Dr Aaliyawani Ezzerin binti Sinin

Department of Science and Technology

Faculty of Humanities, Management and Science
UPMKB
[email protected]

CHAPTER 6
HYPOTHESIS TESTING

6.1 HYPOTHESIS TESTS

6.2 SIGNIFICANCE LEVEL & CRITICAL REGION
6.3 T-TEST
LESSON OUTCOME

At the end of this lesson, students will be able to:

• Explain the meaning of null and alternative hypothesis

• Carry out hypothesis testing concern population mean
• Explain the use of t-test as a tool for hypothesis testing
 6.1 HYPOTHESIS TESTS
NULL AND ALTERNATIVE HYPOTHESIS
Null hypothesis, 𝐻0 : hypothesis that there is no difference between a parameter and a specific
value
Propose a value, 𝐻0 : µ = µ0

Alternative hypothesis, 𝐻1 : claim or belief that we wish to establish

May take any of the following three forms:
𝐻1 : µ < µ0 𝑜𝑛𝑒 − 𝑡𝑎𝑖𝑙𝑒𝑑 𝑡𝑒𝑠𝑡 𝑓𝑜𝑟 𝑎 𝑑𝑒𝑐𝑟𝑒𝑎𝑠𝑒
Two-tailed Right-tailed Left-tailed
𝐻1 : µ > µ0 𝑜𝑛𝑒 − 𝑡𝑎𝑖𝑙𝑒𝑑 𝑡𝑒𝑠𝑡 𝑓𝑜𝑟 𝑎 𝑖𝑛𝑐𝑟𝑒𝑎𝑠𝑒 test test test
𝐻1 : µ ≠ µ0 𝑡𝑤𝑜 − 𝑡𝑎𝑖𝑙𝑒𝑑 𝑡𝑒𝑠𝑡 𝑓𝑜𝑟 𝑎 𝑑𝑖𝑓𝑓𝑒𝑟𝑒𝑛𝑐𝑒 H0: μ = k H0: μ = k H0: μ = k
H1: μ ≠ k H1: μ > k H1: μ < k
EXAMPLE 1
(a) A chemist invents an additive to increase the life of an automobile battery.
If the mean lifetime of the automobile battery without the additive is 36 months, then her hypotheses are

𝐻0 : µ = 36 The test is a right-tailed test.

𝐻1 : µ > 36

(b) A contractor wishes to lower heating bills by using a special type of insulation in houses. If the average of the monthly
heating bills is $78, her hypotheses about heating costs with the use of insulation are

𝐻0 : µ = $78 The test is a left-tailed test.

𝐻1 : µ < $78
EXAMPLE 2
An electric company claims that its electric water heater has a mean lifespan of more than 800 hours. If µ represent the
mean lifespan of the electric water heater, then we can formulate two hypothesis as follows:

𝐻0 : µ = 800 ℎ𝑜𝑢𝑟𝑠 (The mean lifespan of the electric water heater is 800 hours)
𝐻1 : µ > 800 ℎ𝑜𝑢𝑟𝑠 (The mean lifespan of the electric water heater is more than 800 hours)

𝐻0 = 𝑛𝑢𝑙𝑙 ℎ𝑦𝑝𝑜𝑡ℎ𝑒𝑠𝑖𝑠 𝐻1 = 𝑎𝑙𝑡𝑒𝑟𝑛𝑎𝑡𝑖𝑣𝑒 ℎ𝑦𝑝𝑜𝑡ℎ𝑒𝑠𝑖𝑠

• States a specific value of the • States a range of values for µ
population parameters • In any hypothesis test, the 𝐻1 indicates
• Also, the hypothesis that the whether test is one-tailed or two-
company hopes to reject tailed
EXAMPLE 3
State the null and alternative hypothesis for each conjecture
(a) A researcher thinks that if expectant mothers use vitamin pills, the birth weight of the babies will increase. The average
birth weight of the population is 8.6 pounds.
𝐻0 : µ = 8.6 The test is a right-tailed test.
𝐻1 : µ > 8.6

(b) An engineer hypothesizes that the mean number of defects can be decreased in a manufacturing proceed of USB drives
by using robots instead of humans for certain tasks.The mean number of defective drives per 1000 is 18.

𝐻0 : µ = 18 The test is a left-tailed test.

𝐻1 : µ < 18

(c) A psychologist feels that playing soft music during a test will change the results of the test. The psychologist is not sure
whether the grades will be higher or lower. In the past, the mean of the scores was 73.

𝐻0 : µ = 73 The test is a two-tailed test.

𝐻1 : µ ≠ 73
6.2 SIGNIFICANCE LEVEL & CRITICAL REGION

• Test statistics: a value calculated from a sample data to determine acceptance or

rejection of the null hypothesis

• Critical region: is the range of test values that indicates there is a significant difference
and that the null hypothesis should be rejected
PROCEDURE FOR SOLVING HYPOTHESIS TESTING PROBLEM
Step 1 State the hypotheses and identify the claim.
Step 2 State significance level,α and find the critical value(s).
Step 3 Compute the test value.
Step 4 Make the decision to reject or not the null hypothesis.
Step 5 Summarize the results.

