Beruflich Dokumente
Kultur Dokumente
TEST OF HYPOTHESES:
TWO SAMPLES
PREPARED BY: ENGR. KRISTAN IAN CABANA
OUTLINE
( x1 − x2 ) − ( 1 − 2 )
Zc =
2
2
1
+ 2
n1 n2
DIFFERENCE BETWEEN MEANS, VARIANCES KNOWN
MODULE 4
ILLUSTRATIVE EXAMPLE
ILLUSTRATIVE EXAMPLE
STEP 1: State the null and alternative hypotheses.
H0: 𝝁𝟏 = 𝝁𝟐 or 𝝁𝟏 − 𝝁𝟐 = 𝟎
(There is no difference between the two means of ACT Math scores.)
Ha: 𝝁𝟏 > 𝝁𝟐 or 𝝁𝟏 − 𝝁𝟐 > 𝟎
(There is a difference between the two means of ACT Math scores.)
STEP 2: Choose the level of significance, type of test, and sample size.
Level of significance, α = 0.10 ; Right-Tailed Test; n1 = 49 students and
n2 = 44 students
STEP 3: Identify the critical value of the test statistic.
Test Statistic, 𝑍𝑡 = + 1.28
DIFFERENCE BETWEEN MEANS, VARIANCES KNOWN
MODULE 4
ILLUSTRATIVE EXAMPLE
STEP 4: Determine the rejection region.
0.10
z
0 Z = 1.28
ILLUSTRATIVE EXAMPLE
STEP 6: State the Decision Rule.
STEP 7: Interpretation.
There is enough evidence at the 10% level to support the teacher’s claim
that her students score better on the ACT.
INFERENCE ON THE
DIFFERENCE IN MEANS
OF TWO NORMAL
DISTRIBUTIONS,
VARIANCES UNKNOWN
DIFFERENCE BETWEEN MEANS, VARIANCES UNKNOWN
MODULE 4
( x1 − x2 ) − ( 1 − 2 ) ( x1 − x 2 ) − ( 1 − 2 )
tc = tc =
1 1 s12 s 22
Sp + +
n1 n2 n1 n2
Where Pooled Estimator of Variance s12 s 22
2
+
(n1 − 1) S12 + (n2 − 1) S 22 Degrees of n1 n2
Sp = =
n1 + n2 − 2 Freedom s2
2
s 2
2
n
1
n 2
1
+
2
𝐷𝑒𝑔𝑟𝑒𝑒𝑠 𝑜𝑓 𝐹𝑟𝑒𝑒𝑑𝑜𝑚 = 𝑛1 + 𝑛2 − 2 n1 − 1 n2 − 1
DIFFERENCE BETWEEN MEANS, VARIANCES UNKNOWN
MODULE 4
DIFFERENCE BETWEEN MEANS, VARIANCES UNKNOWN
MODULE 4
ILLUSTRATIVE EXAMPLE
ILLUSTRATIVE EXAMPLE
STEP 1: State the null and alternative hypotheses.
H0: 𝝁𝟏 = 𝝁𝟐 or 𝝁𝟏 − 𝝁𝟐 = 𝟎
(There is no difference between the mean annual incomes.)
Ha: 𝝁𝟏 ≠ 𝝁𝟐 or 𝝁𝟏 − 𝝁𝟐 ≠ 𝟎
(There is a difference between the mean annual incomes.)
STEP 2: Choose the level of significance, type of test, and sample size.
Level of significance, α = 0.01 ; Two-Tailed Test; n1 = 14 police officers and
n2 = 15 police officers; df = 14+15-2 = 27
STEP 3: Identify the critical value of the test statistic.
Test Statistic, 𝑡𝑡 = + 2.771
DIFFERENCE BETWEEN MEANS, VARIANCES UNKNOWN
MODULE 4
ILLUSTRATIVE EXAMPLE
STEP 4: Determine the rejection region.
ILLUSTRATIVE EXAMPLE
STEP 6: State the Decision Rule.
STEP 7: Interpretation.
There is not enough evidence at the 1% level to support the claim that
the mean annual incomes differ.
DIFFERENCE BETWEEN MEANS, VARIANCES UNKNOWN
MODULE 4
ILLUSTRATIVE EXAMPLE
Arsenic concentration in public drinking water supplies is a
potential health risk. An article in the Arizona Republic (2001
Issue) reported drinking water arsenic concentrations in
parts per billion (ppb) for 10 metropolitan Phoenix
communities with a sample mean of 12.5 and standard
deviation of 7.63, and 10 communities in rural Arizona with a
sample mean of 27.5 and standard deviation of 15.3.
Determine whether any difference exists in mean arsenic
concentrations. Assume that the population variances are
not the same.
DIFFERENCE BETWEEN MEANS, VARIANCES UNKNOWN
MODULE 4
ILLUSTRATIVE EXAMPLE
STEP 1: State the null and alternative hypotheses.
H0: 𝝁𝟏 = 𝝁𝟐 or 𝝁𝟏 − 𝝁𝟐 = 𝟎
(There is no difference between the mean arsenic concentration of
the Metro Phoenix and Rural Arizona.)
Ha: 𝝁𝟏 ≠ 𝝁𝟐 or 𝝁𝟏 − 𝝁𝟐 ≠ 𝟎
(There is a difference between the mean arsenic concentration of the
Metro Phoenix and Rural Arizona.)
