Hypothesis Testing

What is a Hypothesis?
 A hypothesis is a claim
(assumption) about a
population parameter:
 population mean
Example: The mean monthly cell phone bill
of this city is μ = Rs.42
 population proportion

Example: The proportion of adults in this

city with cell phones is p = .68
 The Null Hypothesis, H0

 States the assumption (numerical) to be

tested
Example: The average number of working adults in
Indian Urban Households is three ( H0 : μ  2 )
 Is always about a population parameter,
not about a sample statistic

H0 : μ  2 H0 : X  2
 The Null Hypothesis, H0
(continued)

 Begin with the assumption that the null

hypothesis is true
 Similar to the notion of innocent until

proven guilty
 Refers to the status quo
 Always contains “=” , “≤” or “” sign
 May or may not be rejected
 The Alternative Hypothesis, H1
 Is the opposite of the null hypothesis
 e.g., The average number of Working adults in
urban Indian households is not equal to 2 ( H1:
μ≠2)
 Challenges the status quo
 Never contains the “=” , “≤” or “” sign
 May or may not be supported
 Is generally the hypothesis that the
researcher is trying to support
 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
 Reason for Rejecting H0
Sampling Distribution of X

X
20 μ = 50
If H0 is true
If it is unlikely that ... then we
we would get a reject the null
sample mean of ... if in fact this were hypothesis that
this value ... the population mean… μ = 50.
 Level of Significance, 

 Defines the unlikely values of the sample

statistic if the null hypothesis is true
 Defines rejection region of the sampling
distribution
 Is designated by  , (level of significance)
 Typical values are .01, .05, or .10
 Is selected by the researcher at the beginning
 Provides the critical value(s) of the test
 Level of Significance
and the Rejection Region
Level of significance = a Represents
critical value
H0: μ = 2 a/2 a/2
Rejection
H1: μ ≠ 2 Two-tail test 0 region is
shaded
H0: μ ≤ 2 a
H1: μ > 2
Upper-tail test 0

H0: μ ≥ 2
a
H1: μ < 2
Lower-tail test 0
 Errors in Making Decisions
 Type I Error
 Reject a true null hypothesis

 Considered a serious type of error

The probability of Type I Error is 

 Called level of significance of the test
 Set by researcher in advance
 Errors in Making Decisions
(continued)

 Type II Error
 Fail to reject a false null hypothesis

The probability of Type II Error is β

 Outcomes and Probabilities

Possible Hypothesis Test Outcomes

Actual Situation
Decision H0 True H0 False
Do Not
No error Type II Error
Key: Reject
(1 - a ) (β)
Outcome H0
(Probability) Reject Type I Error No Error
H0 (a) (1-β)
 Type I & II Error Relationship

 Type I and Type II errors can not happen at

the same time
 Type I error can only occur if H0 is true
 Type II error can only occur if H0 is false

If Type I error probability (  ) , then

Type II error probability ( β )
 Factors Affecting Type II Error
 All else equal,
 β when the difference between
hypothesized parameter and its true value


β when 

β when σ

β when n
 Power of the Test

 The power of a test is the probability of rejecting

a null hypothesis that is false

 i.e., Power = P(Reject H0 | H1 is true)

 Power of the test increases as the sample size

increases
Hypothesis Tests for the Mean

Hypothesis
Tests for 

 Known  Unknown
 Test of Hypothesis
for the Mean (σ Known)
 Convert sample result ( x ) to a z value
Hypothesis
Tests for 

σ Known σ Unknown

Consider the test

H0 : μ  μ0 The decision rule is:
H1 : μ  μ0 x  μ0
Reject H0 if z   zα
σ
(Assume the population is n
normal)
 Decision Rule
H0: μ = μ0
x  μ0
Reject H0 if z   zα H1: μ > μ0
σ
n

Alternate rule:
Reject H0 if X  μ0  Z ασ/ n a

Do not reject H0 Reject H0

Z 0 zα
x μ0 μ0  z α
σ
n

Critical value
 p-Value Approach to Testing

 p-value: Probability of obtaining a test

statistic more extreme ( ≤ or  ) than the
observed sample value given H0 is true
 Also called observed level of significance
 Smallest value of  for which H0 can be
rejected
 p-Value Approach to Testing
(continued)
 Convert sample result (e.g., x ) to test statistic (e.g., z
statistic )
 Obtain the p-value x - μ0

For an upper p - value  P(Z  , given that H0 is true)
tail test: σ/ n

x - μ0
 P(Z  | μ  μ0 )
σ/ n
 Decision rule: compare the p-value to 
 If p-value <  , reject H0
 If p-value   , do not reject H0
 Example: Upper-Tail Z Test
for Mean ( Known)
A phone industry manager thinks that
customer monthly cell phone bill have
increased, and now average over Rs.52 per
month. The company wishes to test this
claim. (Assume  = 10 is known)

