Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                

T-Test Z Test

Download as pptx, pdf, or txt
Download as pptx, pdf, or txt
You are on page 1of 33

Hypothesis Testing

Test Statistics
Z- test Using One-Sample Mean

Problem: An electrical Company claims that lives of the light bulbs if


manufactures are normally distributed with a mean of 1000 hours and a
standard deviation of 150 hours. What can you say about this claim if a random
sample of 100 bulbs produced by this company has a mean life of 980 hours?
Use 0.05 level of significance.
Solution:
Step 1.State the null and alternative hypothesis.
Ho: The average life of all the bulbs produced by the firm is 1000 hours
( = 1000).
Ha: The average life of all the bulbs produced by the firm is not equal to
1000 hours ( 1000).

Step 2. Specify the level of significance.


Use = 0.05

Step 3. Determine the test statistic to be used.


Z-test using one sample mean should be used since n=100 (n30) at
= 0.05, Zt = 1.96
Step 4. Compute the value.
- n
Zc=
s

980 1000 100


= -----------------------
150

-20 100 -200


= ------------ = ---------------------- Zc = -1.33
150 150

Step 5. The /Zc= -1.33/ < / Zt = 1.96.


Since the /Zc value/ is less than /Zt value/, accept the null hypothesis
and reject the alternative hypothesis.

Step 6. Therefore, there is a sufficient evidence to support the claim of the


manufacturer that the average life of the bulbs it produces is 1000
hours.
Z- Test Using Two-Sample Means

Problem: A bank is opening a new branch in one of two


neighborhoods. One of the factors considered by the bank as
whether the average monthly family income (in thousand
pesos) in the two neighborhoods differed. From census
records, the bank drew two random samples of 100 families
each and obtained the following information:
Neighborhood
Sample A Sample B
X = 10,800 X = 10,300
S = 300 S = 400
n = 100 n = 100

The bank wishes to test the null hypothesis that the two
neighborhoods have the same mean income. What should
the bank conclude? Test the hypothesis using = 0.05.
Solution:
Step 1.State the null and alternative hypothesis.

Ho: The average monthly family income of the two


neighborhoods, A and B are equal.

Ha: The average monthly family income of neighborhood A


is not equal to neighborhood B.

Step 2. Specify the level of significance.


Use = 0.05

Step 3. Determine the test statistic to be used.

Z-test using two sample means should be used since n=100


(n30) at = 0.05, Zt = 1.96.
Step 4. Compute the value.
X -- X
Zc=
S S
n n

10,800 - 10,300
=
300 400
100 100

500 500
= =
90,000 160,000 2,500
100 100
= 500
500 50
=
900 1,600 Zc= 10
Step 5. Decision:

The /Zc= 10/ > / Zt = 1.96.


Since the /Zc value/ is greater than /Zt value/,
reject the null hypothesis and accept the
alternative hypothesis.

Step 6. Conclusion

The average family income of neighborhood A is


higher than that of neighborhood B at = 0.05.
T- test Using Two-sample Means

Problem: A taxi company is trying to determine whether the use of radial tires
and belted tires provide the same fuel. Twelve cars were driven twice
over a prescribed test course; and for each test, a car used a different
type of tire ( radial or belted) in random order. The data obtained were
recorded as follows:

Type of tire X S

Radial 5.75 1.10

Belted 5.61 1.30

At 0.05 level of significance, can we conclude that cars equipped with


radial tires and belted tires provide the same fuel consumption?
Assume that data are normally distributed.
Step 1.State the null and alternative hypothesis.
Ho: There is no significant difference on the fuel
consumption of cars using radial and belted tires.
Ha: There is a significant difference.
Step 2. Specify the level of significance.
0.05

Step 3. Determine the test statistic to be used.


t-test; df = 12+12-2 = 22
tabular value: 2.074
two-tailed test
Step 4. Compute the value.
X - X
tc =
[S (n - 1) + S (n - 1)] 1 1
(n + n) 2 n n

5.75 5.61
=
[ (1.10) (12 1) + (1.30) (12 1) ] ( + )
(12 + 12) -2

0.14
=
1.21 (11) + 1.69 (11) ()
22
0.14
=
13.31 + 18.59 ( )
22

0.14
=
31.9 ( 1/6 )
22

0.14
=
0.241666666

0.14
= tc = 0.285
0.49159604
Step 5. Decision:

The /tc= 0.285/ < / Tt = 2.074.


Since the /tc value/ is less than /Tt value/, accept the
null hypothesis and reject the alternative hypothesis.

