVA) involves evaluating multiple variables (more than two)
to identify any possible association among them.

Multivariate analysis o ers a more complete examination of data by looking at all

possible independent variables and their relationships to one another.

Multivariate analysis refers to all statistical techniques that simultaneously

analyze multiple measurements on individuals or objects under investigation. Thus,
any simultaneous analysis of more than two variables can be loosely considered
multivariate analysis.
Univariate statistics summarize only one variable at a time.
Bivariate statistics compare two variables.
Multivariate statistics compare more than two variables.

Let’s imagine you’re interested in the relationship between a person’s social media
habits and their self-esteem. You could carry out a bivariate analysis, comparing
the following two variables:

1. How many hours a day a person spends on Social media

2. Their self-esteem score (measured using a self-esteem scale)
You may or may not nd a relationship between the two variables; however, you
know that, in reality, self-esteem is a complex concept. It’s likely impacted by
many di erent factors—not just how many hours a person spends on Instagram.
You might also want to consider factors such as age, employment status, how
often a person exercises, and relationship status (for example). In order to deduce
the extent to which each of these variables correlates with self-esteem, and with
each other, you’d need to run a multivariate analysis.

So we know that multivariate analysis is used when you want to explore more than
two variables at once.
ff
fi
ff
Caption
 There are many di erent techniques for multivariate analysis, and they can be
divided into two categories:

• Dependence techniques
• Interdependence techniques

Dependence technique:

Dependence methods are used when one or some of the variables are dependent
on others. Dependence looks at cause and e ect; in other words, can the values of
two or more independent variables be used to explain, describe, or predict the
value of another, dependent variable? To give a simple example, the dependent
variable of “weight” might be predicted by independent variables such as “height”
and “age.”

Classi cation of statistical techniques distinguished by having a variable or set of

variables identi ed as the dependent variables) and the remaining variable as
independent. The objective is prediction of the dependent variables) by the
independent variable(s). An example is regression analysis.

Examples: Multiple linear regression, Multiple logistic regression, Discriminant

Fucntion Analysis, MANOVA

A dependence technique may be de ned as one in which a variable or set of vari-

ables is identi ed as the dependent variable to be predicted or explained by other
variables known as independent variables.
An example of a dependence technique is multiple regression analysis. In contrast,
an interdependence technique is one in which no single variable or group of
variables is de ned as being independent or dependent. Rather, the procedure
involves the simultaneous analysis of all variables in the set. Factor analysis is an
example of an interdependence technique.

Interdependence technique:

Interdependence methods are used to understand the structural makeup and

underlying patterns within a dataset. In this case, no variables are dependent on
others, so you’re not looking for causal relationships. Rather, interdependence
methods seek to give meaning to a set of variables or to group them together in
meaningful ways.

• Multidimensional Scaling
• Factor analysis
• Cluster analysis
fi
fi
fi
fi
ff
fi
ff
 Classi cation of statistical techniques in which the variables are not divided into
dependent and independent sets; rather all variables are analyzed as a single set
(e.g., factor analysis).

To be considered truly multivariate, however, all the variables must be random and
interrelated in such ways that their di erent e ects cannot meaningfully be
interpreted separately.

Measurement Error and Multivariate Measurement

The use of multiple variables and the reliance on their combination (the variate) in
multivariate techniques also focuses attention on a complementary issue of
measurement error. Measurement error is the degree to which the observed values
are not representative of the "true" values.

Measurement error has many sources, ranging from data entry errors to the
imprecision of the measurement (eg imposing 7-point rating scales for attitude
measurement when the researcher knows the respondents can accurately respond
only to a 3-point rating) or the inability of respondents to accurately provide
information (e.g., responses as to household income may be reasonably accurate
but rarely precise). Thus, all variables used in multivariate techniques must be
assumed to have some degree of measurement error.

The measurement error adds "noise" to the observed or measured variables. Thus,
the observed value obtained represents both the "true" level and the noise." When
used to compute correlations or means, the "true" e ect is partially masked by the
measurement error, causing the correlations to weaken and the means to be less
precise.

CORRELATION ANALYSIS
Meaning of Correlation Analysis
Correlation is the degree of inter-relatedness among the two or more variables.
Correlation analysis is a process to nd out the degree of relationship between two
or more variables by applying various statistical tools and techniques.
According to Conner “if two or more quantities vary in sympathy, so that
movement in one tend to be accompanied by corresponding movements in the
other, then they said to be correlated.”

