RESEARCH METHODOLOGY

Unit-03:
Testing of hypotheses
Dr.Roopa Ravish
Department of CSE
RESEARCH METHODOLOGY

Topic: Basic concepts - Procedure for hypothesis

testing, flow diagram for hypothesis testing
Testing of Hypotheses I: Introduction

∙Hypothesis is usually considered as the Principal Instrument of research

∙Function is to suggest new experiments and observation.

∙Hypothesis testing is often used strategy for deciding whether sample data offer
such support for hypothesis that generalization can be made.

∙Ordinarily, when one talks about hypothesis, one simply means a mere
assumption or some supposition to be proved or disproved. But for a researcher
hypothesis is a formal question that he intends to resolve.
 What is hypothesis testing?
∙ Mere assumption or some supposition to be proved or disproved.
∙ Defined as a
“Proposition or a set of proposition set forth as an explanation for the occurrence
of some specified group of phenomena either asserted merely as a provisional
conjecture to guide some investigation or accepted as highly probable in the light
of established facts.”

Quite often a research hypothesis is a predictive statement, capable of

being tested by scientific methods, that relates an independent variable
to some dependent variable.
Examples

a. “Students who receive counselling will show a greater increase in creativity than
students not receiving counselling”

b. “The automobile A is performing as well as automobile B”.

These are hypotheses capable of being objectively verified and tested. Thus, we may
conclude that a hypothesis states what we are looking for and it is a proposition which
can be put to a test to determine its validity.
Characteristics of Hypothesis
1) Should be clear and precise.
2) Should be capable of being tested.
a) A Hypotheses is testable if other deductions can be made from it
which, in turn, can be confirmed or disproved by observation.
3) Should state relationship between variables.
4) Should be limited in scope and must be specific.
5) Hypo should be stated in simple terms and easily
understandable.
6) Hypo should be consistent with most known facts.
7) Hypo should be amenable to testing within reasonable time.
Basic concepts: Null Hypothesis and Alternate Hypothesis
In context of Statistical Analysis:
Null Hypothesis – If we compare method A and method B and both are equally
good (H0).
Example : “No difference between coke and diet coke”.

As against this, we may think that the method A is superior or the method B is
inferior, we are then stating what is termed as alternative hypothesis. The null
hypothesis is generally symbolized as H0 and the alternative hypothesis as Ha.

Alternate Hypothesis – If method A is superior than B (H1).

Example : “There is difference between coke and diet coke”.
Example
 Null Hypothesis
∙Suppose we want to test the hypothesis that the population mean (µ) is equal
to the hypothesized mean (µ H0) = 100.

∙Then we would say that the null hypothesis is that the population mean is
equal to the hypothesized mean 100 and symbolically we can express as:

H0: µ = µH0 = 100

If our sample results do not support this null hypothesis, we should conclude that something
else is true.
What we conclude rejecting the null hypothesis is known as alternative hypothesis. Set of
alternatives to the null hypothesis is referred to as the alternative hypothesis. If we accept
H0 , then we are rejecting Ha and
If we reject H0 , then we are accepting Ha.
Possible alternate hypothesis
For H0: µ = µH0 = 100 , we may consider three possible
alternative hypotheses as follows* :
 Possible alternate hypothesis
In the choice of null hypothesis, the following considerations are usually kept in
view:
(a) Alternative hypothesis is usually the one which one wishes to prove and the
null hypothesis is the one which one wishes to disprove.
Thus, a null hypothesis represents the hypothesis we are trying to reject, and
alternative hypothesis represents all other possibilities.

(b) If the rejection of a certain hypothesis when it is actually true involves great
risk, it is taken as null hypothesis because then the probability of rejecting it when
it is true is α (the level of significance) which is chosen very small.

(c) Null hypothesis should always be specific hypothesis i.e., it should not state
about or approximately a certain value.
 Statistically Significant

∙ Measurements are done on the two categorical variables on a sample of

individuals from a population, and they are interested in whether or not
there is a relationship between the two variables in the population.

∙ a relationship as strong as the one observed in the sample (or stronger)

would be unlikely without a real relationship in the population, then the
relationship in the sample is said to be statistically significant.

∙ The notion that it could have happened just by chance is deemed to be

implausible.
 Level of Significance

This is a very important concept in the context of hypothesis testing. It is always some
percentage (usually 5%) which should be chosen with great care, thought and reason.

In case we take the significance level at 5 per cent, then this implies that H0 will be
rejected when the sampling result (i.e., observed evidence) has a less than 0.05
probability of occurring if H0 is true.

In other words, the 5% level of significance means that researcher is willing to take as
much as a 5% risk of rejecting the null hypothesis when it (H0 ) happens to be true.

