You are on page 1of 43

Hypothesis Testing

PPT-1
Logic behind hypothesis testing
Prevalent opinion is
that mean age in that
group is 50 (null Reject
Population Rejectnull
null
hypothesis) hypothesis!
hypothesis!
Sample
Samplemean
meanisis
only
only45!
  45!


 
 Random sample

 Mean
age = 45
 

PPT-2
What is Hypothesis Testing?
Hypothesis testing is a procedure,
based on sample evidence and
probability theory, used to determine
whether the hypothesis is a
reasonable statement and should not
be rejected, or is unreasonable and
should be rejected.

PPT-3
Important Things to Remember about H0
and H1
• H0: null hypothesis and H1: alternate hypothesis
• H0 and H1 are collectively complete
• H0 is always presumed to be true
• H1 has the burden of proof
• A random sample (n) is used to “reject H0”
• Equality is always part of H0 (e.g. “=” , “≥” , “≤”).
• “≠” “<” and “>” always part of H1

PPT-4
Important Things to Remember about H0
and H1
• H0: null hypothesis and H1: alternate hypothesis
• H0 and H1 are collectively complete
• H0 is always presumed to be true
• H1 has the burden of proof
• A random sample (n) is used to “reject H0”
• Equality is always part of H0 (e.g. “=” , “≥” , “≤”).
• “≠” “<” and “>” always part of H1

PPT-5
Concepts of Hypothesis Testing

Example 1:
• An operation manager needs to determine if
the mean demand is greater than 350.
• If so, changes in the ordering policy are
needed.
– There are two hypotheses about a population mean:

prov e
nt to
at yo u wa
w h
This is
PPT-6
Concepts of Hypothesis Testing

• H0: The null hypothesis  = 350


• H1: The alternative hypothesis  > 350

prov e
nt to
at yo u wa
w h
This is
PPT-7
Concepts of Hypothesis Testing
• Assume the null hypothesis is true
(= 350).

= 350
– Sample from the demand population, and build a statistic
related to the parameter hypothesized (the sample mean).

PPT-8
Concepts of Hypothesis Testing
• Assume the null hypothesis is true
(= 350).

x  355
x  450
= 350
x
– Since the is much larger than 350, the mean  is
likely to be > 350. Reject the null hypothesis.

PPT-9
Important Things to Remember about H0
and H1
Null Hypothesis Alternative Hypothesis Number of Tails

μ=M μ≠M 2

μ > M μ<M 1

μ < M μ>M 1

PPT-10
Two Tailed Test

• Two-sided (or two-tailed): If null hypothesis gets rejected when a value of


the test statistic falls in either one or the other of the two tails of its sampling
distribution.
• Two tailed test will reject the null hypothesis if the sample mean is
significantly higher or lower than the hypothesized mean.
• Appropriate when H0 : µ = M and HA: µ ≠ M

• e.g The manufacturer of light bulbs wants to produce light bulbs with a
mean life of 1000 hours. If the lifetime is shorter he will lose customers to
the competition and if it is longer then he will incur a high cost of production.
He does not want to deviate significantly from 1000 hours in either direction.
Thus he selects the hypotheses as H0 : µ = 1000 hours and HA: µ ≠ 1000
hours and uses a two tail test.

PPT-11
One Tailed Test

• One-sided (or One-tailed): A test is called one-sided (or one-tailed) only if the null
hypothesis gets rejected when a value of the test statistic falls in one specified tail
of the distribution.
• A one-sided test is a statistical hypothesis test in which the values for which we can
reject the null hypothesis, H0 are located entirely in one tail of the probability
distribution.
• Lower-tailed Test : You will reject the null hypothesis when the sample mean is
significantly lower than the hypothesized mean.
• H0 : μ < M HA: μ > M
• Higher-tailed Test : You will reject the null hypothesis when the sample mean is
significantly higher than the hypothesized mean.
• H0 : μ > M, HA: µ < M

PPT-12
Example -One Tailed Test

• A wholesaler buys light bulbs from the manufacturer in large lots and decides not to
accept a lot with capacity not less than 1000 hours. H0 : µ less than equal to1000
hours and HA: µ >1000 hours and uses a upper tail test. i.e he rejects H0 only if
the mean life of sampled bulbs is significantly higher 1000 hours. (he accepts HA
and rejects the lot).

• A highway safety engineer decides to test the load bearing capacity of a 20 year old
bridge. The minimum load-bearing capacity of the bridge must be less than 10 tons.
H0 : µ greater than equal to 10 tons and HA: µ less than10 tons and uses an lower
tail test. i.e he rejects H0 only if the mean load bearing capacity of the bridge is
significantly lesser than 10 tons.

