B.

TECH SECOND
YEAR
ACADEMIC YEAR: 2020-2021

COURSE NAME: ENGINEERING MATHEMATICS-IV

COURSE CODE : MA 2201
LECTURE SERIES NO : 35
CREDITS : 03
MODE OF DELIVERY : ONLINE (POWER POINT PRESENTATION)
FACULTY : DR VIVEK SINGH
EMAIL-ID : [email protected]
PROPOSED DATE OF DELIVERY: as per the schedule lecture
SESSION OUTCOME “ANALYZE THE HYPOTHESIS”
ASSIGNMENT
QUIZ
MID TERM EXAMINATION –I
ASSESSMENT
CRITERIA'S
& II
END TERM EXAMINATION
 PROGRAM
OUTCOMES
MAPPING
WITH CO5

 Engineering Knowledge: Understand the key

concept of random variable, its probability
distribution including mean, expectation, variance
and moments
INTRODUCTION TO HYPOTHESIS TESTING
PROBABILITY AND STATISTICS

Introduction to Hypothesis Testing​

Learning Objectives

At the end of this topic, you will be able to: A hypothesis is an assumption, an idea that is
Understand parameters and statistics proposed for the sake of argument so that it
can be tested to see if it might be true.
Understand hypothesis and its different types

Identify the difference between null hypothesis and

alternative hypothesis

Understand the test of significance

PROBABILITY AND STATISTICS

Introduction to Hypothesis Testing​

Parameters

Definition:
Parameters are the numbers that summarise data for an entire population.

Example:
The following are some of the examples of parameters:

10% of students voted for a particular measure. There were only finite number of students, say 30;
you can count what every single one of them voted for.

45% of 120 workers at a particular manufacturing company were paid less than ₹ 20,000 per year.
We have the payroll data of all the workers.
PROBABILITY AND STATISTICS

Introduction to Hypothesis Testing​

Statistics

Definition:
Statistics are the numbers that summarise data from a sample, i.e., some subset of the entire
population.
Examples:
The following are some of the examples of statistics:

55% of Indian residents agreed with the latest health care proposal. It was not
possible to ask every individual in the country due to the large population.
Therefore, to estimate this result, researchers must have taken a sample and given
an overall result.

A survey was conducted in a country to find the most favourite fruit. This was
estimated by taking a sample of 100 people.
PROBABILITY AND STATISTICS

Introduction to Hypothesis Testing​

Difference Between Parameters and Statistics

1. Parameters describe the whole population.

2. It varies from sample to sample.

1. Statistics describe a part of the population.

2. It does not vary from sample to sample.
PROBABILITY AND STATISTICS

Introduction to Hypothesis Testing​

Hypothesis

Meaning:
A hypothesis is an assumption or an idea that is testable on the basis of observed data
modelled as the realised value taken by a collection of random variable.

Examples:

A test which assumes that the data has a normal distribution.

A test which assumes that two samples were drawn from the same underlying
population distribution.
PROBABILITY AND STATISTICS

Introduction to Hypothesis Testing​

Test of Significance

Definition:
A test of significance is a formal procedure for comparing data with a hypothesis, the truth of which is
being assessed.

A significance test starts with a careful statement of

the claims (hypothesis) being compared.

The results of significance test are expressed in terms

of a probability that measures how well the data and
the hypothesis agree.
 PROBABILITY AND STATISTICS

Introduction to Hypothesis Testing​

Example of Test of Significance

We have an IQ score of population, and the

population mean IQ is 100.

In order to determine if the sample mean is

significantly different than the population mean, a
statistical test must be conducted to provide Population mean
evidence. IQ=100

Researchers must collect statistical evidence to make

a claim, and this is done by conducting a test of
statistical significance.

60 85 100 115 130

PROBABILITY AND STATISTICS

Introduction to Hypothesis Testing​

Hypothesis Testing

Definition: Hypothesis testing is a way to test the results of a survey or an experiment to see
if it has the meaningful results. It has two parts– Null Hypothesis and Alternate Hypothesis.
The general idea of hypothesis testing involves the following:

Either
Choose
Figure out State the choose or
the test
the null null reject the
you need
hypothesis hypothesis null
to perform
hypothesis
PROBABILITY AND STATISTICS

Introduction to Hypothesis Testing​

Null Hypothesis

The null hypothesis, is the commonly accepted fact. As researchers work to reject, nullify or
disprove it, that’s why it is called null hypothesis.