Thus the significance level is the maximum value of the probability of rejecting H0 when
it is true and is usually determined in advance before testing the hypothesis.
 Decision rule or test of hypothesis

Given a hypothesis H0 and an alternative hypothesis Ha , we make a rule which is

known as decision rule according to which we accept H0 (i.e., reject Ha ) or reject H0
(i.e., accept Ha ).
Example: If H0 is that a certain lot is good (there are very few defective items in it)
against Ha , that the lot is not good (there are too many defective items in it), then we
must decide the number of items to be tested and the criterion for accepting or
rejecting the hypothesis.
We might test 10 items in the lot and plan our decision saying that if there are none
or only 1 defective item among the 10, we will accept H0 otherwise we will reject H0
(or accept Ha ). This sort of basis is known as decision rule
 Decision rule or test of hypothesis

Given a hypothesis H0 and an alternative hypothesis Ha , we make a rule which is

known as decision rule according to which we accept H0 (i.e., reject Ha ) or reject H0
(i.e., accept Ha ).
Example: If H0 is that a certain lot is good (there are very few defective items in it)
against Ha , that the lot is not good (there are too many defective items in it), then we
must decide the number of items to be tested and the criterion for accepting or
rejecting the hypothesis.
We might test 10 items in the lot and plan our decision saying that if there are none
or only 1 defective item among the 10, we will accept H0 otherwise we will reject H0
(or accept Ha ). This sort of basis is known as decision rule
 Type I and Type II errors

Type I error is denoted by α (alpha) known as α error, also called the level of
significance of test; and Type II error is denoted by β (beta) known as β error.
 Type I and Type II errors

The probability of Type I error is usually determined in advance and is understood as

the level of significance of testing the hypothesis.
If type I error is fixed at 5 per cent, it means that there are about 5 chances in 100
that we will reject H0 when H0 is true.
We can control Type I error just by fixing it at a lower level. For instance, if we fix it at
1 per cent, we will say that the maximum probability of committing Type I error would
only be 0.01.
 Type I and Type II errors

But with a fixed sample size, n, when we try to reduce Type I error, the probability of
committing Type II error increases. Both types of errors cannot be reduced
simultaneously.
There is a trade-off between two types of errors.
To deal with this trade-off in business situations, decision-makers decide the
appropriate level of Type I error by examining the costs or penalties attached to both
types of errors.
Hence, in the testing of hypothesis, one must make all possible effort to strike an
adequate balance between Type I and Type II errors.
One tailed and two tailed test
We test 3 types of Hypotheses given by:

1) H0:µ =µH0 Aganist Ha:µ ≠ µH0

2) H0 :µ = µH0 Aganist Ha :µ > µH0
or
H0 :µ <= µH0 Aganist Ha :µ > µH0
3) H0 :µ = µH0 Aganist Ha :µ < µH0
or
H0 :µ >= µH0 Aganist Ha :µ < µH0
If we have ≠ in alternate hypotheses – Two tailed test
If we have > sign in alternate hypotheses – right tailed
If we have < sign in alternate hypotheses – left tailed
One tailed and two tailed
test λ

H0:µ =µH0 H0 :µ = µH0 H0 :µ = µH0

Ha:µ ≠ λµH0
Ha :µ < µH0 Ha :µ > µH0
One tailed and two tailed test

It should always be remembered that accepting H0 on the basis of sample

information does not constitute the proof that H0 is true. We only mean that
there is no statistical evidence to reject it, but we are certainly not saying that
H0 is true (although we behave as if H0 is true).
 Steps in Hypothesis Testing
The factors that affect the level of
significance are: (a) the magnitude of the
difference between sample means; (b) the
size of the samples; (c) the variability of
measurements within samples The choice generally remains between normal
distribution and the t-distribution.
Type of Hypothesis Tests:

Sl No Type of Alternate NullHypothesis

Hypothesis Test Hypothesis
1 Left Tailed Test < ≥

2 Right Tailed Test > ≤

3 Two Tailed Test ≠ =

Large-Sample Tests for a Population Mean

Different Hypothesis Tests

Hypothesis Test Test Statistic

z-test z- statistic
t-test t- statistic
Chi square test Chi square statistic
Large-Sample Tests for a Population Mean

Note:

Hypothesis Test Population Population S.D.

S.D. known unknown

𝑛 < 30 Small Use z- test Use t-test

sample drawn
from Normal
population
𝑛 ≥ 30 Large Use z- test Use z- test
sample Or t- test
Example:

• The article “Wear in Boundary Lubrication” (S. Hsu, R.

Munro, and M. Shen, Journal of Engineering Tribology,
𝟐𝟎𝟎𝟐: 𝟒𝟐𝟕– 𝟒𝟒𝟏) discusses several experiments involving
various lubricants.

• In one experiment, 𝟒𝟓 steel balls lubricated with purified

paraffin were subjected to a 𝟒𝟎 𝒌𝒈 load at 𝟔𝟎𝟎 𝒓𝒑𝒎 for
𝟔𝟎 𝒎𝒊𝒏𝒖𝒕𝒆𝒔.
Example:

• The average wear, measured by the reduction in

diameter, was 𝟔𝟕𝟑. 𝟐 𝝁𝒎, and the standard deviation
was 𝟏𝟒. 𝟗 𝝁𝒎.

• Assume that the specification for a lubricant is that the

mean wear be less than 𝟔𝟕𝟓 𝝁𝒎.

• Find the 𝑷 -value for testing 𝑯𝟎 : 𝝁 ≥ 𝟔𝟕𝟓 versus

𝑯𝟏 : 𝝁 < 𝟔𝟕𝟓.
Solution:
Solution:
Solution:

• The null hypothesis is that the lubricant does not meet the
specification, and that the difference between the sample mean
of 673.2 and 675 is due to chance.

