Академический Документы
Профессиональный Документы
Культура Документы
What is a Hypothesis?
,
A hypothesis is a claim
(assumption) about a
population parameter:
population mean
Example: The mean monthly cell phone bill
of this city is = $42
population proportion
Example: The proportion of adults in this
city with cell phones is p = .68
Ch. 9-2
Assumption-
; , ;
Hypothesis-,
Claim- , ;
Null- ,
Quo-- quo warranto -
, ,
Ch. 9-3
H0 : X 3
Ch. 9-4
Ch. 9-5
Ch. 9-6
Population
Is X 20 likely if = 50?
If not likely,
REJECT
Null Hypothesis
Copyright 2010 Pearson Education, Inc. Publishing as Prentice Hall
Suppose
the sample
mean age
is 20: X = 20
Now select a
random sample
Sample
Ch. 9-7
20
If it is unlikely that
we would get a
sample mean of
this value ...
= 50
If H0 is true
... then we
reject the null
hypothesis that
= 50.
Ch. 9-8
Level of Significance,
Ch. 9-9
Level of Significance
and the Rejection Region
Level of significance =
H0: = 3
H1: 3
H0: 3
H1: > 3
/2
Two-tail test
/2
Represents
critical value
Rejection
region is
shaded
Upper-tail test
H0: 3
H1: < 3
Lower-tail test
0
Ch. 9-10
Type I Error
Reject a true null hypothesis
Considered a serious type of error
The probability of Type I Error is
Called level of significance of the test
Set by researcher in advance
Ch. 9-11
Type II Error
Fail to reject a false null hypothesis
The probability of Type II Error is
Ch. 9-12
Key:
Outcome
(Probability)
Decision
H0 True
Do Not
Reject
H0
No Error
(1 - )
Type II Error
()
Reject
H0
Type I Error
( )
No Error
(1-)
H0 False
Ch. 9-13
, then
Ch. 9-14
when
when
when
Ch. 9-15
i.e.,
Ch. 9-16
Unknown
Ch. 9-17
Test of Hypothesis
for the Mean ( Known)
Unknown
H0 : 0
H1 : 0
(Assume the population is
normal)
Copyright 2010 Pearson Education, Inc. Publishing as Prentice Hall
n
Ch. 9-18
Decision Rule
x 0
Reject H0 if z
z
H0: = 0
H1: > 0
Alternate rule:
Reject H0 if x 0 Z / n
x
Copyright 2010 Pearson Education, Inc. Publishing as Prentice Hall
Do not reject H0
z
0 z
Reject H0
Critical
value x c
Ch. 9-19
Ch. 9-20
Ch. 9-21
H1: > 52
Ch. 9-22
Reject H0
= .10
Do not reject H0
1.28
Reject H0
x 0
Reject H0 if z
1.28
/ n
Copyright 2010 Pearson Education, Inc. Publishing as Prentice Hall
Ch. 9-23
x 0
53.1 52
z
0.88
10
n
64
Copyright 2010 Pearson Education, Inc. Publishing as Prentice Hall
Ch. 9-24
Example: Decision
(continued)
= .10
Do not reject H0
1.28
0
z = 0.88
Reject H0
Ch. 9-25
(continued)
1.28
Z = .88
Reject H0
P z
10/ 64
Ch. 9-26
One-Tail Tests
H0: 3
H1: < 3
Ch. 9-27
Upper-Tail Tests
H0: 3
H1: > 3
Do not reject H0
Reject H0
Critical value x c
Copyright 2010 Pearson Education, Inc. Publishing as Prentice Hall
Ch. 9-28
Lower-Tail Tests
H0: 3
H1: < 3
Reject H0
-z
Do not reject H0
Critical value x c
Ch. 9-29
Two-Tail Tests