PPT-13
Hypothesis Testing Process

Claim: the
population
mean age is 50.
(Null Hypothesis:
Population
H0: μ = 50 )
Now select a
random sample
Is X 20 likely if μ = 50?
If not likely, Suppose
the sample
REJECT mean age Sample
Null Hypothesis is 20: X = 20
PPT-14
Sampling Distribution of X
H0: μ = 50
• There are two
H1: μ  50
cutoff values
(critical values),
defining the /2 /2
regions of
rejection 50 X
Reject H0 Do not reject H0 Reject H0

0
20 Likely Sample Results

Lower Upper
critical critical
value value PPT-15
Level of Significance
and the Rejection Region
Level of significance =  Represents
critical value
H0: μ = M /2 /2
Rejection
H1: μ ≠ MTwo tailed test 0 region is
shaded

H0: μ ≥M 
H1: μ < MUpper tail test 0


H0: μ ≤ M
H1: μ >M Lower tail test 0
PPT-16
What is a critical value?

A value needed to determine whether to


reject or not to reject the null hypothesis.
But how to determine this value?

PPT-17
Parts of a Distribution in Hypothesis
Testing

PPT-18
One-tail vs. Two-tail Test

PPT-19
Testing Statistical Hypotheses –
example
• Suppose H 0 :   75; H1 :   75
• Assume   10 and population is normal, so sampling
distribution of means is known (to be normal).
• Rejection region: -1.96 Likely Outcome 1.96
• Region (N=25): If Null is True

10
75  1.96  71.08  78.92
• We get data25 Reject Don't reject Reject

• Conclusion:
X
N  25; reject
X  79null. -3 -2 -1 0 1 2 3
Z

PPT-20
Same Example
• Rejection region in original units
• Sample result (79) just over the line
Likely Outcome
If Null is True

Reject Don't reject Reject

71.08 75 78.92
X
PPT-21
Hypothesis Testing Steps

PPT-22
9-1 Hypothesis Testing

9-1.6 General Procedure for Hypothesis Tests


1. From the problem context, identify the parameter of interest.
2. State the null hypothesis, H0 .
3. Specify an appropriate alternative hypothesis, H1.
4. Choose a significance level, .
5. Determine an appropriate test statistic.
6. State the rejection region for the statistic.
7. Compute any necessary sample quantities, substitute these into the
equation for the test statistic, and compute that value.
8. Decide whether or not H0 should be rejected and report that in the
PPT-23
Concept of Errors
• Two types of errors may occur when deciding
whether to reject H0 based on the statistic value.
– Type I error: Reject H0 when it is true.
– Type II error: Do not reject H0 when it is false.
• Example continued
– Type I error: Reject H0 ( = 350) in favor of H1 (
> 350) when the real value of  is 350.
– Type II error: Believe that H0 is correct ( = 350)
when the real value of  is greater than 350.
PPT-24
Errors in Hypothesis Testing &
Level of Significance
Actual Situation (Truth)

The Person Is Not The Person Is Guilty


Guilty

Court’s The person is not Correct decision(1- Type II Error(β)


Decisio guilty. α) [Incorrect decision]
n
The person is guilty Type I Error(α) Correct decision (1-β)
[In correct decision]

PPT-25
Type of Error Conti…
 In hypothesis testing, two types of errors can
occur. Types I Error (α), and Types II Error
(β).
 Types I Error: A Types I Error occurs when a
true null hypothesis is rejected.
 The value of α represents the probability of
committing this type of error; that is,
α = P(Ho is rejected/Ho is true)
 The value of α represents the significance
level of the test.

PPT-26
Type II Error Conti…
 A Type II error occurs when a false null
hypothesis is not rejected.
 The value of β represents the probability
of committing a Type II Error; that is
β = P(Ho is not rejected/Ho is false)
 The value of 1- β is called the power of the
test.
 It represents the probability of not making
a Type II error.
PPT-27
Common Statistical Hypothesis
&Test
 One –sample test: Z or t test

 Two-sample Test: Z test

 Analysis of Variance Test: F-test

 Test of Significance: t test

 Chi-Square goodness-of-fit Test

 Chi-Square Test of Independence

PPT-28
Types of Errors…
• A Type I error occurs when we reject a true null
hypothesis (i.e. Reject H0 when it is TRUE)

H0 T F

Reject I

• AReject IIwhen we don’t reject a false null hypothesis (i.e. Do


Type II error occurs
NOT reject H0 when it is FALSE)

PPT-29
Testing for a Population Mean with a
Known Population Standard Deviation-
Example
Jamestown Steel Company
manufactures and assembles
desks and other office equipment
at several plants in western New
York State. The weekly production
of the Model A325 desk at the
Fredonia Plant follows the normal
probability distribution with a mean
of 200 and a standard deviation
of 16. Recently, because of
market expansion, new production
methods have been introduced
and new employees hired. The
vice president of manufacturing
would like to investigate whether
there has been a change in the
weekly production of the Model
A325 desk.

