© 2002 thomson / south-western slide 8-1 chapter 8 estimation with single samples
TRANSCRIPT
© 2002 Thomson / South-Western Slide 8-1
Chapter 8
Estimation with Single
Samples
© 2002 Thomson / South-Western Slide 8-2
Learning ObjectivesLearning Objectives• Know the difference between point and
interval estimation.• Estimate a population mean from a sample
mean for large sample sizes.• Estimate a population mean from a sample
mean for small sample sizes.• Estimate a population proportion from a
sample proportion.• Estimate the minimum sample size necessary
to achieve given statistical goals.
© 2002 Thomson / South-Western Slide 8-3
Statistical EstimationStatistical Estimation
• Point estimate -- the single value of a statistic calculated from a sample
• Interval Estimate -- a range of values calculated from a sample statistic(s) and standardized statistics, such as the Z. – Selection of the standardized statistic is
determined by the sampling distribution.– Selection of critical values of the
standardized statistic is determined by the desired level of confidence.
© 2002 Thomson / South-Western Slide 8-4
Confidence Interval to Estimate when n is Large
Confidence Interval to Estimate when n is Large
• Point estimate
• Interval Estimate
XX
n
X Zn
or
X Zn
X Zn
© 2002 Thomson / South-Western Slide 8-5
Distribution of Sample Meansfor (1-)% Confidence
Distribution of Sample Meansfor (1-)% Confidence
X
Z0
2Z
2Z
2
2
© 2002 Thomson / South-Western Slide 8-6
Z Scores for Confidence Intervals in Relation to
Z Scores for Confidence Intervals in Relation to
X
Z0
2Z
2Z
2
2
.52
.52
© 2002 Thomson / South-Western Slide 8-7
Distribution of Sample Meansfor (1-)% Confidence
Distribution of Sample Meansfor (1-)% Confidence
X
Z0
2Z
2Z
2
2 1
2 1
2
© 2002 Thomson / South-Western Slide 8-8
Probability Interpretation of the Level of ConfidenceProbability Interpretation of the Level of Confidence
2 2
Pr ob[ ] 1X Xn nZ Z
© 2002 Thomson / South-Western Slide 8-9
Distribution of Sample Means for 95% Confidence
Distribution of Sample Means for 95% Confidence
.4750 .4750
X
95%.025.025
Z1.96-1.96 0
© 2002 Thomson / South-Western Slide 8-10
Example: 95% Confidence Interval for
Example: 95% Confidence Interval for
X and n 4 26 11 60. , . , .
X Zn
X Zn
4 26 19611
604 26 196
11
604 26 0 28 4 26 0 28
3 98 4 54
. ..
. ..
. . . .
. .
© 2002 Thomson / South-Western Slide 8-11
95% Confidence Intervals for 95% Confidence Intervals for
X
95%
XX
X
X
X
X
© 2002 Thomson / South-Western Slide 8-12
95% Confidence Intervals for 95% Confidence Intervals for
X
95%
XX
X
X
X
X
Is our interval,
3.98 4.54, in the
red?
© 2002 Thomson / South-Western Slide 8-13
Demonstration Problem 8.1Demonstration Problem 8.1
X Zn
X Zn
10 455 16457 7
4410 455 1645
7 7
4410 455 191 10 455 191
8 545 12 365
. ..
. ..
. . . .
. .
X and n
Z
10 455 7 7 44
90% 1645
. , . , .
.
confidence
Pr [ . . ] .ob 8545 12 365 0 90
© 2002 Thomson / South-Western Slide 8-14
Demonstration Problem 8.2Demonstration Problem 8.2
1 1
8 800 50 8 800 5034.3 2.33 34.3 2.33
800 1 800 150 5034.3 2.55 34.3 2.55
31.75 36.85
N n N nX Z X Z
N Nn n
X N and n
Z
34 3 8 800 50
98% 2 33
. , , .
.
