Académique Documents
Professionnel Documents
Culture Documents
Hypothesis
Tests for
Known
Unknown
Large
Samples
Small
Samples
rudisalam@stis.ac.id -
z
n
Known
Unknown
Large
Samples
Small
Samples
rudisalam@stis.ac.id -
tn1snzxn
Calculating the Test Statistic
(continued)
Hypothesis
Tests for
Known
Unknown
sometimes
approximated
using a z:
Large
Samples
Small
Samples
rudisalam@stis.ac.id -
tn1sn
(continued)
Hypothesis
Tests for
Known
Unknown
Large
Samples
Small
Samples
rudisalam@stis.ac.id -
3.
4.
5.
6.
(continued)
Reject H0
-z= -1.645
Do not reject
H0
rudisalam@stis.ac.id -
.z
x
2
8
4
.
1
6
2
.
0
0
0
8
n1
Hypothesis Testing Example
rudisalam@stis.ac.id -
(continued)
-1.645
Do not reject
H0
-2.0
(continued)
= .05
x
Reject H0
2.868
2.84
4
Now
expresse
d in x,
not z
units
Do not reject
H0
0.8
x z
3 1.645
2.8684
n
100
rudisalam@stis.ac.id -
x
Convert Sample Statistic (e.g.
) to
Test Statistic ( Z or t statistic )
(continued)
p-value example
P( x 2.84 | 3.0)
2.84 3.0
P z
0.8
100
= .05
p-value
=.0228
x
2.868
2.84
4
rudisalam@stis.ac.id -
p-value example
(continued)
= .05
Here:
p-value = .0228
= .05
p-value
=.0228
2.868
4
2.8
4
rudisalam@stis.ac.id -
HA: > 52
month
Reject H0
= .
10
Do not reject
H0
0
z=1.2
8
Reject H0
Reject H0 if z >
1.28
rudisalam@stis.ac.id -
Review:
Finding Critical Value - One
Tail
What is z given =
0.10?
.90
.10
= .
.50 .40
10
0 1.28
Standard Normal
Distribution Table
(Portion)
.07
.08
.09
Critical
Value
= 1.28
rudisalam@stis.ac.id -
5
3
.
1
5
2
z
0
.
8
0
n64
Example: Test Statistic
(continued)
(=10
rudisalam@stis.ac.id -
Example: Decision
(continued)
= .
10
Do not reject
H0
0
1.28
Reject H0
z = .88
p -Value Solution
(continued)
p-value = .
1894
Reject H0
= .10
0
Do not reject
H0
1.28
z=.
88
Reject H0
P( x 53.1 | 52.0)
53.1 52.0
P z
10
64
H0: =
168 HA:
168
rudisalam@stis.ac.id -
1
7
2
.
5
0
1
6
8
tn1
1
.
4
6
s
4
n
/2=.02
5
/2=.02
5
Reject H0
-t/2
-2.0639
Do not reject
H0
0
Reject H0
t/2
1.4
6
2.0639
rudisalam@stis.ac.id -
rudisalam@stis.ac.id -
Proporsi
dinyatakan dengan p
(continued)
n
sample size
p
p
p
Distribusi
sampling dari p
adalah normal,
sehingga
statistic ujinya
adalah z :
p p
p(1 p )
n
Hypothesis
Tests for p
np 5
and
n(1-p) 5
np < 5
or
n(1-p) < 5
Not
discussed in
this chapter
Check:
n p = (500)(.08)
=40
n(1-p) = (500)(.92)
=460
rudisalam@stis.ac.id -
H 0: p = .
08 HA: p
.08
= .05
n = 500, p = .05
Critical Values:
1.96
Rejec
t
Rejec
t
.
025
-2.47
.05 .08
2.47
.08(1 .08)
500
Decision:
.
025
-1.96 0
pp
p(1 p)
n
1.96
Reject H0 at = .05
Conclusion:
There is sufficient
evidence to reject
the companys claim
of 8% response rate.
rudisalam@stis.ac.id -
p -Value Solution
(continued)
Reject
H0
/2 = .
025
Reject H0
/2 = .
025
.
0068
.
0068
-1.96
z=
-2.47
p-value = .
0136:
1.96
z=
2.47
Soal
Sebuah uang logam dilantun 20 kali dan
menghasilkan 5 muka. Apakah dari sini
cukup ada alasan untuk menolak hipotesis
bahwa uang tadi setangkup dan meyakini
tandingannya bahwa muka muncul kurang
dari 50%? Sebutkan p-value nya.
Chapter Summary
Terima Kasih
rudisalam@stis.ac.id -