PPT-30
Testing for a Population Mean with a
Known Population Standard Deviation-
Example
Step 1: State the null hypothesis and the alternate
hypothesis.
H0:  = 200
H1:  ≠ 200
(note: keyword in the problem “has changed”)

Step 2: Select the level of significance.


α = 0.01 as stated in the problem

Step 3: Select the test statistic.


Use Z-distribution since σ is known

PPT-31
Testing for a Population Mean with a
Known Population Standard Deviation-
Example
Step 4: Formulate the decision rule.
Reject H0 if |Z| > Z/2
Z  Z / 2
X 
 Z / 2
/ n
203.5  200
 Z .01/ 2
16 / 50
1.55 is not  2.58

Step 5: Make a decision and interpret the result.


Because 1.55 does not fall in the rejection region, H0 is not
rejected. We conclude that the population mean is not different from
200. So we would report to the vice president of manufacturing that the
sample evidence does not show that the production rate at the Fredonia
Plant has changed from 200 per week.
PPT-32
Testing for a Population Mean with a Known
Population Standard Deviation- Another Example

Suppose in the previous problem the vice


president wants to know whether there has
been an increase in the number of units
assembled. To put it another way, can we
conclude, because of the improved
production methods, that the mean number
of desks assembled in the last 50 weeks
was more than 200?
Recall: σ=16, n=200, α=.01
PPT-33
Testing for a Population Mean with a Known
Population Standard Deviation- Example
Step 1: State the null hypothesis and the alternate
hypothesis.
H0:  ≤ 200
H1:  > 200
(note: keyword in the problem “an increase”)

Step 2: Select the level of significance.


α = 0.01 as stated in the problem

Step 3: Select the test statistic.


Use Z-distribution since σ is known

PPT-34
Testing for a Population Mean with a Known
Population Standard Deviation- Example
Step 4: Formulate the decision rule.
Reject H0 if Z > Z

Step 5: Make a decision and interpret the result.


Because 1.55 does not fall in the rejection region, H0 is not rejected.
We conclude that the average number of desks assembled in the last
50 weeks is not more than 200

PPT-35
9-2 Tests on the Mean of a Normal
Distribution, Variance Known

Example 9-2

PPT-36
9-2 Tests on the Mean of a Normal Distribution,
Variance Known

Example 9-2

PPT-37
9-2 Tests on the Mean of a Normal Distribution,
Variance Known

Example 9-2

PPT-38
Conclusions of a Test of
Hypothesis
•• IfIf we
we reject
reject the
the null
null hypothesis,
hypothesis, we we
conclude that
conclude that there
there is
is enough
enough
evidence to
evidence to infer
infer that
that the
the alternative
alternative
hypothesis is
hypothesis is true.
true.

•• IfIf we
we do
do not
not reject
reject the
the null
null hypothesis,
hypothesis,
we conclude
we conclude that
that there
there isis not
not enough
enough
statistical evidence
statistical evidence to to infer
infer that
that the
the
alternative hypothesis
alternative hypothesis is is true.
true.

PPT-39
Three Research Approaches
Research Research Hypothesis
purpose Question
Exploratory research Boxed lunches are
1. What new product What alternative ways better than other
should be are there to provide forms
developed? lunches for school
children?
What benefits do the Search for customer
2. What product appeal people seek from the benefits
will be effective in product?
advertising?
What is the nature of Suspect that an image
any customer of impersonalisation
3. How can our services
dissatisfaction? is a problem
be improved?

PPT-40
Three Research Approaches
Research Research Hypothesis
purpose Question
Descriptive research Upper class buyers use
1. How should a new Where do people now speciality stores, and
product be buy similar products? middle class buyers
distributed? use department
stores

Older people buy our


2. What should be the What kind type of brands, whereas the
target segment? people now buy the young married are
product, and who heavy user of
buys our brands? competitors
We are regarded as
3. How should our What is our current being conservative
product be changed? image? and behind the times.

PPT-41
Three Research Approaches
Research Question
Research purpose Hypothesis
Causal research
What is the relationship
1. Will an increase in the For small
between size of service
service staff be organisations, an
staff and revenue?
profitable? increase of 50% or
less will generate
marginal revenue
2. Which advertising What would get people out of in excess of
programme for public cars and into public transit? marginal cost.
transit should be run? Advertising
programme A
3. Should a new budget Will the “ no frills” airfare generates more
or “no frills” class of generate sufficient new new riders than
airfare be introduces? passengers to offset the programme B
loss of revenue from The new airfare will
existing passengers who attract sufficient
switch from economy revenue from new
class? passengers.
PPT-42
Aaker, Kumar& Day , Marketing research
Questions ???

PPT-43

You might also like