HYPOTHESIS TESTING

Prepared by: Muhammad Athar

Assistant Professor of Statistics
Govt. Zamindar Graduate Collge
Gujrat
TESTING OF HYPOTHESIS ABOUT
POPULATION PROPORTION (P)

General Procedure:
 Step 1: Formulation of null and alternative
hypotheses
 Possible null and alternative hypotheses:

 𝐻0 : 𝑝 = 𝑝
0 𝐻1 : 𝑝 ≠ 𝑝0
 𝐻 0 : 𝑝 ≥ 𝑝0 𝐻1 : 𝑝 < 𝑝0
 𝐻 0 : 𝑝 ≤ 𝑝0 𝐻1 : 𝑝 > 𝑝0
 Step 2: Specification of level of significance
denoted by 𝛂
 Step 3: Test to be used to test the null hypothesis
𝑝−𝑝0
 𝑍= 𝑝 0 𝑞0
𝑛

 Step 4: Defining critical region / rejection region

 Critical region is always based on alternative hypothesis.
 If alternative hypothesis is 𝐻1 : 𝑝 ≠ 𝑝0 the critical region will
be 𝑍 ≥ 𝑍𝛼/2
 If alternative hypothesis is 𝐻1 : 𝑝 > 𝑝0 the critical region will
be 𝑍 ≥ 𝑍𝛼
 If alternative hypothesis is 𝐻1 : 𝑝 < 𝑝0 the critical region will
be 𝑍 ≤ −𝑍𝛼
 Where, 𝑍𝛼/2 𝑎𝑛𝑑 𝑍𝛼 are critical values that are calculated
using t-distribution table of critical values.
 Note: critical region tells us how to reject a null hypothesis.

 Step 5: Draw a random sample and using sample
information calculate the value of Z test.


 Step 6: We draw our conclusion whether we

accepted or rejected our null hypothesis.
EXAMPLE 1
 Consider the following hypothesis test:
 H0 p = 20

 H1 p ≠ 20

 A sample of 400 provided a sample proportion p

0.175.
 a. Compute the value of the test statistic.

 b. What is the p-value?

 c. At 0.05, what is your conclusion?

 d. What is the rejection rule using the critical

value? What is your conclusion?
EXAMPLE 2
 An airline promotion to business travellers is
based on the assumption that at least two-thirds
of business travellers use a laptop computer on
overnight business trips.
 a. State the hypotheses that can be used to test
the assumption.
 b. What is the sample proportion from an
American Express sponsored survey that found
355 of 546 business travellers use a laptop
computer on overnight business trips?
 c. Use α = 0.05. What is your conclusion?
EXAMPLE 3
 Eagle Outfitters is a chain of stores specializing in
outdoor clothing and camping gear. It is considering a
promotion that involves sending discount coupons to
all their credit card customers by direct mail. This
promotion will be considered a success if more than
10 per cent of those receiving the coupons use them.
Before going nationwide with the promotion, coupons
were sent to a sample of 100 credit card customers.
 a. Formulate hypotheses that can be used to test
whether the population proportion of those who will
use the coupons is sufficient to go national.
 b. The file ‘Eagle’ contains the sample data. Compute
a point estimate of the population proportion.
 c. Use 0.05 to conduct your hypothesis test. Should
Eagle go national with the promotion?
TESTING OF HYPOTHESIS ABOUT TWO
POPULATION PROPORTIONS 𝒑𝟏 = 𝒑𝟐

 General Procedure:
 Step 1: Formulation of null and alternative
hypotheses
 Possible null and alternative hypotheses:

 𝐻 0 : 𝑝 = 𝑝 𝐻1 : 𝑝 ≠ 𝑝
1 2 1 2
 𝐻 0 : 𝑝1 ≥ 𝑝2 𝐻1 : 𝑝 1 < 𝑝2
 𝐻 0 : 𝑝1 ≤ 𝑝2 𝐻1 : 𝑝 1 > 𝑝2
 Step 2: Specification of level of significance
denoted by 𝛂
 Step 3: Test to be used to test the null
hypothesis
𝑝1 −𝑝2
 𝑍= 1 1
𝑝𝑐 𝑞𝑐 𝑛 +𝑛
1 2
𝑛1 𝑝1 +𝑛2 𝑝2
 Where 𝑝 =
𝑐 𝑛1 +𝑛2
 Step 4: Defining critical region / rejection region
 Critical region is always based on alternative hypothesis.
 If alternative hypothesis is 𝐻1 : 𝑝1 ≠ 𝑝2 the critical region
will be 𝑍 ≥ 𝑍𝛼/2
 If alternative hypothesis is 𝐻1 : 𝑝1 < 𝑝2 the critical region
will be 𝑍 ≥ 𝑍𝛼
 If alternative hypothesis is 𝐻1 : 𝑝1 > 𝑝2 the critical region
will be 𝑍 ≤ −𝑍𝛼
 Where, 𝑍𝛼/2 𝑎𝑛𝑑 𝑍𝛼 are critical values that are calculated
using t-distribution table of critical values.
 Note: critical region tells us how to reject a null hypothesis.
 Step 5: Draw a random sample and using sample
information calculate the value of Z test.
 Step 6: We draw our conclusion whether we accepted or
rejected our null hypothesis.
EXAMPLE 4
 Consider the hypothesis test
 H0: p1 – p2 = 0

 H1: p1 – p2 ≠ 0

 The following results are for independent

samples taken from the two populations.
 Sample 1: n1 = 200, p1= 0.22

 Sample 2: n2 = 300, p2 = 0.10

 With α = 0.05, what is your hypothesis testing
conclusion?
EXAMPLE 5
 In the UNITE 2007 Student Experience Report, it
was reported that 49 per cent of 1600 student
respondents in UK universities considered the
academic reputation of the university an
important factor in their choice of university. In
the 2012 Student Experience Report, 343 out of
488 respondents considered academic reputation
to be important. Test the hypothesis p1 - p2 = 0
with α = 0.05. What is your conclusion?
EXAMPLE 6
 In a random sample of 500 men from Lahore city,
300 are found to be smoker. In one of 1000 men
from Karachi city, 550 are smokers. Do the data
indicate that two cities are significantly different
with respect to the prevalence of smoking among
men?