Features:
The following are some of the features of null hypothesis:

It is always about a population parameter not about a sample statistic.

It refers to the status quo or historical value.

It always contains ‘=‘, ‘≤’ or ‘≥’ sign.

It may or may not be rejected.

PROBABILITY AND STATISTICS

Introduction to Hypothesis Testing​

Alternate Hypothesis

The alternate hypothesis, , is an alternative to the null hypothesis. In many cases, it will just be
the opposite of the null hypothesis. The alternate hypothesis is what we usually test in the
hypothesis testing.

Features:
The following are some of the features of alternate hypothesis:

It is generally the hypothesis that the researchers are trying to prove.

It challenges the status quo or historical value.

It never contains ‘=‘, ‘≤’ or ‘≥’ sign.

It may or may not be proven.

PROBABILITY AND STATISTICS

Introduction to Hypothesis Testing​

Examples of Null and Alternative Hypothesis

Milk samples were tested for their freezing point. Using a

sample, we can test whether the supplier’s claim (hypothesis)
that a batch of milk has an average freezing temperature of
.

One possible hypothesis is that the supplier did not add water
to the milk. This hypothesis is the null hypothesis:

The alternate hypothesis states that the supplier added water

to the milk, that’s why the freezing temperature increased:
 PROBABILITY AND STATISTICS

Introduction to Hypothesis Testing​

Simple and Composite Hypothesis

Simple Hypothesis:
The statistical hypothesis which specifies the population completely is known as simple
hypothesis. The simple hypothesis is defined as

• Smoking leads to cancer.

Examples • Higher ratio of unemployment leads to crimes.

Composite Hypothesis:
The statistical hypothesis which does not specify the population completely is known as composite
hypothesis. The composite hypothesis is defined as or in either case, we cannot know the exact
distribution.

The higher ratio of unemployment, poverty and illiteracy leads

Examples
to crimes like dacoit etc.
PROBABILITY AND STATISTICS

Introduction to Hypothesis Testing​

Testing About a Population Mean

When we conduct a significance test, then there are three possible alternative hypothesis. Their
general forms are given below:

Right-tailed Left-tailed Two-tailed

•: •: •:

where is a predetermined number and is the mean of the population.

PROBABILITY AND STATISTICS

Introduction to Hypothesis Testing​

Right-Tailed Alternative Hypothesis

Definition:
When the researchers try to prove that the mean in the sample is specifically higher than the
population mean, then it is known as the right-tailed hypothesis.

The general form of right-tailed hypothesis is and : .

Population mean

Sample mean
PROBABILITY AND STATISTICS

Introduction to Hypothesis Testing​

Left-Tailed Alternative Hypothesis

Definition:
When the researchers try to prove that the mean in the sample is specifically lower than the
population mean, then it is known as the left-tailed hypothesis.

The general form of right-tailed hypothesis is and : .

Population mean

Sample mean
PROBABILITY AND STATISTICS

Introduction to Hypothesis Testing​

Two-Tailed Alternative Hypothesis

Definition:
When the researchers suspect that the sample mean could either be lower or higher than the
population mean, then the alternate hypothesis would be two-sided hypothesis.

The general form of two-tailed hypothesis is and : .

Population mean

Sample mean Sample mean

PROBABILITY AND STATISTICS

Introduction to Hypothesis Testing​

FEATURES
 Power of prediction
 Clarity

 Simplicity

 Testibility

 Relevant to problems
 Specific

 Fruitfulfor new discoveries

 Consistancy and harmony.

 Closest to observable things.

 PROBABILITY AND STATISTICS

Introduction to Hypothesis Testing​

In the context of testing of hypotheses, there are basically two types of errors
we can make:-

Errors

Type-I Errors Type-II Errors

PROBABILITY AND STATISTICS

Introduction to Hypothesis Testing​

Type-I Errors
A type I error, also known as an error of the first kind, occurs when the null hypothesis (H0) is
true, but is rejected. The alpha symbol, α, is usually used to denote a Type I error.