Z-TEST
Z-test : statistical test for the mean of a population. It can be used either when n ≥ 30 or
when the population is normally distributed and σ is known.
The formula for Z-test
𝑋ത − 𝜇
𝑍=𝜎
ൗ 𝑛
where 𝑋ത = sample mean
𝜇 = hypothesized population mean
𝜎 = population standard deviation
𝑛 = sample size
CRITICAL VALUES
Significance level, Values
0.10 0.05 0.025 0.01 0.005 0.0025 obtained from
α
normal
𝑧 1.282 1.645 1.960 2.326 2.576 2.807 distribution
table

Right-tailed Left-tailed Two-tailed

test test test
H0: μ = μ0 H0: μ = μ0 H0: μ = μ0
H1: μ > μ0 H1: μ < μ0 H1: μ ≠ μ0
EXAMPLE
Consider a population mean, µ and standard deviation 70 which is normally distributed with (800, 702).
𝐻0 : µ = 800
𝐻1 : µ < 800

ҧ
𝑥−800
Standardized test statistics 𝑧 = 70
𝑛

To test null hypothesis, take a sample of size 50 from the population.

ҧ
𝑥−800
Standardized test statistics 𝑧 = 70 can be calculated if 𝑥ഥ is obtained.
50

Critical values depends on the

i) significance level
ii) test is one-tail or two-tailed

If value of test statistics falls in the critical region, then 𝑯𝟎 is rejected and 𝑯𝟏 is accepted.
EXAMPLE 4
The height of police trainee in a particular training centre has a normal distribution with mean, µ cm and standard
deviation 7.5 cm. the mean height of a random sample of 40 police trainee from the training centre is 166.5 cm. carry out a
test, at 1% significance level, to determine whether µ is less than 170.
Step 1: state the null and alternative hypothesis Step 3: calculate test statistics
𝐻0 : µ = 170 cm Test statistic, 𝑧
𝐻1 : µ < 170 cm ҧ
𝑥−170
𝑧 = 7.5
40
Step 2: state the significance level, determine critical value 𝑧=
166.5−170
7.5
1% significance level: α= 0.01 40
𝑧 = −2.95
Significance
0.10 0.05 0.025 0.01 0.005 0.0025
level, α Step 4: Determine to reject or not the null hypothesis
𝑧 1.282 1.645 1.960 2.326 2.576 2.807 Test value of -2.95 falls in the critical region, reject 𝑯𝟎

Critical value
Step 5: Summarize
Since test value of -2.95 falls in the critical region, reject 𝐻0
and conclude there is enough evidence to show that mean
height of police trainee in training centre is less than 170
Acceptance region cm at 1% significance level.
Rejection
region

-2.326
 6.3 T-TEST
• T-test is used when population parameters (mean and standard deviation) are not known
• Used to compare the means of two given samples

t-Score
• Difference between 2 groups and the difference within the groups
o Large t-score tells that the groups are different
o Small t-score tells that the groups are similar

t Values & p Values

• A p-value is the probability that the results from your sample data occurred by chance.
• p-values are from 0% - 100%.
• For example, a p value of 5% is 0.05 (good)
• Low p-values are good
CALCULATING t-TEST
3 main types of t-test:
1) An independent samples t-test compares the means for two groups.
2) A dependent sample t-test compares means from the same group at different times (say, one year
apart).
3) A one sample t-test tests the mean of a single group against a known mean.
1) INDEPENDENT SAMPLES :Testing the Difference Between Two
Means
• Independent sample - the samples are not related
o Eg: Newborn male infants and newborn female infants
EXAMPLE 5
A researcher wishes to see if the average weight of newborn male infants are different from weights of newborn female
infants. She selects a random sample of 10 male infants and find the mean weights is 123 oz and standard deviation of the
sample is 8 oz. She selects a random sample of 8 female infants and finds that the mean weight is 116 oz, and the standard
deviation of the sample is 5 oz. Can it be concluded α = 0.05 that the mean weight of the males is different from the mean
weight of the females? Assume that the variables are normally distributed
Step 1: state the hypothesis, and identify the claim
H0: μ1 = μ2 Hypothesis
H1: μ1 ≠ μ2 Claim

Step 2: Determine the critical values

Since the test is two-tailed and α = 0.05, the degrees of freedom are
the smaller of n1-1 or n2-1.
𝑛1 − 1 = 10 − 1 = 9
𝑛2 − 1 = 8 − 1 = 7
From the t-table, the critical values are +2.365 and -2.365

-2.365 +2.365
Step 3: Compute the test value

Step 4: Make the decision

Since 2.268 < 2.365, do not reject 𝑯𝟎

Rejection Acceptance region Rejection

region region

-2.365 +2.268 +2.365

Step 5: Summarize the results

There is not enough evidence to support the claim that the mean of the weights of the male
infants is different from the mean of the weights of the female infants
1) DEPENDENT SAMPLES : Testing the Difference Between Two
Means
• Dependent sample - the subjects are paired or matched in the same way
o Eg: A medical researcher wants to see whether a drug will affect the reaction time of its users. To
test this hypothesis, the researcher must pre-test the subjects before taking the drugs and post-test
after testing the drugs.
o The same samples are used and therefore, they are dependent samples.

d.f – degrees of freedom

 EXAMPLE 6
A dietitian wishes to see if a person’s cholesterol level will change if the diet is supplemented by a certain mineral. 6
randomly selected subjects were pretested, and then they took the mineral supplement for a 6-week period. The results
are shown in the table. (Cholesterol level is measured in milligrams per decilitre). Can it be concluded that the cholesterol
level has been changed at α = 0.10? Assume that the variable is normally distributed.

Step 1: state the hypothesis, and identify the claim

H0: μD = 0 Hypothesis
H1: μD ≠ 0 Claim
Step 2: Determine the critical values
α = 0.10, degrees of freedom ∶ 𝑛 − 1 = 6 − 1 = 5

From the t-table, the critical values are +2.015 and -2.015

-2.015 +2.015