Form hypothesis test:

H0: μ ≤ 52 the average is not over Rs. 52 per month
H1: μ > 52 the average is greater than Rs. 52 per
month
(i.e., sufficient evidence exists to support the
manager’s claim)
 Example: Find Rejection Region
(continued)
 Suppose that  = .10 is chosen for this test

Find the rejection region: Reject H0

 = .10

Do not reject H0 Reject H0

0 1.28

x  μ0
Reject H0 if z   1.28
σ/ n
 Example: Sample Results
(continued)

Obtain sample and compute the test statistic

Suppose a sample is taken with the following

results: n = 64, x = 53.1 (=10 was assumed known)
 Example: Sample Results
(continued)

Obtain sample and compute the test statistic

Suppose a sample is taken with the following

results: n = 64, x = 53.1 (=10 was assumed known)
 Using the sample results,

x  μ0 53.1  52
z   0.88
σ 10
n 64
 Example: Decision
(continued)
Reach a decision and interpret the result:
Reject H0

 = .10

Do not reject H0 Reject H0

0
1.28
z = 0.88

Do not reject H0 since z = 0.88 < 1.28

i.e.: there is not sufficient evidence that the
mean bill is over Rs.52
 Example: p-Value Solution
(continued)
Calculate the p-value and compare to 
(assuming that μ = 52.0)
p-value = .1894
P(x  53.1 | μ  52.0)
Reject H0
 = .10 53.1  52.0 

 P z  
 10/ 64 
0
Do not reject H0
1.28
Reject H0
 P(z  0.88)  1 .8106
Z = .88
 .1894

Do not reject H0 since p-value = .1894 >  = .10

 One-Tail Tests

 In many cases, the alternative hypothesis

focuses on one particular direction

H0: μ ≤ 2 This is an upper-tail test since the

alternative hypothesis is focused on
H1: μ > 2 the upper tail above the mean of 3

This is a lower-tail test since the

H0: μ ≥ 2
alternative hypothesis is focused on
the lower tail below the mean of 3
H1: μ < 2
 Upper-Tail Tests

 There is only one H0: μ ≤ 2

critical value, since H1: μ > 2
the rejection area is
in only one tail a

Do not reject H0 Reject H0

Z 0 zα
x μ

Critical value
 Lower-Tail Tests
H0: μ ≥ 2
 There is only one
critical value, since H1: μ < 2
the rejection area is
in only one tail a

Reject H0 Do not reject H0

-z 0 Z

μ x
Critical value
 Two-Tail Tests
 In some settings, the
H0: μ = 2
alternative hypothesis does
not specify a unique direction H1: μ ¹
2

/2 /2
 There are two
critical values, x
2
defining the two
Reject H0 Do not reject H0 Reject H0
regions of
-z/2 0 +z/2 z
rejection
Lower Upper
critical value critical value
 Hypothesis Testing Example
Test the claim that the true mean # of adult
working individuals in urban indian
households equal to 3 assume σ = 0.8)

 State the appropriate null and alternative

hypotheses
 H : μ = 3 , H : μ ≠ 3 (This is a two tailed test)
0 1
 Specify the desired level of significance
 Suppose that  = .05 is chosen for this test

 Choose a sample size

 Suppose a sample of size n = 100 is selected
 Hypothesis Testing Example
(continued)

 Determine the appropriate technique

 σ is known so this is a z test

 Set up the critical values

 For  = .05 the critical z values are ±1.96

 Collect the data and compute the test statistic

 Suppose the sample results are
n = 100, x = 2.84 (σ = 0.8 is assumed known)
So the test statistic is:
X  μ0 2.84  3  .16
z     2.0
σ 0.8 .08
n 100
 Hypothesis Testing Example
(continued)
 Is the test statistic in the rejection region?

