Professional Documents
Culture Documents
Keeping Records
based on observations Decision
-Making
Organizing Data
according to records
2
© 1984-1994 T/Maker Co.
Statistics
A collection of principles and
methods concerned with extracting
useful information from a set of
data to help managers make
decisions.
The subject of statistics can be
sub-divided into two basic areas:
Descriptive statistics
Inferential statistics 3
Descriptive Statistics
• Collect data
e.g. Survey
• Present data
e.g. Tables and graphs
• Characterize data
e.g. Sample mean = X i
n
4
Inferential Statistics
• Estimation
e.g. Estimate the population
mean weight using the
sample mean weight
• Hypothesis testing
e.g. Test the claim that the population mean
weight is 120 pounds
Drawing conclusions and/or making decisions
concerning a population based on sample results.
5
Problem Under Study
Data
Survey Experiment
– population mean
Example: The mean monthly cell phone bill of
this city is μ = $42
– population proportion
Example: The proportion of adults in this city
with cell phones is π = 0.68
The Null Hypothesis, H0
• States the claim or assertion to be tested
Example: The average number of TV sets in
( 0 :μ 3 )
U.S. Homes is equal to three H
Claim: the
population
mean age is 50.
(Null Hypothesis:
Population
H0: μ = 50 )
Now select a
random sample
Is X 20 likely if μ = 50?
If not likely, Suppose
the sample
REJECT mean age Sample
Null Hypothesis is 20: X = 20
Testing of Hypothesis: Objectives
• Normal Test
• t - Test
• Chi - Square Test
• F - Test
The Normal Distribution
Changing σ increases or
decreases the spread.
σ
μ X
The Normal Distribution:
as mathematical function (pdf)
1 x 2
1 ( )
f ( x) e 2
2
This is a bell shaped
Note constants: curve with different
=3.14159 centers and spreads
e=2.71828 depending on and
Normal distribution is defined by
its mean and standard dev.
2
x ~ N (μ, σ )
E(X)=
Var(X)=2
Standard Deviation(X)=
68-95-99.7 Rule
68% of
the data
H0 : = 0 or
Test Criteria
Depending on the alternative hypothesis selected, the test
criteria is as follows:
Reject H0 at level
H1 Test of significance
if
0 Two-tailed test Z> Z/2
< 0 Left-tailed test Z < -Z
> 0 Right-tailed test Z > Z
5% 1.960 1.645
1% 2.580 2.330
Test for the Mean…
X μ 2.84 3 .16
Z 2.0
σ 0.8 .08
n 100
Hypothesis Testing Example
(continued)
• 6. Is the test statistic in the rejection region?
= 0.05/2 = 0.05/2
= 0.05/2 = 0.05/2
Under H0,
18.7 19.0
Z 1.440
1.25
36
H0 is accepted at 5% level of significance.
Test for Difference of Means
H0 : 1 = 2
Z = 3.36
Z > 1.96, H0 is rejected. The average expenditure per month
per family in the two populations is not equal.
Test for Difference of Means…
Under H0
x1 x 2 x1 x 2
Z if σ12 σ 22 σ 2
σ12 σ 22 1 1
σ
n1 n 2 n1 n 2
n Sample size
x Persons possessing the given attribute
x
p Observed proportion of successes
n
P Population proportion, Q = 1- P
H0: P = P0
Test Criteria:
Reject H0 at level of
H1 Test
significance if
P P0 Two-tailed test Z> Z/2
P < P0 Left-tailed test Z < -Z
P > P0 Right-tailed Z > Z
test
Test for Single Proportion…Example
Q =1-P
p1 p 2
Z
1 1
PQ( )
n1 n 2
n1p1 n 2 p 2
P
n1 n 2
Test for difference of proportions…Example
In a district, 450 persons were regular consumers of tea out of a
sample of 1000 persons. In another district, 400 were regular
consumers of tea out of a sample of 800 persons. Is there a
significant difference between the two districts as far as tea
drinking habit is concerned?
Solution: H0: P1 = P2 = P
H1: P1 P2
0.45 0.5
Z 2.08
1 1
0.47x0.53( )
1000 800
Test Criteria:
Reject H0 at level
H1 Test
of significance if
0 Two-tailed test t> tn-1(/2)
< 0 Left-tailed test t < -tn-1()
> 0 Right-tailed t > tn-1()
test
Test for the Mean…Example
Suppose the claim has been made that the height of adult males in a
college is different from what it used to be and we wish to test this
hypothesis. A campus wide survey made 20 years ago found that the
mean height of males was 69.5 in. To study this, a random sample of
15 males of the same age from current students was taken and their
height recorded.
Solution:
H0: The average height is 69.5 in.