Uses of Correlation Analysis

1. It is used in deriving the degree and direction of relationship within the variables.
2. It is used in reducing the range of uncertainty in matter of prediction.
3. It is used in presenting the average relationship between any two variables
through a single value of coe cient of correlation.
4. In the eld of science and philosophy these methods are used for making
progressive conclusions.
5. In the eld of nature also, it is used in observing the multiplicity of the inter
related forces.
fi
fi
fi
ffi
fi
ff
ff
ff
Caption Caption
Where & Why we use Correlation

1. Prediction: Correlations can be used to help make

predictions. If two variables have been known in the past to
correlate, then we can assume they will continue to correlate
in the future. We can use the value of one variable that is
known now to predict the value that the other variable will

take on in the future. For example, we require high school

students to take the SAT exam because we know that in the
past SAT scores correlated well with the GPA scores that the
students get when they are in college. Thus, we predict high
SAT scores will lead to high GPA scores, and conversely.

2. Validity: Suppose we have developed a new test of

intelligence. We can determine if it is really measuring
intelligence by correlating the new test's scores with, for
example, the scores that the same people get on standardized IQ
tests, or their scores on problem solving ability tests, or their
performance on learning tasks, etc. This is a process for
validating the new test of intelligence. The process is based on
correlation.

3. Reliability: Correlations can be used to determine the reliability

of some measurement process. For example, we could
administer our new IQ test on two di erent occasions to the
same group of people and see what the correlation is. If the
correlation is high, the test is reliable. If it is low, it is not.
4. Theory Veri cation: Many Psychological theories make speci c
predictions about the relationship between two variables. For
example, it is predicted that parents and children's intelligences
are positively related. We can test this prediction by
administering IQ tests to the parents and their children, and
measuring the correlation between the two scores.
fi
ff
fi
 Caption

POSITIVE AND NEGATIVE CORRELATION

•The correlation between two variables is said to be positive or direct if an
increase (or a decrease) in one variable corresponds to an increase (or a
decrease) in the other.
•The correlation between two variables is said to be negative or inverse if an
increase (or a decrease) corresponds to a decrease (or an increase) in the
other.
SIMPLE, PARTIAL AND MULTIPLE CORRELATION

•Simple Correlation: It involves the study of only two variables. For example,
when we study the correlation between the price and demand of a product, it is
a problem of simple correlation.
•Partial Correlation: It involves the study of three or more variables, but
considers only two variables to be in uencing each other. For example, if we
consider three variables, namely yield of wheat, amount of rainfall and amount of
fertilizers and limit our correlation analysis to yield and rainfall, with the e ect of
fertilizers removed, it becomes a problem relating to partial correlation only.
•Multiple Correlation: It involves the study of three or more variables
simultaneously. For example, if we study the relationship between the yield of
fl
ff
wheat per acre and both amount of rainfall and the amount of fertilizers used, it
becomes a problem relating to multiple correlation.

Caption
 LINEAR AND NON-LINEAR CORRELATION (The Form (Shape) of a Relationship or
linearity)
•Linear Correlation: The correlation between two variables is said to be linear if
the amount of change in one variable tends to bear a constant ratio to the amount
of change in other variable.
•Non-linear (or Curvilinear): The correlation between two variables is said to be
non-linear or curvilinear if the amount of change in one variable does not bear a
constant ratio to the amount of change in other variable.

MULTIPLE CORRELATION (R)

Coe cient, R, is a measure of the strength of the association between the independent
(explanatory) variables and the one dependent (prediction) variable

The R squared is the percentage of variance in DV explained by the linear combination of

IVs.

In many studies related to education and psychology, we nd that the variable is

dependent on a number of other variables called independent variables.
Eg: If we take the case of one's academic achievement, it may be found associated with
or dependent on variables like intelligence, socio-economie status, education of the
parents, the methods of teaching, the quality of teachers, aptitude, interest,
environmental setup, number of hours spent on studies and so on.

Interpretation of R
Strength of the Association:
The strength of the association is measured by the Multiple Correlation Coe cient, R.
R can be any value from 0 to +1.

The closer R is to one, the stronger the linear association is.

If R equals zero, then there is no linear association between the dependent
variable and the independent variables.

Unlike the simple correlation coe cient, r. which tells both the strength and
direction of the association, R tells only the strength of the association. R is never a
negative value. This can be seen from the formula below since the square root of this
value indicates a positive root.