• The alternate hypothesis is that the lubricant does indeed meet

the specification.

𝟔𝟕𝟑. 𝟐 − 𝟔𝟕𝟓
𝒛 = = −𝟎. 𝟖𝟏
𝟐. 𝟐𝟐
Soution:
• The 𝑷 − 𝒗alue is 𝟎. 𝟐𝟎𝟗 .

• Therefore if 𝑯𝟎 is true, there is a 𝟐𝟎. 𝟗% chance to

observe a sample whose disagreement with 𝑯𝟎 is as least
as great as that which was actually observed.

• Since 𝟎. 𝟐𝟎𝟗 is not a very small probability,

• we do not reject 𝑯𝟎 .

• Instead, we conclude that 𝑯𝟎 is plausible.

Example:

• A scale is to be calibrated by weighing a 1000 g test

weight 60 times.

• The 60 scale readings have mean 1000.6 g and standard

deviation 2 g.

• Find the P-value for testing

𝑯𝟎 ∶ 𝝁 = 𝟏𝟎𝟎𝟎 𝒗𝒆𝒓𝒔𝒖𝒔 𝑯𝟏 ∶ 𝝁 ≠ 𝟏𝟎𝟎𝟎.
Solution:

𝑯𝟎 ∶ 𝝁 = 𝟏𝟎𝟎𝟎 𝒗𝒆𝒓𝒔𝒖𝒔 𝑯𝟏 ∶ 𝝁 ≠ 𝟏𝟎𝟎𝟎.

We assume 𝑯𝟎 is true

𝟏𝟎𝟎𝟎. 𝟔 − 𝟏𝟎𝟎𝟎
𝒛 =
𝟎. 𝟐𝟓𝟖

= 𝟐. 𝟑𝟐
Solution:

• The P-value is the sum of the areas in both of these tails,

which is 0.0204.

• Therefore, if 𝑯𝟎 is true, the probability of a result as

extreme as or more extreme than that observed is only
0.0204.

• The evidence against 𝑯𝟎 is pretty strong. It would be

prudent to reject𝑯𝟎 and to recalibrate the scale.
Example:
• A sample of 𝟒𝟎𝟎 male students is found to have a mean
height 𝟔𝟕. 𝟒𝟕 inches.

• Can it be reasonably regarded as a sample from a large

population with mean height 𝟔𝟕. 𝟑𝟗 inches and standard
deviation𝟏. 𝟑𝟎 inches? Test at 5% level of significance.
Solution:

𝑯𝟎 : 𝝁 = 𝟔𝟕. 𝟑𝟗inches

𝑯𝟏 : 𝝁 ≠ 𝟔𝟕. 𝟑𝟗inches

𝑿 − 𝝁𝟎 67.47 − 67.39
𝒛 = 𝝈 = = 𝟏. 𝟐𝟑𝟏
𝒏 130 / 𝟒𝟎𝟎

H0 is accepted.
Drawing Conclusions from the Results of Hypothesis Tests

• The only two conclusions that can be reached in a hypothesis

test are that

• 𝑯𝟎 is false or that 𝑯𝟎 is plausible.

• One can never conclude that 𝑯𝟎 is true.

Drawing Conclusions from the Results of Hypothesis Tests

• How do we know when to reject 𝑯𝟎 ?

• The smaller the 𝑷-value, the less plausible 𝑯𝟎 becomes.

• A common rule of thumb is to draw the line at 𝟓%. According

to this rule of thumb, if 𝑷 ≤ 𝟎. 𝟎𝟓, 𝑯𝟎 is rejected; otherwise
𝑯𝟎 is not rejected.
Drawing Conclusions from the Results of Hypothesis Tests

• The smaller the 𝑷-value, the more certain we can be that 𝑯𝟎 is

false.

• The larger the 𝑷-value, the more plausible 𝑯𝟎 becomes, but we

can never be certain that 𝑯𝟎 is true.
Drawing Conclusions from the Results of Hypothesis Tests

• There is no sharp dividing line between conclusive evidence

against 𝑯𝟎

• So while this rule of thumb is convenient, it has no real

scientific justification.
Drawing Conclusions from the Results of Hypothesis Tests

• A rule of thumb suggests to reject 𝑯𝟎 whenever 𝑷 ≤ 𝟎. 𝟎𝟓.

Drawing Conclusions from the Results of Hypothesis Tests

Statistical Significance:

• Whenever the P-value is less than a particular threshold, the

result is said to be “statistically significant” at that level.

• So, for example, if 𝑷 ≤ 𝟎. 𝟎𝟓 , the result is statistically

significant at the 𝟓% level; if 𝑷 ≤ 𝟎. 𝟎𝟏 , the result is
statistically significant at the 𝟏% level, and so on.
Statistical Significance:

• If a result is statistically significant at the 𝟏𝟎𝟎𝜶% level, we can

also say that the null hypothesis is “rejected at level 𝟏𝟎𝟎𝜶%.”
Drawing Conclusions from the Results of Hypothesis Tests

• The null hypothesis is rejected at the 𝟏𝟎𝟎𝜶% level.