A type I error may be compared with a so called false positive

A Type I error occurs when we believe a falsehood

An α of 0.05 indicates that you are willing to accept a 5% chance that you are wrong when you
reject the null hypothesis.
It usually equals the significance level of a test.

To lower this risk, you must use a lower value for α. However, using a lower value for alpha
means that you will be less likely to detect a true difference if one really exists.
 PROBABILITY AND STATISTICS

Introduction to Hypothesis Testing​

EXAMPLES
 Let’s say that our null hypothesis is that there is “no wolf present.”A
type I error (or false positive) would be “crying wolf” when there is
no wolf present.
 That is, the actual condition was that there was no wolf present;

however, the shepherd wrongly indicated there was a wolf present by

calling “Wolf! Wolf!”
 This is a type I error or false positive error.
 PROBABILITY AND STATISTICS

Introduction to Hypothesis Testing​

Building inspection
 An inspector has to choose between certifying a building as
safe or saying that the building is not safe.
 There are two hypotheses: Building is safe or not safe.

 : Building is not safe

 : Building is safe
 PROBABILITY AND STATISTICS

Introduction to Hypothesis Testing​

Type-II Errors
 Type II error, also known as an error of the second kind, occurs when the null
hypothesis is false, but erroneously fails to be rejected.
 Type II error means accepting the hypothesis which should have been rejected.

 A type II error may be compared with a so-called False Negative.

 A Type II error is committed when we fail to believe a truth.

 A type II error occurs when one rejects the alternative hypothesis (fails to reject the

null hypothesis) when the alternative hypothesis is true.

 The rate of the type II error is denoted by the Greek letter β (beta) and related to the

power of a test (which equals 1-β ).

 PROBABILITY AND STATISTICS

Introduction to Hypothesis Testing​

EXAMPLE
 Hypothesis: "Adding fluoride to toothpaste protects against cavities."
 Null hypothesis (H ): "Adding fluoride to toothpaste has no effect on cavities."
0
 This null hypothesis is tested against experimental data with a view to nullifying it
with evidence to the contrary.
 A type II error occurs when failing to detect an effect (adding fluoride to toothpaste

protects against cavities) that is present. The null hypothesis is false (i.e., adding
fluoride is actually effective against cavities), but the experimental data is such that
the null hypothesis cannot be rejected.
 PROBABILITY AND STATISTICS

Introduction to Hypothesis Testing​

HYPOTHESIS STATEMENT EXAMPLE
 PROBABILITY AND STATISTICS

Introduction to Hypothesis Testing​

In the tabular form two error can be presented as follows:

Null hypothesis Null hypothesis

(H0) is (H0) is
true false

Reject null Type I Correct

hypothesis error outcome
False True positive
positive
Fail to reject Correct Type II
null outcome error False
hypothesis True negative
negative
 PROBABILITY AND STATISTICS

Introduction to Hypothesis Testing​

If there is a diagnostic value distinguish the choice of two means, moving it to

decrease type I error will increase type II error (and vice-versa)
PROBABILITY AND STATISTICS

Introduction to Hypothesis Testing​

Graphical depiction of the relation between Type I and Type II errors

 PROBABILITY AND STATISTICS

Introduction to Hypothesis Testing​

What are the differences between Type I errors and Type II errors?

Type I Error Type II Error

 A type I error is when a statistic calls for  A type 2 error is when a statistic does not give
the rejection of a null hypothesis which is enough evidence to reject a null hypothesis even
factually true. when the null hypothesis should factually be
 We may reject H0 when H0 is true rejected.
is known as Type I error .  We may accept H0 when infect H0 is not true is
 A type 1 error is called a false known as Type II Error.
positive.  A type 2 error is a false negative.
 It denoted by the Greek letter α (alpha).  It denoted by the *Beta*
 Null hypothesis and type I error  Alternative hypothesis and type II error
PROBABILITY AND STATISTICS

Introduction to Hypothesis Testing

Summary

In this topic, you learnt:

Parameters describe the whole population whereas the statistics describe a part of the population.

The results of significance test are expressed in terms of a probability that measures how well the
data and the hypothesis agree.

Different tests for testing hypothesis can be categorised into one-tailed test and two-tailed test.
THANK YOU