Multiple correlation coe cient (R) yields the maximum degree of liner relationship that can
be obtained between two or more independent variables and a single dependent variable.
(R is never signed as + or −. R (squared) represents the proportion of the total variance in
the dependent variable that can be accounted for by the independent variables.)
ffi
ffi
ffi
fi
ffi
 For example, crimes in a city may be in uenced by illiteracy, increased population and
unemployment in the city, etc. The production of a crop may depend upon amount of
rainfall, quality of seeds, quantity of fertilizers used and method of irrigation, etc. Similarly,
performance of students in university exam may depend upon his/her IQ, mother’s
quali cation, father’s quali cation, parents income, number of hours of studies, etc.
Whenever we are interested in studying the joint e ect of two or more variables on a
single variable, multiple correlation gives the solution of our problem.

In fact, multiple correlation is the study of combined in uence of two or more variables on
a single variable.

Advantages:
1. Multiple correlation provides better prediction about a variable as compared to
simple correlation because it is based on three or more variables which also helps
in making better decisions.

Disadvantages :
1. This method needs lot of calculation and cannot be easily understood by a
layman. Since this method is based on all data, it cannot be calculated if any data
is missing. Any error in data will lead to misleading results and decision-making.
[Link] (extreme observations) strongly in uence the correlation coe cient. If
we see outliers in our data, we should be careful about the conclusions we draw
from the value of r. The outliers may be dropped before the calculation for a
meaningful conclusion.
3. Correlation does not imply a causal relationship. That a change in one variable
causes a change in another.

META ANALYSIS

Meta-analysis is a subset of systematic reviews that combines pertinent quali-

tative and quantitative study data from several selected studies to develop a single
conclusion with greater statistical power.

Meta-analysis is a statistical technique for combining the results of di erent

studies to see if the overall e ect is signi cant. People usually do this when there
are multiple studies with con icting results—example: a drug does or does not
work, reducing salt in food does or does not a ect blood pressure. Meta-analysis
is a way of combining the results of all the studies; ideally, the result is the same as
doing one study with a really big sample size, one large enough to conclusively
demonstrate an e ect if there is one, or conclusively reject an e ect if there isn't
one of an appreciable size.

Meta Analysis is-

‘a single paper that summarizes and synthesizes all relevant papers to answer a
speci c research question with the help of statistics’
fi
fi
ff
fi
ff
fl
fl
fi
fl
ff
ff
fl
ff
ffi
ff
 Caption

Meta-analysis is a popular and frequently used statistical technique used to combine data
from several studies and reexamine the e ectiveness of treatment interventions.

The evidence pyramid

Meta-analysis would be used for the following purposes:

• To establish statistical signi cance with studies that have con icting results
fi
ff
fl
 • To develop a more correct estimate of e ect magnitude (E ect size is a
dimensionless estimate (ie, a measure with no units) that indicates both
direction and magnitude of the treatment e ect.
• To provide a more complex analysis of harms, safety data, and bene ts
• To examine subgroups with individual numbers that are not statistically
signi cant
If the individual studies utilized randomized controlled trials (RCT), combining
several selected RCT results would be the highest level of evidence on the
evidence hierarchy, followed by systematic reviews, which analyze all available
studies on a topic.

The Evidence Pyramid

The evidence pyramid is a hierarchical framework that organizes di erent
types of research evidence based on their strength and reliability. It is widely
used in evidence-based practice, especially in elds such as medicine,
psychology, and education. The pyramid illustrates that not all evidence is
created equal; some types of research provide more robust and reliable
information than others.

The levels of evidence pyramid provides a way to visualize both the

quality of evidence and the amount of evidence available. For example,
systematic reviews are at the top of the pyramid, meaning they are both
the highest level of evidence and the least common. As you go down
the pyramid, the amount of evidence will increase as the quality of the
evidence decreases.
Structure of the Evidence Pyramid

Filtered resources appraise the quality of studies and often make

recommendations for practice. The main types of ltered resources in evidence-
based practice are:
• systematic reviews
• critically-appraised topics
• critically-appraised individual articles

Un ltered resources:
Un ltered resources: typically original research and rst-person accounts
◦ randomized controlled trials
◦ cohort studies
◦ case-controlled studies, case series, and case report