• When reporting the result of a hypothesis test, report the

𝑷 −value, rather than just comparing it to 𝟓% 𝒐𝒓 𝟏%.
Drawing Conclusions from the Results of Hypothesis Tests

• Let 𝜶 be any value between 0 and 1. Then, if 𝑷 ≤ 𝜶,

• The result of the test is said to be statistically significant at

the 𝟏𝟎𝟎𝜶% level.
Drawing Conclusions from the Results of Hypothesis Tests

Example:

• A hypothesis test is performed of the null hypothesis

𝐇𝟎 : 𝛍 = 𝟎. 𝐓𝐡𝐞 𝐏 − 𝐯𝐚𝐥𝐮𝐞 𝐭𝐮𝐫𝐧𝐬 out to be 𝟎. 𝟎𝟑.

• Is the result statistically significant at the 𝟏𝟎% level? The

𝟓% level? The 1% level?

• Is the null hypothesis rejected at the 10%level? The 𝟓% level?

The𝟏% level?
Drawing Conclusions from the Results of Hypothesis Tests

Solution:
• The result is statistically significant at any level greater than
or equal to 𝟑%.

• Thus it is statistically significant at the 𝟏𝟎% and 𝟓% levels,

but not at the 1% level.

• Similarly, we can reject the null hypothesis at any level

greater than or equal to 𝟑%

• So 𝑯𝟎 is rejected at the 𝟏𝟎% and 𝟓% levels, but not at the

𝟏% level.
Drawing Conclusions from the Results of Hypothesis Tests

The P-value Is Not the Probability That H0 Is True

It makes sense to define the P-value as the probability of observing an

extreme value of a statistic such as X, since the value of X could come
out differently if the experiment were repeated. The null hypothesis, on
the other hand, either is true or is not true. The truth or falsehood of H0
cannot be changed by repeating the experiment. It is therefore not
correct to discuss the “probability” that H0 is true.
THANK YOU

Dr. Roopa Ravish

Department of Computer Science & Engineering
RESEARCH METHODOLOGY

Unit-03:
Testing of hypotheses
Dr.Roopa Ravish
Department of CSE

1
RESEARCH METHODOLOGY

Topic: Basic concepts - Procedure for hypothesis

testing, flow diagram for hypothesis testing

2
Tests of Hypothesis

(a) Parametric tests or standard tests of hypotheses

(b) Non-parametric tests or distribution-free test of hypotheses.

3
 Tests of Hypothesis

• Parametric tests usually assume certain properties of the parent population from which we draw
samples.

• Assumptions like observations come from a normal population, sample size is large,
assumptions about the population parameters like mean, variance, etc., must hold good before
parametric tests can be used.

• But there are situations when the researcher cannot or does not want to make such assumptions. In
such situations we use statistical methods for testing hypotheses which are called non-parametric
tests.

• Besides, most non-parametric tests assume only nominal or ordinal data, whereas parametric tests
require measurement equivalent to at least an interval scale.
• Non-parametric tests need more observations than parametric tests to achieve the same size of Type
I and Type II errors.

4
z-test vs t-test

5
 Eg: t-test
The specimen of copper wires drawn form a large lot have the following breaking strength (in kg.
weight):
578, 572, 570, 568, 572, 578, 570, 572, 596, 544
Test (using Student’s t-statistic)whether the mean breaking strength of the lot may be taken to be
578 kg. weight (Test at 5 per cent level of significance).

6
 Eg: t-test
The specimen of copper wires drawn form a large lot have the following breaking strength (in kg.
weight):
578, 572, 570, 568, 572, 578, 570, 572, 596, 544
Test (using Student’s t-statistic)whether the mean breaking strength of the lot may be taken to be
578 kg. weight (Test at 5 per cent level of significance).
Eg: t-test
Eg: t-test
Eg:
Eg:
Eg:
 Chi-Square tests
A chi-square goodness of fit test determines if a sample data matches a population.

Used to obtain confidence interval estimate of unknown population variance.

Non-parametric test and as such no rigid assumptions are necessary in respect of type of
population.

chi-square can be used (i) as a test of goodness of fit and (ii) as a test of independence.

As a test of goodness of fit, test enables us to see how well does the assumed theoretical
distribution (such as Binomial distribution, Poisson distribution or Normal distribution) fit to the
observed data.
If the calculated value of is less than the table value at a certain level of significance, the fit is
considered to be a good one which means that the divergence between the observed and expected
frequencies is attributable to fluctuations of sampling. But if the calculated value of is greater
than its table value, the fit is not considered to be a good one.
 Chi-Square tests
As a test of independence, test enables us to explain whether or not two attributes are associated (Independent
Variable/Dependent Variable).
On this basis we first calculate the expected frequencies and then work out the value of . If the calculated value
of is less than the table value at a certain level of significance for given degrees of freedom, we conclude that
null hypothesis stands which means that the two attributes are independent or not associated .
But if the calculated value of is greater than its table value, our inference then would be that null hypothesis
does not hold good which means the two attributes are associated and the association is not because of some chance
factor but it exists in reality. It may, however, be stated here that is not a measure of the degree of relationship
or the form of relationship between two attributes, but is simply a technique of judging the significance of such
association or relationship between two attributes.
Conditions for chi-square test.
STEPS INVOLVED IN APPLYING CHI-SQUARE TEST
Example
Example
Example
Example 2
Example 2
Example 2
 Problem - 3