STEP 2: Choose the level of significance, type of test, and sample size.
Level of significance, 7.632ൗ + 15.32ൗ
2
10 10
α = 0.05 ; Two-Tailed; 𝑑𝑓 = 2 2 = 13.2 𝑜𝑟 13
2
7.63 ൗ 2
15.3 ൗ
n1 = 10 and n2 = 10 10 ൘ 10 ൘
10 − 1 + 10 − 1
DIFFERENCE BETWEEN MEANS, VARIANCES UNKNOWN
MODULE 4
ILLUSTRATIVE EXAMPLE
STEP 3: Identify the critical value of the test statistic.
Test Statistic, 𝑡𝑡 = + 2.160
ILLUSTRATIVE EXAMPLE
12.5 − 27.5 − 0
𝑡𝑐 = = −2.77
7.632 15.32
+
10 10
DIFFERENCE BETWEEN MEANS, VARIANCES UNKNOWN
MODULE 4
ILLUSTRATIVE EXAMPLE
STEP 6: State the Decision Rule.
STEP 7: Interpretation.
ഥ − 𝜇𝐷
𝐷
𝑧𝑐 = 𝜎
𝐷
ൗ 𝑛
σ𝑛
𝑖=1 𝐷𝑖
Where: ഥ=
𝐷
𝑛
μD = hypothesized mean difference
σD = population standard deviation of the difference scores
n = sample size
𝐷𝑖 = difference between two samples
COMPARING MEANS OF TWO RELATED POPULATIONS
MODULE 4
ഥ − 𝜇𝐷
𝐷
𝑡𝑐 = 𝑠
𝐷
ൗ 𝑛
σ𝑛
𝑖=1 𝐷𝑖
Where: ഥ=
𝐷 2
𝑛 σ𝑛𝑖=1(𝐷𝑖ഥ
− 𝐷൯
μD = hypothesized mean difference 𝑠𝐷 =
n = sample size 𝑛−1
𝐷𝑖 = difference between two samples
COMPARING MEANS OF TWO RELATED POPULATIONS
MODULE 4
ILLUSTRATIVE EXAMPLE
A reading center claims that students will perform better on
a standardized reading test after going through the reading
course offered by their center. The table shows the reading
scores of 6 students before and after the course. At = 0.05,
is there enough evidence to conclude that the students’
scores after the course are better than the scores before the
course?
Student 1 2 3 4 5 6
Score (before) 85 96 70 76 81 78
Score (after) 88 85 89 86 92 89
COMPARING MEANS OF TWO RELATED POPULATIONS
MODULE 4
ILLUSTRATIVE EXAMPLE
STEP 1: State the null and alternative hypotheses.
H0: 𝝁𝑫 = 𝟎
(The students’ scores after the exams are not better.)
Ha: 𝝁𝑫 < 𝟎
(The students’ scores after the exams are better.)
STEP 2: Choose the level of significance, type of test, and sample size.
Level of significance, α = 0.05 ; Left-Tailed; n = 6; df = 6-1 = 5
COMPARING MEANS OF TWO RELATED POPULATIONS
MODULE 4
ILLUSTRATIVE EXAMPLE
STEP 3: Identify the critical value of the test statistic.
Test Statistic, 𝑡𝑡 = - 2.015
Rejection Region
z
t = -2.015 0
COMPARING MEANS OF TWO RELATED POPULATIONS
MODULE 4
ILLUSTRATIVE EXAMPLE
STEP 5: Calculate the standardized test statistic.
Student 1 2 3 4 5 6 𝐷𝑖 = −43
Score (before) 85 96 70 76 81 78
Score (after) 88 85 89 86 92 89 −43
ഥ=
𝐷 = −7.167
d −3 11 −19 −10 −11 −11 6
d2 9 121 361 100 121 121 𝑠𝐷 = 10.245
ഥ − 𝜇𝐷 −7.167 − 0
𝐷
𝑡𝑐 = 𝑠 = = −1.714
𝐷
ൗ 𝑛 10.245ൗ
6
COMPARING MEANS OF TWO RELATED POPULATIONS
MODULE 4
ILLUSTRATIVE EXAMPLE
STEP 6: State the Decision Rule.
STEP 7: Interpretation.
There is not enough evidence at the 5% level to support the claim that
the students’ scores after the course are better than the scores before
the course.
COMPARING TWO POPULATION
PROPORTIONS
COMPARING TWO POPULATION PROPORTIONS
MODULE 4
1 − 𝑃
𝑃 2 − (𝑃1 − 𝑃2 )
𝑍=
ത 1 1
𝑃(1 − 𝑃) 𝑛 + 𝑛
1 2
WITH
x1 + x2 p1 =
x1
p2 =
x2
p=
n1 + n2 n1 n2
COMPARING TWO POPULATION PROPORTIONS
MODULE 4
ILLUSTRATIVE EXAMPLE
A recent survey stated that male college students smoke
less than female college students. In a survey of 1245 male
students, 361 said they smoke at least one pack of cigarettes
a day. In a survey of 1065 female students, 341 said they
smoke at least one pack a day. At = 0.01, can you support
the claim that the proportion of male college students who
smoke at least one pack of cigarettes a day is lower then the
proportion of female college students who smoke at least
one pack a day?
END OF PRESENTATION