1. Systematic Reviews and Meta-Analyses

fi
fi
fi
ff
ff
fi
fi
fi
ff
fi
ff
 ◦ De nition: Systematic reviews comprehensively summarize the results of all
available studies on a speci c topic, using a standardized and transparent
methodology. Meta-analyses statistically combine the results of multiple
studies to provide a more precise estimate of the e ect size.
◦ Systematic Review: A summary of evidence, typically conducted by an
expert or expert panel on a particular topic, that uses a rigorous process (to
minimize bias) for identifying, appraising, and synthesizing studies to answer
a speci c clinical question and draw conclusions about the data gathered.
◦ Meta-Analysis: A process of using quantitative methods to summarize the
results from multiple studies, obtained and critically reviewed using a
rigorous process (to minimize bias) for identifying, appraising, and
synthesizing studies to answer a speci c question and draw conclusions
about the data gathered.
◦ Strength: Considered the highest level of evidence because they synthesize
data from numerous high-quality studies, reducing bias and increasing
reliability.
2. Randomized Controlled Trials (RCTs)

◦ De nition: Randomized controlled trials are thought to represent the

highest quality of evidence based on their methodologic strengths of
random- ization of patient assignment and blinding of intervention and
outcome. Studies are ran- domized to eliminate selection bias and to bal-
ance confounding factors between both groups. Experimental studies where
participants are randomly assigned to either the intervention group or the
control group.
◦ Strength: High level of evidence due to the rigor of their design, which
includes control groups and randomization. The advantages of a
randomized controlled trial are the quality of the study associated with its
inherent internal validity because potential confounding variables can be
controlled for, thereby potentially providing strong evidence for cause and
e ect relationships.
◦ Example: An RCT testing a new drug for hypertension, comparing
outcomes between the drug group and a placebo group.
3. Cohort Studies

In the cohort study design, the cohort represents a group of people followed up with
time to see whether an outcome of interest develops.

A cohort study is a type of epidemiological study in which a group of people with a

common characteristic is followed over time to nd how many reach a certain
health outcome of interest (disease, condition, event, death, or a change in health
status or behavior).

Cohort studies are types of observational studies in which a cohort, or a group of

individuals sharing some characteristic, are followed up over time, and outcomes are
measured at one or more time points. Cohort studies can be classi ed as
prospective or retrospective studies,

◦ Observational studies that follow a group of people (cohort) over time to

determine how certain exposures a ect outcomes.
ff
fi
fi
fi
fi
ff
fi
ff
fi
fi
 ◦ Strength: Cohort studies can be prospective in nature meaning that
they begin at a speci ed point and are followed forward in time to
evaluate the in uence of certain prognostic factors or interventions on
the desired outcomes. Examples include prospective cohort studies
such as one evaluating refractures in patients initially treated for a
fracture.
◦ The drawback at the expense is involving a large number of subjects
and requirement of a long study period.
◦ Example 1: A cohort study tracking the health outcomes of smokers
versus non-smokers over 20 years.
◦ Example 2: The Framingham Heart Study is an example of a large
cohort study involving residents of a Massachusetts community with
identi able cardiovascular risk factors being followed up for
cardiovascu- lar events.

A retrospective cohort or historic cohort involves identifying patients from past

records and following this group backward in time from the present to the past
records. Retrospective cohort studies have the advantage of being shorter in
duration compared with prospective studies but they lack the ability to control the
selection of subjects and lack the control over outcome measurements.

Cohort studies are observational in nature and subject to systematic bias (inherent
tendency of a process to support particular outcomes).
fi
fl
fi
 4. Case-Control Studies

◦ One type of observational study is the case- control study that starts with
the identi cation of individuals who already have the outcome of interest,
cases, and are compared with a suit- able control group without the
outcome event. The relationship between a particular interven- tion or
prognostic factor and the outcome of in- terest is examined by comparing
the number of individuals with each intervention or prognos- tic factor in the
cases and controls. Case-control studies can be used to study prognostic
factors.
◦ Observational studies that compare individuals with a speci c
condition (cases) to those without the condition (controls) to identify
factors that may contribute to the condition.
◦ Strength: Useful for studying rare conditions but more prone to recall and
selection bias.
◦ Example: A case-control study investigating the relationship between
exposure to a particular chemical and the development of a rare cancer.
5. Cross-Sectional Studies

◦ De nition:Cross-sectional studies are observational studies that analyze

data from a population at a single point in time. They are often used to
measure the prevalence of health outcomes, understand determinants of
health, and describe features of a population.
◦
◦ Strength: Provide a snapshot of a population but cannot establish causality.
Unlike other types of observational studies, cross-sectional studies do not
follow individuals up over time. They are usually inexpensive and easy to
conduct. They are useful for establishing preliminary evidence in planning a
future advanced study.
◦ Example: A cross-sectional study examining the prevalence of depression
in di erent age groups within a community.
◦ Example 2: In a simple hypothetical example of a cross-sectional study, we
record the prevalence of COPD and investigate the association between
COPD and smoking status in adult patients. The outcome variable is the
presence or absence of COPD, and the exposure is the smoking status. This
study can be conducted by interviewing participants about their smoking
history and, at the same time, assessing COPD status clinically.