Genetic theory states that children having one parent of blood type A and the other of blood type
B will always be of one of three types, A, AB, B and that the proportion of three types will on
an average be as 1 : 2 : 1. A report states that out of 300 children having one A parent and B
parent,30 per cent were found to be types A, 45 per cent per cent type AB and remainder type
B. Test the hypothesis by test

Class Obs Freq Exp Freq Oi – Ei (Oi – Ei)^2/Ei

A
AB
B
Answer: Problem - 3
Problem
Problem
The table shows the data obtained during outbreak of smallpox.Test the effectiveness of the vaccine at 5%
significance level.
H0: The vaccine has no effect; Ha: Vaccine is effective. Exp Freq Attacked Not Attacked Row Tol
Ob Freq Attacked(A) Not Attacked(NA) Row Tol
Vaccinated 500*216/2000 446 500
Vaccinated( 31 469 500 =54
V) Not 162 1500*1784/20 1500
Not 185 1315 1500 Vaccinated 00= 1338
Vaccinated
(NV) Col Total 216 1784 2000

Col Total 216 1784 2000

Class Obs Freq Exp Freq Oi – Ei (Oi – Ei)^2/Ei

V-A 31 54 -23 -23^2/54=9.80
V-NA 469 446 23 23^2/446=1.19
NV-A 185 162 23 23^2/162=3.27
NV-NA 1315 1338 -23 23^2/1338=0.40
Home work -1

29
Home work
THANK YOU

Dr. Roopa Ravish

Department of Computer Science & Engineering
RESEARCH METHODOLOGY

Topic: Basic concepts - ANALYSIS OF VARIANCE (ANOVA)

Dr. Roopa Ravish

Department of Computer Science & Engineering
1
 ANOVA: Analysis of Variance
• Used of hypothesis testing when >2 population/samples cases are involved



 ANOVA: Analysis of Variance
• This technique is used when multiple sample cases are involved.

• The significance of the difference between the means of two samples can be judged
through either z-test or the t-test, but the difficulty arises when we happen to examine the
significance
of the difference amongst more than two sample means at the same time.

• The ANOVA technique enables us to perform this simultaneous test and as such is
considered to be an important tool of analysis in the hands of a researcher. Using this
technique, one can draw inferences about whether the samples have been drawn from
populations having the same mean.
 ANOVA: Analysis of Variance
• The ANOVA technique is important in the context of all those situations where we want to
compare more than two populations such as in comparing the yield of crop from several
varieties of seeds, the gasoline mileage of four automobiles, the smoking habits of five
groups of university students and so on.

• Therefore, one quite often utilizes the ANOVA technique and through it investigates the
differences among the means of all the populations simultaneously.

• “The essence of ANOVA is that the total amount of variation in a set of data is broken down
into two types, that amount which can be attributed to chance and that amount which can be
attributed to specified causes.”

• There may be variation between samples and also within sample items. ANOVA consists in
splitting the variance for analytical purposes.
 ANOVA: Analysis of Variance
Hence, it is a method of analysing the variance to which a response is subject into its various
components corresponding to various sources of variation.

Through this technique one can explain whether various varieties of seeds or fertilizers or soils
differ significantly so that a policy decision could be taken accordingly, concerning a particular
variety in the context of agriculture researches.

Thus, through ANOVA technique one can, in general, investigate any number of factors which are
hypothesized or said to influence the dependent variable.

If we take only one factor and investigate the differences amongst its various
categories having numerous possible values, we are said to use one-way ANOVA and in case we
investigate two factors at the same time, then we use two-way ANOVA. In a two or more way
ANOVA, the interaction (i.e., inter-relation between two independent variables/factors), if any,
between two independent variables affecting a dependent variable can as well be studied for better
decisions.
 ANOVA: Analysis of Variance
THE BASIC PRINCIPLE OF ANOVA

we have to make two estimates of population variance viz., one based on between samples
variance and the other based on within samples variance.
Then the said two estimates of population variance are compared with F-test, wherein we work
out.

This value of F is to be compared to the F-limit for given degrees of freedom.

If the F value we work out is equal or exceeds* the F-limit value we may say that there are
significant differences between the sample means.
ANOVA TECHNIQUE: One Way (Single Factor)
ANOVA TECHNIQUE: One Way (Single Factor)
ANOVA TECHNIQUE: One Way (Single Factor)
ANOVA TECHNIQUE: One Way (Single Factor)
ANOVA TECHNIQUE: One Way (Single Factor)
ANOVA TECHNIQUE: One Way (Single Factor)
ANOVA TECHNIQUE: One Way (Single Factor)
ANOVA TECHNIQUE: One Way (Single Factor)
ANOVA TECHNIQUE: One Way (Single Factor)
ANOVA
Compare 3
population means Is one mean so far away , it is
to see if they are from a different population
different

