Probability and
Statistics
Topic : Hypothesis
Testing
TARGETS
Illustrates null hypothesis, alternative hypothesis, level of
significance, rejection region, and type of errors in
hypothesis testing
Calculates the probabilities of committing a type 1 and type
2 error
Identifies the parameter to be tested given a real life
problem
TARGET OBJECTIVES
Formulates the appropriate null and alternative
hypothesis on a population mean
Identifies the appropriate form of the test-statistic
when
a. Population variance is assumed to be known
b. The population variance is assumed to be unknown
c. The Central Limit Theorem is to be used
TARGET OBJECTIVES
Identifies the rejection region for a given level of significance
when:
a. The population variance is known
b. The population variance is unknown
c. The Central Limit Theorem is to be used.
Computes for the test-statistic value (population mean)
TARGET OBJECTIVES
Drawn conclusion about the population mean based
on the test –statistic value and the rejection region.
Solve problems involving test of hypothesis on the
population mean
Formulates the appropriate null and alternative
hypotheses on a population proportion
TARGET OBJECTIVES
Identifies the appropriate form of the test-statistic
when the Central Limit Theorem is to be Used
Identifies the appropriate rejection region for a
given level of significance when the Central Limit
Theorem is used.
Computes for the test- statistic value (population
proportion)
TARGET OBJECTIVES
Draw conclusion about the population proportion
based on the test –statistic value of the rejection
region
Solve problems involving test of hypothesis on the
population proportion.
Descriptive Statistics
Inferential Statistics
Hypothesis
A statistical hypothesis is a
conjecture or a supposition
about a population
parameter.
Hypothesis Testing
A process of evaluating claims about the population based on
the characteristics of the samples.
Hypothesis need to be resolved, whether to accept it or reject it.
Making a decision about two opposing hypotheses (the null and
the alternative)
Types
Null Hypothesis (Ho)
= a statistical hypothesis that states that there is
no difference between a parameter and a particular
value
= equal (assumption that mean, proportion and
standard deviation is equal to a specific parameter
value)
Types
Alternative hypothesis (Ha)
= a statistical hypothesis that states that a
parameter and a particular value has a difference
Stating the Hypotheses
Ho : = k
Ha : ≠ k
or
>k
<k
Type of Tests
Non- Directional (two tailed-test)
Ha : ≠ k
Directional (one tailed-test)
Ha : > k (right tailed test)
Ha : < k (left tailed test)
Two tailed and direction tests
≠k <k >k
Stating the Hypothesis
Stating Ho and H1
Example 1
A maternity hospital claims that the mean weight
of babies delivered in their charity ward is 2.5 kg.
H0 : The mean weight of babies is 2.5 kg.
H1 : The mean weight of babies is not equal to 2.5 kg.
H0 : = 2.5 H1 : 2.5
Example 2
A parents’ organization in a school is concerned about the
proportion of fat content of the burgers sold in the school
canteen. The canteen claims that the proportion is only
about 18%.
H0 : The fat content proportion of burgers is 18%.
H1 : The fat content proportion of burgers is not 18%.
H0 : p = 18% H1 : p 18%
Example 3
A farmer believes that using organic fertilizers on his plants will
yield greater income. His average income from the past was P
200,000 per year.
H0 : The average income is P 200,000.
H1 : The average income is greater than P 200,000.
H0 : = P 200,000 H1 : > P 200,00
Example 4
The average weight loss for a sample of people who exercise
30 minutes per day for 6 weeks is greater than 3.7 kg.
H0 : The average weight loss is 3.7 kg .
H1 : The average weight loss is greater than 3.7 kg .
H0 : = 3.7 kg H1 : > 3.7 kg
Write the null hypothesis and the alternative hypothesis
Decisions
in words and in symbols for each of the following:
1. The net weight of a packet of a snack brand is 130 g. A
sample of 80 packets yielded a sample mean weight of 112 g
with a standard deviation of 15 g.
Write the null hypothesis and the alternative hypothesis
Decisions
in words and in symbols for each of the following:
2. A healthcare provider saw that 48% of their members
received their flu shot in a recent year. The healthcare
provider tried a new advertising strategy in the following
year, and they took a sample of members to test if the
proportion who received their flu shot had changed.
FOUR POSSIBILITIES
IN DECISION MAKING
Decision H0 is true H0 is false
Reject Ho Type 1 Error Correct
Decision
Do not Correct Type II Error
Reject Ho Decision
(Accept Ho)
Decision H0 is true H0 is false
NOT GUILTY
GUILTY
GUILTY
NOT
GUILTY
Decision H0 is true H0 is false
NOT GUILTY
GUILTY
GUILTY Type 1
Error
NOT
GUILTY
Decision H0 is true H0 is false
NOT GUILTY
GUILTY
GUILTY Type 1 Correct
Error Decision
NOT
GUILTY
Decision H0 is true H0 is False
NOT GUILTY
GUILTY
GUILTY Type 1 Correct
Error Decision
NOT Correct
GUILTY Decision
Decision H0 is true H0 is false
NOT GUILTY
GUILTY
GUILTY Type 1 Error Correct
Decision
NOT Correct Type II Error
GUILTY Decision
Think about criminal cases that result in
wrong decisions because of making
mistakes in judgement. What do you think
is worse, to convict an innocent man or set
the guilty free.
Errors in Hypothesis Testing
Type I error, decision of reject the Ho when
it fact it is true.
Type II error, decision of accepting the Ho
when it fact it is false.
Drills : Type 1 or Type II Errors
1. Maria insists that she is 30years old when,
in fact she is 32 years old.
2. On a moonlit night, a young man declares
that there are two moons.
Drills : Type 1 or Type II Errors
3. Thousands of years ago, Ptolemy declared
that the earth is flat.
4. On a campus, a signage reads, “This school is
an environment-friendly school.” A few yards
away are rubbish scattered.
Hypothesis
H0 ,if found to be statistically true, if
not rejected (is accepted).
Decision H0 is true H0 is false
Reject Ho Type 1 Error Correct
p = Decision
p = 1-
Correct Type II Error
Failed to Decision p=
Reject Ho p=1-
(Accept Ho)
Errors
Level of significance () is the maximum allowable
probability of committing a type I error.
The probability of committing a type II error is denoted by
.
Errors
Level of significance () is the maximum allowable
probability of committing a type I error.
A 0.01 level of significance means that the researcher is
willing to take 1% error in making decisions. This further
implies that he is 99% confident that he will make a right
decision.
Errors
The probability of committing a Type I error is
called the significance level of a test.
For any hypothesis test,
p-value = probability of committing a
Type I error
Errors
