Hypothesis Testing and Errors in Hypothesis: Dr. Abdur Rasheed

Hypothesis Testing
And Errors in
Hypothesis
Dr. Abdur Rasheed

Inferential Statistics
Consist of generalization from sample to population,

performing estimation and hypothesis test, determining
relationship among variables and making predictions.
Inferential Statistics
Let’s say you wanted to know about the favorite ice cream flavors of
everyone in the world. Well, there are about 8 billion people in the
world, and it would be impossible to ask every single person about
their ice cream preferences.
Instead, you would try to sample a representative population of
people and then extrapolate your sample results to entire
population.
While this process isn’t perfect and it is very difficult to avoid errors,
it allows researcher to make well reasoned inference about the
population in question. This is the idea behind the inferential
statistics.
Hypothesis
A hypothesis is an assumption about one or more population
parameters.
A parameter is a characteristic of the population, like its mean or

variance.
The parameter must be identified before analysis.
I assume the mean

height of a class is
5.3 feet
Purpose of hypothesis
The purpose of hypothesis testing is to aid clinician,

researcher or administrator in reaching a conclusion
about a population by examining a sample from
that population.
Examples of hypothesis
• Mean height of IoBM students is μ = 5.1 feet
• The population mean monthly cell phone bill of city is: μ = 425
• The average number of TV sets in U.S. Homes is equal to three; μ = 3

Hypothesis
Remember
• It Is always about a population parameter, not

about a sample statistic.
• Sample evidence is used to assess the probability
that the claim about the population parameter is
true
Hypothesis
Statistical Research
hypothesis hypothesis
Research Hypothesis
• It is the assumption that motivate the
research.
• It is usually the result of long observation by
the researcher.
• This hypothesis led directly to the second
type of hypothesis
Statistical Hypothesis
• This is stated in a way that can be evaluated by
appropriate statistical technique.
Statistical hypothesis
It is composed of two types:
Null hypothesis( Ho):

It is the particular hypothesis under test, and it is
the hypothesis of “no difference”
Alternative hypothesis (HA):

Apposite null hypothesis
Properties of Null hypothesis
Null Hypothesis H0
• Always contains ‘=‘ sign i.e., (=, ≤, ≥ )
e.g., the average height of students of a class is 5.6
feet. H0 : µ = 5.6
• Null hypothesis may or may not be rejected.
Properties of Alternative hypothesis
• Apposite of null hypothesis
contain signs of (≠, <, > )
• e.g., the average height of students of a class is
< 5.6 feet. HA : µ < 5.6
• Alternative hypothesis may or may not be
accepted.
• Is generally the hypothesis that the researcher is
trying to prove. Evidence is always examined
with respect to H1, never with respect to H0.
Remember
What we hope or expect to able to conclude as a result of the

test usually should be placed in alternative hypothesis
The null hypothesis should contain statement of equality (=, ≤, ≥ )
The alternative hypothesis should contain statement with (≠, <, > )
The null hypothesis is the hypothesis that is tested.
The null and alternative hypothesis are complementary

Examples 1
A generic brand of the anti-histamine Diphenhydramine markets a
capsule with a 50 milligram dose. The manufacturer is worried that the
machine that fills the capsules has come out of calibration and is no
longer creating capsules with the appropriate dosage.
Null Hypothesis: On the average, the dosage sold under this
brand is 50 mg (population mean dosage = 50 mg).
Alternative Hypothesis: On the average, the dosage sold under
this brand is not 50 mg (population mean dosage ≠ 50 mg).

Examples 2
To test whether cloud seeding increases the average annual rainfall in
an area which usually has an average annual rainfall of 20 cm, we
define the null and alternative hypotheses as follows,
where μ represents the average rainfall after cloud seeding.
H0: µ ≤ 20 (i.e. average rainfall does not increase after cloud

seeding)
HA: µ > 20 (i.e. average rainfall increases after cloud seeding)

Examples 3
Researchers are interested in the mean age of certain population. Let
us say that they are asking the question. Can we conclude that the
mean age of this population is different from 30 years?
H0: µ = 30 years (i.e. population mean age is not different from 30)
HA: µ ≠ 30 years (i.e. population mean age is different from 30)

Examples 4
Bon Air Elementary School has 1000 students. The principal of the school
thinks that the average IQ of students at Bon Air is at least 110. To prove
her point, she administers an IQ test to 20 randomly selected students.
Among the sampled students, the average IQ is 108 with a standard
deviation of 10.
H0: µ ≥ 110 (i.e. students’ average IQ is at least 110)
HA: µ < 110 (i.e. students’ average IQ is less than 110)

Errors
Rejection of null hypothesis means acceptance of

alternative hypothesis
Rejection of alternative hypothesis means

acceptance of null hypothesis
We test null hypothesis
We will either reject or accept null
hypothesis
There is a possibility that we may reject true null hypothesis or
accept false null hypothesis