Step 6. Conclusion

Therefore, we can say that there is no significant


difference on the fuel consumption of cars using radial and belted
tires at = 0.05, with df = 22.
Analysis of Variance

Example

1. In a Statistics class, 10 students are randomly assigned to each


of four groups. Each group is asked to perform a set of tasks
after exposure to the experimental treatment. Do the groups
differ in task performance? Use the raw score method to test
this problem at 5% level of significance.
Analysis of Variance

Group 1 Group 2 Group 3 Group 4


20 19 18 16
18 18 18 16
17 18 15 15
17 17 14 15
15 15 13 14
14 14 12 12
12 13 12 12
11 13 11 10
10 10 10 8
10 8 9 5
Anova: Single Factor

SUMMARY
Groups Count Sum Average Variance

Column 1 10 144 14.4 12.71111

Column 2 10 145 14.5 13.16667

Column 3 10 132 13.2 9.511111

Column 4 10 123 12.3 13.56667


ANOVA

Source of Variation SS df MS F P-value F crit

Between Groups 33 3 11 0.898774 0.451281 2.866266

Within Groups 440.6 36 12.23889

Total 473.6 39
Analysis of Variance

Assignment:

1. Three different milling machines were being considered for


purchase by a clothing manufacturing company. The company
would be purchasing hundreds of these machines. To make
sure it made the best decision, the company borrowed five of
each machines and were assigned to 15 technicians. Each
machine was put through a series of tasks and was rated using
a standard test. The following results were obtained:
1. State the hypothesis:

Ho: There is no significant difference among the


performance using a standardized test of the three
machines.

Ha: There is a significant difference among the performance


using a standardized test of the three machines.

2. Level of significance: = 0.01

3. Test statistic: F test


Analysis of Variance

Machine 1 Machine 2 Machine 3


24.5 28.4 26.1
23.5 34.2 28.3
26.4 29.5 24.3
27.1 32.2 26.2
29.9 30.1 23.8
SUMMARY

Groups Count Sum Average Variance

Column 1 5 131.4 26.28 6.172

Column 2 5 154.4 30.88 5.357

Column 3 5 128.7 25.74 3.183


ANOVA

Source of
SS df MS F P-value F crit
Variation

Between
79.78533 2 39.89267 8.13472 0.00585 6.9266
Groups

Within
58.848 12 4.904
Groups

Total 138.6333 14
5. Decision: Since the computed value is greater than the
tabular value, reject the null hypothesis and accept the
alternative hypothesis.

6. Conclusion: Thus, there is a significant difference among


the performance using a standardized test of the three
machines at = 0.01.
Pearsons Product Moment Correlation Coefficient

Assignment

1. To determine the relationship between years of


education and salary potential, 10 persons who have
been employed for 5 years were interviewed. The results
obtained on their number of years of higher education
(college degree and higher) and their monthly salaries
are shown in the following table:
Assignment
Below are data from an experiment on the
effects of sleep deprivation on the time it takes to
solve mathematical problems. Subjects went without
sleep for either 16, 24, 32 or 40 hours. Are increased
levels of sleep loss associated with longer problem
solving time? Do a test statistic using 5% level of
significance.
Problem Solving Time (in hours)

Hours without Sleep


16 24 32 40
4 4 5 5
4 6 6 6
5 6 8 7
6 7 8 10
7 8 9 11
7 8 9 11
1. Ho: There is no significant difference on the time
solving two mathematical problems when categorized
according to the hours without sleep.

Ha: There is a significant difference on

2. 0.05 level of significance

3. Analysis of Variance using F-test


Ft (3, 21) = 3.07
4. Compute:
ANOVA: Single Factor

SUMMARY
Groups Count Sum Average Variance
16 Hours 6 33 5.5 1.9
24 Hours 6 39 6.5 2.3
32 Hours 6 45 7.5 2.7
40 Hours 6 50 8.333333 7.066667
ANOVA

Source of Variation SS df MS F P-value F crit

Between Groups 27.125 3 9.041667 2.589499 0.08139 3.098391

Within Groups 69.83333 20 3.491667

Total 96.95833 23
5. Since the computed value (Fc = 2.60) is less
than the tabular value (Ft = 3.07), accept the
null hypothesis and reject the alternative
hypothesis.

6. Thus, there is no significant difference on the


time solving two mathematical problems
when categorized according to the hours
without sleep at = 0.05.
Chi-Square
Pearsons Product Moment Correlation Coefficient
Employee Salary in Years in Higher
P1000s Education
A 21.4 4
B 18.7 4
C 27.5 5
D 42 8
E 12.6 1
F 25.3 5
G 55.5 10
H 17.3 4
I 48.8 8
J 14 1

You might also like