H1: The average height is more than 69.5 in. 65.0, 67.5, 68.0,
x 70.4 s 0.71 68.5, 69.0, 69.5,
69.5, 70.0, 71.0,
70.4 69.5 71.5, 71.5, 72.5,
t 1.27 ~ t14
0.71/ 15 72.5, 74.5, 75.5
Since |t| < 2.14 (value of t at 5% and 14 d.f), the mean height is 69.5
in.
t-table
p
0.50 0.10 0.05 0.02 0.01
n
1 1.000 6.34 12.71 31. 82 63.66
2 0.816 2.92 4.30 6.96 9.92
3 0.765 2.35 3.18 4.54 5.84
4 0.741 2.13 2.78 3.75 4.60
5 0.727 2.02 2.57 3.36 4.03
6 0.718 1.94 2.45 3.14 3.71
7 0.711 1.90 2.36 3.00 3.50
8 0.706 1.86 2.31 2.90 3.36
9 0.703 1.83 2.26 2.82 3.25
10 0.700 1.81 2.23 2.76 3.17
11 0.697 1.80 2.20 2.72 3.11
12 0.695 1.78 2.18 2.68' 3.06
13 0.694 1.77 2.16 2.65 3.01
14 0.692 1.76 2.14 2.62 2.98
15 0.691 1.75 2.13 2.60 2.95
16 0.690 1.75 2.12 2.58 2.92
17 0.689 1.74 2.11 2.57 2.90
18 0.688 1.73 2.10 2.55 2.88
19 0.688 1.73 2.09 2.54 2.86
20 0.687 1.72 2.09 2.53 2.84
Test for the Difference of Two Population Means
Blue Overlay – 70, 80, 90, 80, 50, 80, 70, 80, 70, 80, 80, 70
Clear Overlay – 50, 40, 50, 50, 60, 60, 60, 40, 60, 70, 60, 80
Solution:
H0 : 1 = 2 H1 : 1 > 2
x1 75, x 2 56.7,
s12 100, s 22 133.3
t 4.15 ~ t 22
When n1 = n2 = n
Let di = xi - yi
H0 : 1 - 2 = 0
Before training: 49 53 51 52 47 50 52 53
After training: 52 55 52 53 50 54 54 53
Solution:
H0 : B = A H 1 : B < A
2
Researcher No. Before After di = xi - ydi i
(xi) (yi)
1. 49 52 -3 9
2. 53 55 -2 4
3. 51 52 -1 1
4. 52 53 -1 1
5. 47 50 -3 9
6. 50 54 -4 16
7. 52 54 -2 4
8. 53 53 0 0
Paired t-test…Example
1 n - 16
d di -2
n i 1 8
1 n
s (d i d) 2 1.714
2
7 i 1
|d| 2
| t | 4.32 ~ t 7
s/ n 1.714/ 8
H0 : σ 2 σ 02
2
n xi x
2
~ 2n -1
i 1 σ 0 when is unknown
Chi-Square tests… Example
x 2.51 2
n xi x
2
1.182
i 1 σ 0
Test Statistic:
Oi Observed frequency of ith class
Ei Expected frequency of ith class, i =1,…,n.
n
2
Oi E i 2 ~ 2n -r -1
i 1 Ei
Test of Goodness of Fit…Example
• They were asked to taste the four brands without disclosing the
brand name and then declare their preference.
H0 : PA =PB = PC = PD = 0.25
Test of Goodness of Fit…Example
Frequency
Observed (Oi) Expected (Ei) Oi - Ei
20 25 -5
31 25 6
28 25 3
21 25 -4
2
(O E ) 2
2 i i
3.44
i 1 Ei
Since 3.44 < 7.82 (value of chi-square at 5% and 3 d.f), the result is
not significant and hence the proportion is same which is 1/4.
Table of Chi-square
p
0.99 0.95 0.50 0.30 0.20 0.10 0.05 0.01
n
1 0.0002 0.004 0.46 1.07 1.64 2.71 3.84 6.64
2 0.020 0.103 1.39 2.41 3.22 4.00 5.99 9.21
3 0.115 0.35 2.17 3.66 4.64 6.25 7.82 11.34
4 0.30 0.71 3.86 4.88 5.99 7.78 9.49 13.28
5 0.55 1.14 4.35 6.06 7.29 9.24 11.07 15.09
6 0.87 1.64 5.35 7.23 8.56 10.64 12.59 16.81
7 1.24 2.17 6.35 8.38 9.80 12.02 14.07 18.48
8 1.65 2.73 7.34 9.52 11.03 13.36 15.51 20.09
9 2.09 3.32 8.34 10.66 12.24 14.68 16.92 21.67
10 2.56 3.94 9.34 11. 78 13.44 15.99 18.31 23.21
11 3.05 4.58 10.34 12.90 14.63 17.28 19.68 24.72
12 3.37 5.23 11.34 14.01 15.81 18.55 21.03 26.22
13 4.11 5.89 12.34 15.12 16.98 19.81 22.36 27.69
14 4;66 6.57 13.34 16.22 18.15 21.06 23.68 29.14
15 5.23 7.26 14.34 17.32 19.31 22.31 25.00 30.58
16 5.81 7.96 15.34 18.42 20.46 23.54 26.30 32.06