6. Case Reports and Case Series

◦ Descriptive studies focusing on one (case report) or a few (case series)

individuals with a particular condition. Case reports are an uncontrolled,
descriptive study design involving an intervention and out- come with a
detailed pro le of one patient. Expansion of the individual case report to
include multiple patients with an outcome of interest is a case series.
◦ Advantages/ Strength: Provide detailed information on rare conditions or
novel treatments but lack generalizability. Although descriptive stud- ies are
limited in their design to make causal inferences about the relationship
fi
ff
fi
fi
fi
 Caption
Caption

between risk factors and an outcome of interest, they are helpful in

developing a hypothesis that can be tested using an analytic study design.
◦ Example: A case report detailing a unique side e ect of a new medication.
7. Expert Opinion and Anecdotal Evidence

◦ De nition: Recommendations from persons with established expertise in a

speci c clinical area often based on clinical experience; not considered a
research method because systematic (or critical) inquiry is lacking. Opinions
from experts in the eld or anecdotal reports based on personal experience.
◦ Strength: Considered the lowest level of evidence due to the high potential
for bias and lack of systematic approach.
◦ Example: An expert panel's recommendation based on clinical experience
rather than systematic research.
Visual Representation

The pyramid typically appears as follows (from top to bottom):

1. Systematic Reviews and Meta-Analyses

2. Randomized Controlled Trials (RCTs)
3. Cohort Studies
4. Case-Control Studies
5. Cross-Sectional Studies
6. Case Reports and Case Series
7. Expert Opinion and Anecdotal Evidence
fi
fi
fi
ff
 Advantages
1. Meta-analysis provides a way to reevaluate the results of a
particular clinical question.
2. Greater statistical power.
3. Con rmatory data analysis
4. Greater ability to extrapolate to the general population a ected
5. Considered an evidence-based resource
6. A meta-analysis can help iron out any inconsistencies in data, as
long as the studies are similar.
7. They help improve precision about evidence since many studies are
too small to provide convincing data.

Disadvantages
1. Eysenck believes that meta-analysis encourages a narrow focus on
the e ect size, without consideration of other aspects of the
included studies, such as methods or individual study outcomes
that are in opposite directions. This may lead to an erroneous
conclusion.
2. Eysenck also argues that only meta-analysis of a simple question is valid
and, when several studies are positive but not signi cant because of
insu cient statistical power, using meta-analysis to examine e ect size
can lead to spurious conclusions.
3. Di cult and time-consuming to identify appropriate studies
4. Not all studies provide adequate data for inclusion and analysis
5. Requires advanced statistical techniques.

This form of research relies on combining statistical results from two or more
existing studies. When multiple studies are addressing the same problem or
question, it’s to be expected that there will be some potential for error. Most
studies account for this within their results.

Why is meta-analysis important?