Do all the 3 means

come from the Do all of these come from
same population different population

Per Acre yeild

Plot of Variety of Wheat
land A B C
1 6 5 5
2 7 5 4
3 3 3 3
4 8 7 4
 ANOVA

Per Acre yield

Plot of Variety of Wheat

land A B C

1 6 5 5

2 7 5 4

3 3 3 3

4 8 7 4

𝑥 6 5 4

n = total number of items in all the samples

(n – 1) = (k – 1) + (n – k)
i.e., n1 + n2 + … + nk
k = number of samples
 ANOVA
Source of Sum of Deg of Mean Sqaure(MS) F- Ratio
Variation Squares (SS) Freedom
Between SS Between (k-1) MS Between = MS between
SS Between/(k-1) MS Within
Within SS Within (n-k) MS Within =
SS within/(n-k)
Total SS Total (n -1)

18
 ANOVA

Per Acre yield

Plot of Variety of Wheat

land A B C

1 6 5 5

2 7 5 4

3 3 3 3

4 8 7 4

𝑥 6 5 4

n = total number of items in all the samples

i.e., n1 + n2 + … + nk
k = number of samples
 ANOVA

Per Acre yield

Plot of ariety of Wheat

land A B C

1 6 5 5

2 7 5 4

3 3 3 3

4 8 7 4

𝑥 6 5 4

n = total number of items in all the samples

i.e., n1 + n2 + … + nk
k = number of samples
 ANOVA

Per Acre yield

Anova: Single Factor

Plot of ariety of Wheat

SUMMARY
land A B C Groups Count Sum Average Variance
A 4 24 6 4.666667
1 6 5 5 B 4 20 5 2.666667
C 4 16 4 0.666667
2 7 5 4

3 3 3 3 ANOVA
Source of
Variation SS df MS F P-value F crit
4 8 7 4 Between
Groups 8 2 4 1.5 0.274016 4.256495
𝑥 6 5 4 Within Groups 24 9 2.666667

n = total number of items in all the samples Total 32 11

i.e., n1 + n2 + … + nk
k = number of samples
THANK YOU

Dr. Roopa Ravish

Department of Computer Science & Engineering

22
RESEARCH METHODOLOGY

Topic: Data Representation

Department of Computer Science & Engineering

1
Research Methodology
Scientific Publishing- Data representation

PRESENTATION OF DATA

refers to the organization of data into tables,

graphs or charts, so that logical and statistical
conclusions can be derived from the collected
measurements.

Data may be presented in(3 Methods):

-Textual
- Tabular or
- Graphical.

Text, tables, and graphs are effective communication

media that present and convey data and information
2
Research Methodology
Scientific Publishing- Data representation

3
Research Methodology
Scientific Publishing- Data representation

A Table refers to any data which is presented in

orderly rows across and/or down the page, often
enclosed within borders.

A Figure refers to any other form

of presentation such as a bar or pie chart, a graph,
a diagram, a map, a photograph, a line drawing or
a sample of material.

4
Research Methodology
Scientific Publishing- Data representation

Tabular Presentation of data is a method

of presentation of data.

It is a systematic and logical arrangement

of data in the form of Rows and Columns
with respect to the characteristics of data.

It is an orderly arrangement which is

compact and self-explanatory.

5
Research Methodology
Scientific Publishing- Data representation

•In a tabular presentation, data is arranged in columns

and rows, and the positioning of data makes
comprehension and understanding of data more
accessible.
Table number. It is included for identification and
becomes easy for reference in future.
•Title.
•Stub.
•Caption.
•Body.
•Footnote.

6
Research Methodology
Scientific Publishing- Data representation

7
Research Methodology
Scientific Publishing- Data representation

8
Research Methodology
Scientific Publishing- Data representation

9
 Research Methodology
Scientific Publishing- Data representation
Advantages of table:

A table facilitates representation of even large amounts of data in

an attractive, easy to read and organized manner.

The data is organized in rows and columns.

Table is one of the most widely used forms

of presentation of data since data tables are easy to construct and
read.

One of the major benefits of using an Excel table is that it will

automatically expand when you add a new record – even if it is
added at the end of the table. So the range of cells that your name
refers to will also automatically expand. This is known as a dynamic
range. 10
Research Methodology
Scientific Publishing- Data representation

Table and its Characteristics:

1. A table is perceived as a two-dimensional

structure composed of rows and columns.

2. Each table row represents a single entity

occurrence within the entity set.

3. Each table column represents an attribute,

and each column has a distinct name.

11
Research Methodology
Scientific Publishing- Data representation

Numerical Tables:

These are the most common types of data, which

typically represent quantitative data, but sometimes
may present a combination of quantitative and
qualitative data.

As its name suggests, most of the body of

the table consists of specific number values.

12
Research Methodology
Scientific Publishing- Data representation

Features for good table

Attractive: It should be attractive as to
leave good impression on reader.
Clarity: A table should be simple and clear i.e. can
easily be understood.
Manageable size: Too much details should not be
there and the size of the table should be medium i.e.
neither too big nor too small.

13
Research Methodology
Scientific Publishing- Data representation

14
Research Methodology
Scientific Publishing- Data representation

15
Research Methodology
Scientific Publishing- Data representation

16
Research Methodology
Scientific Publishing- Data representation

17
 Research Methodology
Scientific Publishing- Data representation
Visualization, as the word suggests is the art of representing
information in visual form like diagrams, charts or images. The
visuals are usually supported by narration from the presenter.