H0: = 3
H1:
3
/2
/2
x
3
Reject H0
Do not reject H0
-z/2
Lower
critical value
Copyright 2010 Pearson Education, Inc. Publishing as Prentice Hall
Reject H0
+z/2
Upper
critical value
Ch. 9-30
Ch. 9-31
X 0
2.84 3
.16
2.0
0.8
.08
n
100
Ch. 9-32
Reject H0 if
z < -1.96 or
z > 1.96;
otherwise
do not
reject H0
= .05/2
Reject H0
-z = -1.96
= .05/2
Do not reject H0
Reject H0
+z = +1.96
Ch. 9-33
Reject H0
-z = -1.96
= .05/2
Do not reject H0
Reject H0
+z = +1.96
-2.0
Ch. 9-34
Example: p-Value
x = 2.84 is translated to
a z score of z = -2.0
P(z 2.0) .0228
P(z 2.0) .0228
/2 = .025
/2 = .025
.0228
.0228
p-value
= .0228 + .0228 = .0456
Copyright 2010 Pearson Education, Inc. Publishing as Prentice Hall
-1.96
-2.0
1.96
2.0
Ch. 9-35
Example: p-Value
(continued)
/2 = .025
.0228
.0228
-1.96
-2.0
Copyright 2010 Pearson Education, Inc. Publishing as Prentice Hall
/2 = .025
1.96
2.0
Ch. 9-36
Ch. 9-37
Ch. 9-38
Ch. 9-39
Ch. 9-40
Unknown
H0 : 0
H1 : 0
(Assume the population is
normal)
Copyright 2010 Pearson Education, Inc. Publishing as Prentice Hall
H0 : 0
H1 : 0
Ch. 9-42
H0: = 168
H1:
168
Ch. 9-43
Example Solution:
Two-Tail Test
H0: = 168
H1:
168
= 0.05
/2=.025
Reject H0
-t n-1,/2
-2.0639
n = 25
is unknown, so
use a t statistic
t n1
Critical Value:
t24 , .025 = 2.0639
/2=.025
Do not reject H0
Reject H0
1.46
t n-1,/2
2.0639
x
172.50 168
1.46
s
15.40
n
25
Ch. 9-44
Ch. 9-45
Ch. 9-46
Ch. 9-47
Ch. 9-48
Ch. 9-49
Proportions
(continued)
P(1 P)
p P
p
n
Ch. 9-50
The sampling
distribution of p is
Hypothesis
approximately
Tests for P
normal, so the test
statistic is a z
nP(1 P) < 5
nP(1 P) > 5
value:
p P0
P0 (1 P0 )
n
Not discussed
in this chapter
Ch. 9-51
Check:
Our approximation for P is
p = 25/500 = .05
nP(1 - P) = (500)(.05)(.95)
= 23.75 > 5
Ch. 9-52
H0: P = .08
H1: P .
08= .05
= .05
n = 500, p
Reject
.025
.025
-1.96
1.96
.05 .08
2.47
.08(1 .08)
500
Decision:
p P0
P0 (1 P0 )
n
-2.47
Copyright 2010 Pearson Education, Inc. Publishing as Prentice Hall
Reject H0 at = .05
Conclusion:
There is sufficient
evidence to reject the
companys claim of 8%
response rate.
Ch. 9-53
p-Value Solution
(continued)
Reject H0
Reject H0
/2 = .025
p-value = .0136:
/2 = .025
.0068
-1.96
2(.0068) 0.0136
1.96
Z = -2.47
Z = 2.47
Ch. 9-54
Ch. 9-55
Ch. 9-56
Ch. 9-57
Ch. 9-58
Ch. 9-59
Hypothesis Tests of
one Population Variance
Goal: Test hypotheses about the
population variance, 2
If the population is normally distributed,
2
n 1
(n 1)s
Chap 11-60
Hypothesis Tests of
one Population Variance
(continued)
2
n 1
(n 1)s
2
0
Chap 11-61
Upper-tail test:
Two-tail test:
H0: 2 02
H1: 2 < 02
H0: 2 02
H1: 2 > 02
H0: 2 = 02
H1: 2 02
n21,1
n21,
Reject H0 if
2
n 1
2
n 1,1
Reject H0 if
n21 n21,
/2
/2
n21,1 / 2
n21, / 2
Reject H0 if
or
n21 n21, / 2
n21 n21,1 / 2
Chap 11-62