•
• Meta-analyses can settle divergences between con icting studies. By
formally assessing the con icting study results, it is possible to eventually
reach new hypotheses and explore the reasons for controversy.
• They can also answer questions with a broader in uence than individual
studies. For example, the e ect of a disease on several populations across
the world, by comparing other modest research studies completed in
speci c countries or continents.
ffi
ffi
fi
fi
ff
fl
ff
fl
fl
fi
ff
ff
 Steps in a Meta Analysis
A total of seven steps need to be followed while conducting a systematic review
and/or meta- analysis. These include-
1. Formulating a research question
Perhaps the most important step of clinical research in general and meta-analysis in
particular, is to formulate the research question well. This is the uncertainty or
lacuna that the researcher is attempting to answer. Asking the right question will
lead to the right study design, an appropriate literature search strategy and
statistical analysis that will generate the right research evidence that is needed to
drive practice decisions. Thus, it ensures that the question will be answered in all
likelihood.
PICOT
A widely accepted and used acronym or mnemonic for formulating a research
question is PICO or PICO[T]. It stands for
P-Patient or Problem or Population
I-Intervention
C-Control
O-Outcome
T-Time
It essentially involves breaking down the research question into ve components
that ensures that the researcher and the reader are able to identify its’ individual
elements.
2. Writing the protocol and registering it in public domain
The protocol for a systematic review and/or meta-analysis should clearly state the
rationale, objectives, search strategy, methods, end points and quality checks that
would be used.
Registration ensures that the protocol [and the methodology within] is accessible to
all [much like registration of clinical trials before they are initiated] and will also
prevent duplication by another author.
3. Identi cation of the studies using a clear and comprehensive search
strategy
The search strategy should be all encompassing and ensure that all relevant articles
are retrieved. Serious bias and erroneous conclusions may be drawn if the search
strategy is poor.
Sensitivity of a strategy refers to identi cation of as many potentially relevant
articles as possible. Speci city refers to picking up the de nitely relevant articles. All
fi
fi
fi
fi
fi
 search strategies should aim at maximizing sensitivity so as not to miss articles that
are likely to be relevant.
Commonly searched databases include National Library of Medicine [Medline],
Experta Medica Database [EMBASE], Biosciences Information Service [BIOSIS],

4. Selecting the right studies to be included [based on the protocol]

The next step is to read the title and abstract of each reference obtained and
eliminate those that are not relevant.
5. Data Extraction
Once the nal list is ready, from each article, depending upon the protocol, we
extract the relevant information-case/disease de nitions used, key variables, study
design, outcome measures, nature of participants; therapeutic area, year of
publication; results; setting and so on. These will now need to be fed into the
software for analysis.
6. Quality Assessment of included studies
Once the number of studies to be included is rmed, it is important to assess their
quality. These include among others, the Jadad score, the CONSORT statement,
and the Cochrane Back Review Group criteria.
7. Statistical analysis
Statistical synthesis of data- Once data from all the shortlisted studies is ready, it
is fed into Revman (see later ). The two commonly used methods for analysis are
Mantel- Haenszel and DerSimonian -Lard.
Some Criticisms of Meta-Analysis
1. A single number cannot summarize an entire area of research as each study is
di erent from the other.
2. Publication bias- publication bias occurs when the outcome of an experiment or
research study biases the decision to publish or otherwise distribute it. Publishing
only results that show a signi cant nding disturbs the balance of ndings in favor
of positive results. Negative studies are less likely to be published
3. When studies are combined, it is like mixing apples and oranges [as every study
fundamentally di ers from another]
4. Garbage in, Garbage out or GIGO i.e., [the quality of what we put into a meta-
analysis will determine its nding]
5. Key studies may be ignored.
6. A meta -analysis may show a completely di erent result than a large Randomized
Controlled Trial [RCT]
ff
fi
ff
fi
fi
fi
ff
fi
fi
fi
7. The researcher may perform the meta-analysis poorly.

Publication Bias
A phenomenon in which studies with positive results have a better chance of being
published, are published earlier, and are published in journals with higher impact
factors. Therefore, conclusions based exclusively on published studies can be
misleading.

CONTENT ANALYSIS
CONCEPT AND MEANING
Content analysis is a set of procedures for collecting and organizing information in a
standardized format that allows analysts to make inferences about the
characteristics and meaning of written and other recorded materials.
Content analysis is a multipurpose research method developed speci cally for
investigating a broad spectrum of problems.
Content analysis covers both the content of the material and its structure. Content
refers to the speci c topics or themes in the material. Structure refers to form.
Careful reading of the written materials is necessary for all kinds of researches in
social sciences.
Sources of data could be from interviews, open-ended questions, eld research
notes, conversations, or literally any occurrence of communicative language (such
as books, essays, discussions, newspaper headlines, speeches, media, historical
documents). A single study may analyze various forms of text in its analysis. To
analyze the text using content analysis, the text must be coded, or broken down,
into manageable code categories for analysis (i.e. “codes”). Once the text is coded
into code categories, the codes can then be further categorized into “code
categories” to summarize data even further.

Content analysis involves a researcher establishing coding units before they

look through their qualitative data. They then go through the data and count
up the number of times each coding unit appears in the data. As a result, the
qualitative data is turned into quantitative, nominal data!