17 6.41 8.67 16.34 19.51. 21.62 24.77 27.59 33.41
18 7.02 9.39 17.34 20.60 22.76 25.99 28.87 34.80
19 7.63 10.12 18.34 21.69 23.90 27.20 30.14 36.19
20 8.26 10.85 19.34 22.78 25.04 28.41 31.41 37.57
Test of Independence
Contingency Table
Class A1 A2 A3
Test Statistic:
Oij Observed frequency
Eij Expected frequency i =1,…,r; j =1,…,s
c r (Oij - E ij ) 2
2 ~ (r2 -1) (c-1)
j1 i 1 E ij
From the following table, test the hypothesis that the test
result is related to the sex of the student:
χ 2 0.492 ~ χ 12
χ 12 (5%) 3.84
Test of Independence…Example 2
Educational Standard
Illiterat Matric Graduat Post
e e Graduate
Adopted 60 70 35 25
(110.2) (38.0) (20.9) (20.9)
Not 230 30 20 30
Adopted (179.8) (62.0) (34.1) (34.1)
χ 2 96.99 ~ χ 32 χ 32 (5%) 7.82 χ 32 (1%) 11.34
F- tests
1 n1 1 n2
s12 i 1 ,
(x x ) 2
s 22 j 2
(x x ) 2
n1 1 i1 n 2 1 j1
1 n1 1 n2
x1 x i , x2 xj
n1 i 1 n 2 j1
F- test…
2 2
H0 : σ1 σ 2
Test Statistic:
s12
F 2 ~ Fn1 1, n 2 1
s2
Solution: n1 = 6, n2 = 5
H0 : σ1 σ 2 ,
2 2
H1 : 12 22
s12
F 2 4.08 ~ F5, 4
s2
2 18.51 19.00 19.16 19.25 19.30 19.33 19.37 19.41 19.45 19.50
3 10.13 9.55 9.28 9.12 9.01 8.94 8.84 8.74 8.64 8.53
4 7.71 6.94 6.59 6.39 6.26 6.16 6.04 5.91 5.77 5.63
5 6.61 5.79 5.41 5.19 5.05 4.95 4.82 4.68 4.53 4.36
6 5.99 5.14 4.76 4.53 4.39 4.28 4.15 4.00 3.84 3.67
7 5.59 4.74 4.35 4.12 3.97 3.87 3.73 3.57 3.41 3.23
8 5.32.. 4.46 4.07 3.84 3.69 3.58 3.44 3.28 8.12 2.93
9 5.12 4.26 3.86 3.63 3.48 3.37 3.23 3.07 2.90 2.71
10 4.96 4.10 3.71 3.48 3.33 3.22 3.07 2.91 2.74 2.54
12 4.75 3.88 3.49 3.26 3.11 3.00 2.85 2.69 2.50 2.30
14 4.60 3.74 3.34 3.11 2.96 2.85 2.70 2.53 2.35 2.13
16 4.49 3.63 3.24 3.01 2.85 2.74 2.59 2.42 2.24 2.01
18 4.41 3.55 3.16 2.93 2.77 2.66 2.51 2.34 2.15 1.92
20 4.35 3.49 3.10 2.87 2.71 2.60 2.45 2.28. 2.08 1.84
25 4.24 3.38 2.99 2.76 2.60 2.49 2.34 2.16 1.96 1.71
30 4.17 3.32 2.92 2.69 2.53 2.42 2.27 2.09 1.89 1.62
40 4..08 3.23 2.84 2.61 2.45 2.34 2.18 2.00 1.79 1.51
60 4..00 3.15 2.76 2.52 2.37 2.25 2.10 1.92. 1.70 1.39
80 3.96 3.11 2.72 2.49 2.33 2.21 2.06 1.88 1.65 1.32
Example: Z Test for
Proportion
A marketing company
claims that it receives
8% responses from its
mailing. To test this
claim, a random sample
of 500 were surveyed
Check:
with 25 responses. Test
at the = 0.05 n π = (500)(.08) = 40
significance level. n(1-π) = (500)(.92) = 460
Z Test for Proportion: Solution
Test Statistic:
H0: π = 0.08
H1: π 0.08 p .05 .08
Z 2.47
(1 ) .08(1 .08)
= 0.05
n 500
n = 500, p = 0.05
Critical Values: ± 1.96 Decision:
Reject Reject Reject H0 at = 0.05
Conclusion:
.025 .025
There is sufficient
-1.96 0 1.96 z evidence to reject the
-2.47 company’s claim of 8%
response rate.
Example: Two-Tail Test
( Unknown)
The average cost of a
hotel room in New York
is said to be $168 per
night. A random sample
of 25 hotels resulted in
X = $172.50 and
H0: μ= 168
S = $15.40. Test at the
H1: μ 168
= 0.05 level.
(Assume the population distribution is normal)
Example Solution:
Two-Tail Test
H0: μ= 168 /2=.025 /2=.025
H1: μ 168
t24 = ± 2.0639 Do not reject H0: not sufficient evidence that true
mean cost is different than $168