18
Research Methodology
Scientific Publishing- Data representation

19
Research Methodology
Scientific Publishing- Data representation

20
Research Methodology
Scientific Publishing- Data representation

21
Research Methodology
Scientific Publishing- Data representation

22
Research Methodology
Scientific Publishing- Data representation

23
Research Methodology
Scientific Publishing- Data representation

24
Research Methodology
Scientific Publishing- Data representation

25
Research Methodology
Scientific Publishing- Data representation

26
Research Methodology
Scientific Publishing- Data representation

27
Research Methodology
Scientific Publishing- Data representation

28
THANK YOU

29
RESEARCH METHODOLOGY

Topic: Results and Discussion (Data

Interpretation)

Department of Computer Science & Engineering

1
Step by step:
An effective DISCUSSION
Results - Findings

• It describes what you found in your research, without

discussion, interpretation or reference to the
literature.

• Just the facts, presented as tables, figures, interview

summaries and/or descriptions of what you found that
is important and noteworthy.

• The objective is to present a simple, clear and

complete account of the results of your research.
Discussion: is considered as the heart of the paper

Purpose: To state your

• Interpretations ;
• Opinions;
• Explain the implications of your findings and
• Make suggestions for future research.

Function:
• To answer questions posed in the Introduction,
• Explain how the results support the answers and
• How the answers fit in with existing knowledge on the
topic.
Discussion
Not mere details about the results;
interpret and explain the results.

1. (Un)expected results
2. Reference to previous research
3. Explanation
4. Exemplification
5. Deduction and hypothesis
6. Recommendation

Provide
a commentary and not a reiteration of the results
Discussion
• Begin by briefly summarizing the previous chapters,
then discuss what you found.

• Provide meaningful answers to the question

• Interpret objectively and subjectively and to make

references to what others have said on the subject.

• Make sure that every conclusion you draw is

defensible and not just your own personal opinion.
Discussion- Technique

1.

Organize the Discussion from the

specific to the general:
your findings to the literature, to theory, to practice
Discussion- Technique

2.

Begin by re-stating the hypothesis you were testing

and answering the questions posed in the
introduction
Discussion- Technique

3.

• Explain how your results relate to expectations

• Clearly state why they are acceptable and
• How they are consistent or fit with published
knowledge
Discussion- Technique

4.

Address all the results regardless of whether or not

the findings were statistically significant.
Discussion- Technique

5.
Describe the patterns, principles, and relationships
shown by each major finding/result and put them in
perspective.
The sequencing:
First - state the answer,
Second - support with relevant results,
Third - cite the work of others.
Discussion- Technique

6.
Defend your answers by explaining both why your
answer is satisfactory and why others are not.

Only by giving both sides to the argument can you

make your explanation convincing.
Discussion- Technique

7.

Discuss and evaluate conflicting explanations of the

results.

This is the sign of a good discussion.

Discussion- Technique

8.

Discuss any unexpected findings.

When discussing an unexpected finding, begin the

paragraph with the finding and then describe it.
Discussion- Technique

9.

Identify potential limitations and weaknesses and

comment on the relative importance of these to
your interpretation of the results and how they may
affect the validity of the findings.

When identifying limitations and weaknesses, avoid

using an apologetic tone.
Discussion- Technique

10.

• Summarize concisely (brief, and specific)

• Explain implication and importance
• Provide recommendations (not >2) for further
research.
Discussion- Do’s & Don’ts

DO: Provide context and explain why people should care.

DON'T: Simply rehash your results.

DO: Emphasize the positive.

DON'T: Exaggerate.

DO: Look toward the future.

DON'T: End with it.
RESEARCH METHODOLOGY

Topic: Summary and Conclusions

Department of Computer Science & Engineering

1
Summary, Conclusions &
Recommendation
 Summary, Conclusions &
Recommendation

• The summary is a brief restatement of the main

findings presented under each factor

• The conclusion is an interpretation of the facts

you gathered and discussed.
It is not a repetition of the facts.
It is not an action that one must take.
Summary

• The Summary section may be the Conclusion

• Summary: summarizes the findings/conclusion
• Conclusion: ultimate take-away message
• Future work
• Limitation
The Purpose of Conclusion
1. Tie together, integrate and synthesize the various
issues raised in the discussion sections, while
reflecting the -Introduction, Problem Statement or
Objectives

2. Provide answers to the research question (s)

3. Identify the theoretical implications of the study

4. Highlights the study limitations

5. Provide direction and areas for future research

Conclusion
Succinctly summarize implications

No sweeping statements or conclusions that reach beyond

your data

Present the bottom line message, point, value of the

described study

Tell the reader what they should take away

• Advantages
• Novelty
• Limitations
• Suggestions
The content of a good conclusion
• Be a logical ending synthesizing what has been previously
discussed and never contain any new information or
material

• It must pull together all of the parts of your argument and

refer the reader back to the focus you have outlined in your
introduction and to the central topic and thereby create a
sense of unity.

• Be very systematic, brief and never contain any new

information

• Add to the overall quality and impact of the research.

The content of a good conclusion
Restate the research questions which reinforces the importance of the study
and its findings.

Empirical Findings: summary of the main finding in the different chapters

provide answers to or the specific research

Theoretical Implication: Present a modest position of how the work has

contributed to existing understanding of concepts that has been investigated.