Neuendorf de nes content analysis as “ the systematic, objective, quantitative

analysis of message characteristics”.
Based on the above de nitions, the following characteristics of content analysis
emerge: objectivity, systematic and generality.
Objectivity: To have objectivity, the analysis must be carried out on the basis of
explicitly formulated rules which will enable two or more investigators to obtain the
fi
fi
fi
fi
fi
 same results from the same documents. This requirement of objectivity gives
scienti c standing to content analysis and di erentiates it from literary crtiticism.
Systematic: In a systematic analysis, the inclusion and exclusion of content or
categories is done according to consistently applied criteria of selection. This
USES OF CONTENT ANALYSIS
Content Analysis
Content analysis is a scienti c, objective, systematic, quantitative and generalizable
description of content. This method can be used to understand a wide range of
themes such as social change, cultural symbols, changing trends in the theoretical
content of di erent disciplines, changes in mass media content, nature of news
coverage of social issues, election issues as re ected in mass media.
It is used in several mass media and literature to cultural studies, psychology,
economics, political science, gender, age issues, as well as many other elds where
inquiry is made. Written documents, pictures, videos, can also be used for content
analysis.
TERMS USED IN CONTENT ANALYSIS
The following concepts and terms are frequently used in content analysis. Let us
understand these terms.
Manifest Content Analysis: It involves simply counting words, phrases, or
“surface” features of the text itself. It provides reliable quantitative data that can
easily be analyzed using inferential statistics.
Latent Content Analysis: It involves interpreting the underlying meaning of the text.
Latent analysis is di erent to manifest analysis because researcher must have a
clearly stated idea about what is being measured. The value of the latent content
analysis actually depends upon the researcher’s ability to expose previously marked
themes, messages and cultural values within the text. This analysis is widely used in
qualitative content analysis.
Coding: Coding is the process whereby raw data are systematically transformed
and aggregated into units which permit precise description of relevant content
characteristics. There are two methods of coding: (i) deductive measurement, (ii)
inductive measurement.
APPROACHES OF CONTENT ANALYSIS
Conceptual Content Analysis
Traditionally, content analysis has most often been thought in terms of conceptual
analysis. In conceptual analysis, a concept is chosen for examination and the
analysis involves quantifying and tallying its presence. It is also known as thematic
analysis. The focus here is on looking at the occurrence of selected terms within a
text or texts.
Relational Content Analysis
fi
ff
ff
fi
ff
fl
fi
Relational content analysis, like conceptual analysis, begins with the act of
identifying concepts present in a given text or set of texts. However, relational
analysis seeks to go beyond presence by exploring the relationships between the
concepts identi ed. Relational analysis has also been termed semantic analysis.
PROCEDURE INVOLVED IN CONTENT ANALYSIS
The various steps involved in content analysis are:
(i) Formulation of research questions:
By making a clear statement of the research question, the researcher can ensure
that the analysis focuses on those aspects of content which are relevant for the
research. The question should be based on a clear understanding of research needs
and the available data.
(ii) Determining materials to be included
Content analysis can be used to study any recorded materials as long as the
information is available to be reanalyzed for reliability checks.
Sampling: Sampling is necessary if the population is too extensive to be analyzed.
Thus a sample should be selected from the population in order to make valid
conclusion and generalization about a population. Simple random sampling, interval
sampling, cluster sampling and multistage sampling techniques are used in content
analysis.
(iii) Developing content categories
Content analysis is no better than its categories., since they re ect the formulated
thinking , hypotheses, and the purpose of the study. Categories provide structure
for grouping and recording units. Developing the category system to classify the
text is the heart of content analysis. Berelson (1952) has emphasized the
importance of formulating coding categories by quoting that “ content analysis
stands or falls by its categories.
(iv) Selecting and Finalizing units of analysis
The unit of analysis is the smallest unit of content that is coded under the content
category. The unit of analysis vary with the nature and objective of the analysis.
Thus, the unit of analysis might be a single word, a theme, a letter, a symbol, a news
story, a short story, a character or an entire article etc. There are two kinds of unit of
analysis : Recording unit and Context unit.
(v) Code the materials.
(vi) Analyze and interpret the results
The main objective of content analysis is to analyze the collected information with
regard to the proposed objective of the analysis. The analysis involves summarizing
the coded data, discovering patterns and relationships within the data, testing
hypotheses about the patterns and relationship to assess the validity of the analysis.
fi
fl
 ADVANTAGES AND DISADVANTAGES OF CONTENT ANALYSIS
Advantages
The Advantages of content analysis as a research technique can be summarized as
follows:
1) The greatest advantage of content analysis is its economy in terms of time and
money. There is no requirement for a large research sta . No special equipment is
needed.
2) The methods allows the correction of errors. In content analysis, it is usually
easier to repeat a portion of the study than it is in other research method.
3) Content analysis permits the study of processes occurring over a long time.
4) Content analysis has the advantage of all unobtrusive measures that it has any
e ect on the subject being studied.
5) It can present an objective account of events, themes, issues, and so forth, that
may not be immediately apparent to a reader or viewer .
6) It deals with large volume of data. Processing may be laborious but of late
computer has made it easy.
Disadvantages
1) It is limited to the examination of recorded communication. Such communication
may be oral, written, or graphic, but they must be in some fashion which permits
analysis.
2) Content analysis may not be as objective as it claims since the researcher must
select and record data accurately. In some instances the researcher must make
choices about how to interpret particular form of behaviour.
3) It has both advantages and disadvantages in terms of reliability and validity.
Problems of validity is unlikely unless researcher happen to be studying
communication process itself.
4) It describes, rather explains people’s behaviour. It does not tell us what behaviour
means to those involved and those watching.
5) By attempting to quantify behaviour, this method may not tell us very much about
the quality of people’s relationship,
ff
ff
REGRESSION ANALYSIS
The most commonly used techniques for investigating the relationship between two
quantitative variables are correlation and linear regression. Correlation quanti es the
strength of the linear relationship between a pair of variables, whereas regression
expresses the relationship in the form of an equation. For example, in patients
attending an accident and emergency unit (A&E), we could use correlation and
regression to determine whether there is a relationship between age and urea level,
and whether the level of urea can be predicted for a given age.

