Scribd
Upload
21 views15 pages

Statistics For MGT II - CH 3

The document discusses hypothesis testing, including the different types of hypotheses, errors, and steps to conduct a hypothesis test. It provides examples to illustrate key concepts like null and alternative hypotheses, test statistics, significance levels, and conducting hypothesis tests on means, proportions and more.

Uploaded by

Eyoseyas
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
21 views15 pages

Statistics For MGT II - CH 3

The document discusses hypothesis testing, including the different types of hypotheses, errors, and steps to conduct a hypothesis test. It provides examples to illustrate key concepts like null and alternative hypotheses, test statistics, significance levels, and conducting hypothesis tests on means, proportions and more.

Uploaded by

Eyoseyas
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 15

Chapter Three

Hypothesis Testing
 Usually, when we make predictions or
estimates about the population measures we
have no idea of the actual values of the
measure we are trying to estimate.
 Hypothesis – is the claim about the population
parameter measures to be a particular value
 Hypothesis Testing – the use of sample results
to investigate whether the claim is true called
hypothesis testing.
Cont…
 There are two types of statistical hypothesis for each
situation, the null hypothesis and the alternative
hypothesis.
 In hypothesis testing we begin by making a
tentative assumptions about a population
parameter.
 This tentative assumption or stated claim is
called the null hypothesis (denoted by H0).
 The hypothesis to be accepted if the null
hypothesis is rejected is an alternative
hypothesis, denoted by Ha.
Cont…
 Summary of forms of null and alternative hypothesis:
H0: µ > X H0: µ < X H0: µ = X
Ha: µ < X Ha: µ > X Ha: µ ≠ X
• The equality part of the expression (either >, < or
=) usually appears in the null hypothesis.
 Type I and Type II errors
 Ideally the hypothesis testing procedure should
lead to the acceptance of H0 when H0 is true and
the rejection of H0 when Ha is true.
 In hypothesis testing there are two correct
decisions and two wrong decisions
Cont…
Population condition
When H0 is true When H0 is false

Right decision Type II error


Accept H0
Decision
Reject H0 Type II error Right
decision
Cont…
 A type I error occurs if you reject the null hypothesis when it is
true
 A type II error occurs if you do not reject the null hypothesis
when it is false
*The probability of making a type I error is called the level of
significance, denoted by∂.
 There are two types of tests
1. One- tail tests – when the rejection region is located only in one
of the tail areas;
i. Lower (left) tail test- the rejection region is located to the left tail of
the distribution.
When H0 stated as µ > X
ii. Upper (Right) tail test – the rejection region is
located to the right tail of the distribution.
When H0 stated as µ < X
Cont…

2. Two - tail test - When the rejection areas


are located on both tails of the distribution.
The general form of two tail test about µ;
It occurs When H0: µ = X and H0: µ ≠ X
Steps of hypothesis Testing
Step 1. Develop the null and alternative
hypothesis
Step 2. Specify the level of significance
Step 3. collect the sample data and compute the
value of the test statistics
Step 4. Use the level of significance to
determine the critical value and the rejection
rule
Step 5. Use the value of the test statistics and the
rejection rule to decide whether to reject H 0.
Cont…
E.g. 1. A company claims that the mean monthly salary
of its employee is 4000birr or more. To test the claim, a
sample of 36 employees was drawn and the sample
mean is computed to be 3,900birr. Assuming the
population standard deviation is known to be 300birr,
use a significance level of 5% and test the claim of the
company.
Solution
Step 1. state H0 and Ha
H0: µ > 4000
Ha: µ < 4,000
Step 2. ∂ = 5% = 0.05
Cont…
Step 3. compute the test statistics value
Z= =
σX̄ = = = = 50
Z= = -2
Step 4. determine the critical points and develop the
decision rule
∂ = 0.05 and it is the left tail test
for 5% ∂ of one tail test Z value is equal to 1.65
* Since it is a left tail test, Z value is negative (-1.65)
Decision rule;
- Reject H0 if the test statistics value is < -1.65
- Do not reject H0 if the test statistics value is > -1.65
Step 5. Decision – reject H because -2 < -1.65
Cont…
E.g. 2 A department claims that the mean age of
first year students enrolled to the department is
20 years. To test the claim, a researcher took a
random sample of 25 students and found the
sample mean age of 21 with a standard deviation
of 2 years. Use a 5% significance level and test
the claim.
Step 1. H0: µ = 20
Ha: µ ≠ 20
Step 2. ∂ = 5% = 0.05
Cont…
Step 3. t=, σX̄ = = = 0.4
t = = 2.5
Step 4. ∂ = 0.05 and it is a two tail test. Therefore, ∂ is
divided
by 2. Then, = 0.025
df = n-1 = 25-1 = 24
t value (24df, ∂ =0.025) = 2.064
Decision rule
- Reject H0 if the t value is < -2.064 or > 2.064
-Do not reject H0 if the t value lies b/n -2.064 and 2.064
Step 5. Decision
reject H0 because 2.5 > 2.064
Hypothesis testing about P
The 3 forms of a hypothesis test about P are as
follows. H0: P > P0 H0: P < P0 H0: P = P0
Ha: P < P0 Ha: P > P0 Ha: P ≠ P0
Z= and =

E.g. A manufacturing company believes that the


proportion of defective items produced is not
more than 5% of the total items produced. The
randomly selected 100 items produced show that
7% of them are defective items. With 10% level
of significance test the claim of the company.
Cont…
1. H0: P < 5%
Ha: P > 5%
2. ∂ = 10% = 0.1
3. Z = , first, = = = 0.0218
Z = = 0.92
4. ∂ = 10% and it is a one-tail test, z value at the critical
point = 1.28
Decision rule;
- Reject H0 if Z value > 1.28
-Do not reject H0 if Z value < 1.28
5. Decision
don’t reject H0
End of Chapter Three

You might also like