Recommendation for future research: Further research that has not been
covered but is worthwhile to investigate in the near future.

Limitation of the study: Identify the various limitations which were encountered
during the sampling, lab work, data collection and analysis stages of the research
or project.
 Different
Styles Of
Referencing
 Agenda ……
• Objective.
• What is reference style.
• Why to reference.
• Types of references.
• Different styles of writing reference.
A. Harvard style of referencing.

B. American Psychological Association style (APA) .

C. Vancouver style.

D. MLA citation style (modern language association).

E. The Chicago manual of style .

F. Royal society of chemistry style

• Conclusion
 style ????
 A referencing style is a specific format for presenting in-
text references (footnotes or endnotes),

and bibliography.

 It is a act of referring.

Reference :
• The action of mentioning or alluding to something or,
• The use of a source of information in order to ascertain
something.
 Why to reference??

 Proves that substantial research has been done to support

our analysis .

 Enables others to follow up on our work .

 Gives credit to other people's work .

 Avoids charges of plagiarism.

 Required to support all significant statements.

 Used to indicate the origin of material & source for research
& further reading.
 Types of references
 Journal Reference

 Book Reference

 Internet Reference
Reference Elements
•Authors name
•Article title
•Journal name
•Year
•Volume
•Page numbers
Different styles of writing references:

 Harvard style of referencing.

 American Psychological Association style (APA) .

 Vancouver style.

 MLA citation style (modern language association ).

 The Chicago manual of style .

 Royal society of chemistry style.

 Harvard style of referencing
 Author’s name followed by its initials.
 Year of publication.
 Article title with single quotation mark followed by full stop.
 Name of Journal in italic form.
 Volume followed by a comma
 Issue no. in bracket.
 Page no.

Example
1. Padda, J. (2003) ‘creative writing in coventry'. Journal of writing studies 3
(2), 44-59.
2. Lennernas, H. (1995) ‘Experimental estimation of the effective unstirred
water layer thickness in the human jejunum & its importance in oral drug
absorption’. Eur. J. pharm sci (3), 247-253.
 Vancouver style.

 Author Surname followed by Initials.

 Title of article followed by double quotation.
 Title of journal (abbreviated).
 Date of Publication followed by semicolon.
 Volume Number.
 Issue Number in bracket.
 Page Number.

 Example
1. Haas AN, Susin C, Albandar JM, et al. "Azithromycin as a adjunctive
treatment of aggressive periodontitis: 12-months randomized clinical
trial". N Engl J Med. 2008 Aug; 35(8):696-704.
 Vancouver Style does not use the full journal name, only the commonly-
used abbreviation: “New England Journal of Medicine” is cited as “N Engl J
Med”.
 MLA citation style (modern
language association )

• Authors name.
• Title of article.
• Name of journal.
• Volume number followed by decimal & issue no.
• Year of publication.
• Page numbers.
• Medium of publication.

Example
1. Matarrita-Cascante, David. "Beyond Growth: Reaching Tourism-Led
Development." Annals of Tourism Research 37.4 (2010): 1141-63. Print
 American Psychological Association style

 Author’s name followed by its initials.

 Year of publication.
 Article title followed by full stop.
 Name of Journal in italic form
 Volume followed by a comma
 Page no.

Example
1. Alibali, M. W., Phillips, K. M., & Fischer, A. D. (2009). Learning
new problem-solving strategies leads to changes in problem
representation. Cognitive Development, 24, 89-101.
The Chicago manual of style

 Name of author.
 Article title in double quotation mark.
 Title of journal in italic.
 Volume.
 Year of publication.
 Page no.

Example
1. Joshua I. Weinstein, “The Market in Plato’s ” Classical
Philology, 104 (2009): 440.
Royal society of chemistry styling
 INITIALS. Author’s surname.
 Title of journal (abbreviated).
 Year of publication.
 Volume number.
 Pages no.

Example
H. Yano, K. Abe, M. Nogi, A. N. Nakagaito, J. Mater. Sci.,
2010, 45, 1–33.
 Difference between Reference List and
Bibliography

Referencelist sources we have

cited in our text arranged in the order they appeared within the text.
It is usually put at the end of our work but it can also appear as a
footnote (at the bottom of the page), or endnote (at the end of each
chapter) which serves a similar purpose.

Bibliography – a separate list of sources we have

consulted but not specifically cited in our work including background
reading. It is arranged alphabetically by the author's surname.
• We conclude that there are many standard style used for
referencing, we can use any one of them.

• It gives us a standard format of presenting or reference.

• Supports or significant statement and helps to know origin of work.

• Plagiarism can be avoided.

 Reference
 Art Of Writing & Publishing In Pharmaceutical Journals By Ajay
Semalty, Shaiiendra K. Saraf, Mona Semalty, Shubhini A. Saraf, Ranjit
Singh, 1st Edition: Pharma Book Syndicate, Hyderabad, Pg. No. 80.

 Library Services Help Sheet, London South Bank University, Perry

Library & Learning Resources Pg. No. 2.

 Different Style Of Writing References In A Research Report By

Caryn Anderson.
 Coventry University Harvard Reference Style Guide By Lisa
Ganobcsik Williams & Catalina Neculai, Pg. No. 7.