Regression is mainly used for two purposes. First, regression is used for prediction
and forecasting problems. Secondly, it is used to map the causality of factors, to
infer the cause and e ect relationship between the dependent and independent
variables.

Regression analysis is one of the most commonly used statistical techniques in

social and behavioral sciences as well as in physical sciences which involves
identifying and evaluating the relationship between a dependent variable and one or
more independent variables, which are also called predictor or explanatory
variables.
Linear regression explores relationships that can be readily described by straight
line. A surprisingly large number of problems can be solved by linear regression.
When there is a single continuous dependent variable and a single independent
variable, the analysis is called a simple linear regression analysis. This analysis
assumes that there is a linear association between the two variables. Multiple
regression is to learn more about the relationship between several independent or
predictor variables and a dependent or criterion variable.
Independent variables are characteristics that can be measured directly; these
variables are also called predictor or explanatory variables used to predict or to
explain the behavior of the dependent variable.

A Dependent variable is a characteristic whose value depends on the values of

independent variables.
Our dependent variable (in this case, the level of event satisfaction) should be
plotted on the y-axis, while our independent variable (the price of the event ticket)
should be plotted on the x-axis.

Once your data is plotted, you may begin to see correlations. If the theoretical
chart above did indeed represent the impact of ticket prices on event satisfaction,
then we’d be able to con dently say that the higher the ticket price, the higher the
levels of event satisfaction.

But how can we tell the degree to which ticket price a ects event satisfaction?
ff
fi
ff
fi
To begin answering this question, draw a line through the middle of all of the data
points on the chart. This line is referred to as your regression line, and it can be
precisely calculated using a standard statistics program like Excel.

The formula for a regression line might look something like Y = 100 + 7X + error
term.

This tells you that if there is no “X”, then Y = 100. If X is our increase in ticket price,
this informs us that if there is no increase in ticket price, event satisfaction will still
increase by 100 points.

3.2. Objectives of Regression Analysis

Regression analysis used to explain variability in dependent variable by means of
one or more of independent or control variables and to analyze relationships
among variables to answer; the question of how much dependent variable changes
with changes in each of the independent's variables, and to forecast or predict
the value of dependent variable based on the values of the independent's variables.
 Simple Regression Model
Simple linear regression is a statistical method that allows us to summarize and
study relationships between two continuous (quantitative) variables. In a cause and
e ect relationship, the independent variable is the cause, and the dependent
variable is the e ect.
Least squares linear regression is a method for predicting the value of a dependent
variable y, based on the value of an independent variable x.
One variable, denoted (x), is regarded as the predictor, explanatory, or independent
variable.
The other variable, denoted (y), is regarded as the response, outcome, or dependent
variable.
ff
ff