Reject H0 if  = .05/2  = .05/2

z < -1.96 or
z > 1.96;
otherwise Reject H0 Do not reject H0 Reject H0

do not -z = -1.96 0 +z = +1.96

reject H0

Here, z = -2.0 < -1.96, so the

test statistic is in the rejection
region
 Hypothesis Testing Example
(continued)
 Reach a decision and interpret the result

 = .05/2  = .05/2

Reject H0 Do not reject H0 Reject H0

-z = -1.96 0 +z = +1.96
-2.0
Since z = -2.0 < -1.96, we reject the null hypothesis
and conclude that there is sufficient evidence that the
mean number of adult working men is not equal to 3
 Example: p-Value
 Example: How likely is it to see a sample mean of
2.84 (or something further from the mean, in either
direction) if the true mean is  = 3.0?

x = 2.84 is translated to
a z score of z = -2.0
P(z  2.0)  .0228 /2 = .025 /2 = .025

.0228 .0228
P(z  2.0)  .0228

p-value
= .0228 + .0228 = .0456 -1.96 0 1.96 Z
-2.0 2.0
 Example: p-Value
(continued)
 Compare the p-value with 
 If p-value <  , reject H0
 If p-value   , do not reject H0

Here: p-value = .0456 /2 = .025 /2 = .025

 = .05
.0228 .0228
Since .0456 < .05, we
reject the null
hypothesis
-1.96 0 1.96 Z
-2.0 2.0
 t Test of Hypothesis for the Mean
(σ Unknown)
 Convert sample result ( x ) to a t test statistic
Hypothesis
Tests for 

σ Known σ Unknown

Consider the test

The decision rule is:
H0 : μ  μ0
x  μ0
H1 : μ  μ0 Reject H0 if t   t n-1, α
s
(Assume the population is n
normal)
 t Test of Hypothesis for the Mean
(σ Unknown)
(continued)
 For a two-tailed test:
Consider the test
H0 : μ  μ0 (Assume the population is normal,
and the population variance is
H1 : μ  μ0 unknown)

The decision rule is:

x  μ0 x  μ0
Reject H0 if t   t n-1, α/2 or if t   t n-1, α/2
s s
n n
 Example: Two-Tail Test
( Unknown)

The average cost of a

hotel room in an Indian
City is said to be Rs1680
per night. A random
sample of 25 hotels
resulted in x = Rs1725 H0: μ = 1680
and s = Rs.154. Test at H1: μ ¹ 1680
the  = 0.05 level.
t24 , .025 = ± 2.0639
 Example Solution:
Two-Tail Test

H0: μ = 1680 a/2=.025 a/2=.025

H1: μ ¹ 1680

 a = 0.05 Reject H0 Do not reject H0 Reject H0

t n-1,α/2
-t n-1,α/2 0
 n = 25 -2.0639 2.0639
1.46
  is unknown, so x μ 1725  1680
use a t statistic t n 1    1.46
s 154
 Critical Value: n 25

t24 , .025 = ± 2.0639 Do not reject H0: insufficient evidence that true
mean cost is different than Rs.1680
 Tests of the Population Proportion

 Involves categorical variables

 Two possible outcomes
 “Success” (a certain characteristic is present)
 “Failure” (the characteristic is not present)
 Fraction or proportion of the population in the
“success” category is denoted by P
 Assume sample size is large
 Proportions
(continued)
 Sample proportion in the success category is
denoted by p̂

 ˆp  x  number of successes in sample

n sample size

 When nP(1 – P) > 9, p̂ can be approximated

by a normal distribution with mean and standard
deviation

μp̂  P P(1 P)
σ p̂ 
n
 Hypothesis Tests for Proportions

 The sampling
distribution of p̂ is Hypothesis
approximately Tests for P
normal, so the test
statistic is a z
nP(1 – P) > 9 nP(1 – P) < 9
value:
p̂  P
z
P (1  P)
n
 Example: Z Test for Proportion

A marketing company
claims that it receives
8% responses from its
mailing. To test this
claim, a random sample
of 500 were surveyed
with 25 responses. Test
at the  = .05
significance level.
 Example: Z Test for Proportion

A marketing company
claims that it receives
8% responses from its
mailing. To test this
claim, a random sample
of 500 were surveyed
approximation for P is
with 25 responses. Test = 25/500 = .05
at the  = .05 p̂
significance level.
 Z Test for Proportion: Solution
Test Statistic:
H0: P = .08
p̂  P .05  .08
H1: P z   2.47
P (1  P ) .08(1  .08)
a¹ = .05
.08
n 500
n = 500, p̂ = .05
Critical Values: ± 1.96 Decision:
Reject Reject Reject H0 at  = .05
Conclusion:
.025 .025
There is sufficient
-1.96 0 1.96 z evidence to reject the
-2.47 company’s claim of 8%
response rate.
 p-Value Solution
(continued)
Calculate the p-value and compare to 
(For a two sided test the p-value is always two sided)

Do not reject H0
Reject H0 Reject H0 p-value = .0136:
/2 = .025 /2 = .025
P(Z  2.47)  P(Z  2.47)
.0068 .0068
 2(.0068)  0.0136
-1.96 0 1.96

Z = -2.47 Z = 2.47

Reject H0 since p-value = .0136 <  = .05