Errors
Type I error
This error is committed when true null hypothesis is rejected.
Reject null hypothesis when it is true
The rate of type of I error is also called size of the test
The probability of committing type I error is α (level of significance)
If type I error is fixed as 5%, it means that there are about 5
chance in 100 that we will reject null hypothesis when null
hypothesis is true.
Errors
Type II error
This error is committed when false null hypothesis is accepted

Accept = Fail to reject.
Accept null hypothesis when it is false
The probability of committing type II error is β
NOTE: we do not say that we accept the null hypothesis if

a statistician is around…
Fail to reject false null hypothesis

Actual state of nature
H0 is true H0 is false
Type I
Correct
Reject H0 Error
Decision
Type II
Accept H0 Correct
Error
Power of the test
Probability of rejection of false null hypothesis
“Power” of a test is the probability of rejecting null
hypothesis when it is false.
“Power” = 1 -P(Type II error)
To minimize the P(Type II error), we equivalently want to
maximize power.
But power depends on the value under the alternative
hypothesis ...
Power of the test
Power is probability, so number between

0 and 1.
0 is bad!
1 is good!
Need to make power as high as

possible.
Hypothesis Testing…
The probability of a Type I error is denoted as α (Greek letter alpha).
The probability of a type II error is β (Greek letter beta).
The two probabilities are inversely related. Decreasing one increases

the other, for a fixed sample size.
In other words, you can’t have  and β both real small for
any old sample size. You may have to take a much larger
sample size, or in the court example, you need much more
evidence.
11.26
The goal is to determine whether there is enough evidence to infer that
the alternative hypothesis is true, or the null is not likely to be true.
There are two possible decisions:
Conclude that there is enough evidence to support the alternative
hypothesis. Reject the null.
Conclude that there is not enough evidence to support the
alternative hypothesis. Fail to reject the null.

A Type I error is the probability of telling you things are wrong, given
that things are correct.
A Type II error is the probability of telling you things are correct, given
that things are wrong.
Power is the probability of telling you things are wrong, given that
things are wrong.

Hypothesis Testing and Errors in Hypothesis: Dr. Abdur Rasheed

Uploaded by

Copyright:

Available Formats

Hypothesis Testing and Errors in Hypothesis: Dr. Abdur Rasheed

Uploaded by

Document Information

Original Description:

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Hypothesis Testing and Errors in Hypothesis: Dr. Abdur Rasheed

Uploaded by

Copyright:

Available Formats

Hypothesis Testing

Dr. Abdur Rasheed

Consist of generalization from sample to population,

A parameter is a characteristic of the population, like its mean or

I assume the mean

The purpose of hypothesis testing is to aid clinician,

• Mean height of IoBM students is μ = 5.1 feet

• The average number of TV sets in U.S. Homes is equal to three; μ = 3

• It Is always about a population parameter, not

• Sample evidence is used to assess the probability

that the claim about the population parameter is

• It is usually the result of long observation by

• This hypothesis led directly to the second

Null hypothesis( Ho):

Alternative hypothesis (HA):

What we hope or expect to able to conclude as a result of the

The null hypothesis should contain statement of equality (=, ≤, ≥ )

The null hypothesis is the hypothesis that is tested.

The null and alternative hypothesis are complementary

Null Hypothesis: On the average, the dosage sold under this

brand is 50 mg (population mean dosage = 50 mg).

Alternative Hypothesis: On the average, the dosage sold under

this brand is not 50 mg (population mean dosage ≠ 50 mg).

H0: µ ≤ 20 (i.e. average rainfall does not increase after cloud

HA: µ > 20 (i.e. average rainfall increases after cloud seeding)

HA: µ ≠ 30 years (i.e. population mean age is different from 30)

H0: µ ≥ 110 (i.e. students’ average IQ is at least 110)

HA: µ < 110 (i.e. students’ average IQ is less than 110)

Rejection of null hypothesis means acceptance of

Rejection of alternative hypothesis means

There is a possibility that we may reject true null hypothesis or

accept false null hypothesis

This error is committed when true null hypothesis is rejected.

Reject null hypothesis when it is true

The rate of type of I error is also called size of the test

The probability of committing type I error is α (level of significance)

If type I error is fixed as 5%, it means that there are about 5

chance in 100 that we will reject null hypothesis when null

This error is committed when false null hypothesis is accepted

NOTE: we do not say that we accept the null hypothesis if

Fail to reject false null hypothesis

“Power” of a test is the probability of rejecting null

hypothesis when it is false.

“Power” = 1 -P(Type II error)

To minimize the P(Type II error), we equivalently want to

But power depends on the value under the alternative

Power is probability, so number between

Need to make power as high as

The two probabilities are inversely related. Decreasing one increases

the alternative hypothesis is true, or the null is not likely to be true.

There are two possible decisions:

Conclude that there is enough evidence to support the alternative

hypothesis. Reject the null.

Conclude that there is not enough evidence to support the

alternative hypothesis. Fail to reject the null.

that things are correct.

that things are wrong.

things are wrong.