=
confidence
© 2002 Thomson / South-Western Slide 8-15
Confidence Interval to Estimate when n is Large and is UnknownConfidence Interval to Estimate when n is Large and is Unknown
X ZS
nor
X ZS
nX Z
S
n
2
2 2
© 2002 Thomson / South-Western Slide 8-16
Z Values for Some of the More Common Levels of ConfidenceZ Values for Some of the More Common Levels of Confidence
90%
95%
98%
99%
Confidence Level Z Value
1.645
1.96
2.33
2.575
© 2002 Thomson / South-Western Slide 8-17
Estimating the Mean of a Normal Population: Small n and Unknown
Estimating the Mean of a Normal Population: Small n and Unknown
• The population has a normal distribution.• The value of the population standard
deviation is unknown.• The sample size is small, n < 30.• Z distribution is not appropriate for these
conditions• t distribution is appropriate
© 2002 Thomson / South-Western Slide 8-18
The t DistributionThe t Distribution
• A family of distributions -- a unique distribution for each value of its parameter, degrees of freedom (d.f.)
• Symmetric, Unimodal, Mean = 0, Flatter than a Z
• t formulatXSn
© 2002 Thomson / South-Western Slide 8-19
Comparison of Selected t Distributions to the Standard Normal
Comparison of Selected t Distributions to the Standard Normal
-3 -2 -1 0 1 2 3
Standard Normal
t (d.f. = 25)
t (d.f. = 5)
t (d.f. = 1)
© 2002 Thomson / South-Western Slide 8-20
Table of Critical Values of tTable of Critical Values of t
df t0.100 t0.050 t0.025 t0.010 t0.0051 3.078 6.314 12.706 31.821 63.6562 1.886 2.920 4.303 6.965 9.9253 1.638 2.353 3.182 4.541 5.8414 1.533 2.132 2.776 3.747 4.6045 1.476 2.015 2.571 3.365 4.032
23 1.319 1.714 2.069 2.500 2.80724 1.318 1.711 2.064 2.492 2.79725 1.316 1.708 2.060 2.485 2.787
29 1.311 1.699 2.045 2.462 2.75630 1.310 1.697 2.042 2.457 2.750
40 1.303 1.684 2.021 2.423 2.70460 1.296 1.671 2.000 2.390 2.660
120 1.289 1.658 1.980 2.358 2.6171.282 1.645 1.960 2.327 2.576
t
© 2002 Thomson / South-Western Slide 8-21
Confidence Intervals for of a Normal Population: Small n and Unknown
Confidence Intervals for of a Normal Population: Small n and Unknown
X tS
nor
X tS
nX t
S
ndf n
1
© 2002 Thomson / South-Western Slide 8-22
Solution for Demonstration Problem 8.3
X tS
nX t
S
n
2 14 3 012129
142 14 3 012
129
142 14 104 2 14 104
110 318
. ..
. ..
. . . .
. .
X S n df n
t
214 129 14 1 13
2
1 99
20 005
3012005 13
. , . , ,
..
.. ,
© 2002 Thomson / South-Western Slide 8-23
Solution for Demonstration Problem 8.3Solution for Demonstration Problem 8.3
X tS
nX t
S
n
214 3012129
14214 3012
129
14214 104 214 104
110 318
. ..
. ..
. . . .
. .
Pr [ . . ] .ob 110 318 0 99
© 2002 Thomson / South-Western Slide 8-24
Confidence Interval to Estimate the Population Proportion
Confidence Interval to Estimate the Population Proportion
:
ppq
nP p
pq
nwhere
p
q p
P
n
Z Z 2 2
1
= sample proportion
= -
= population proportion
= sample size
© 2002 Thomson / South-Western Slide 8-25
Solution for Demonstration Problem 8.5Solution for Demonstration Problem 8.5
. .( . )( . )
. .( . )( . )
. . . .
. .
p Zpq
nP p Z
pq
n
P
P
P
016 1645016 0 84
212016 1645
016 0 84
212016 0 04 016 0 04
012 0 20
n X pX
nq p
Confidence Z
212 3434
212016
1 1 016 0 84
90% 1645
, , .
. .
.
= -
Pr [ . . ] .ob P012 0 20 0 90
© 2002 Thomson / South-Western Slide 8-26
Determining Sample Size when Estimating
Determining Sample Size when Estimating
• Z formula
• Error of Estimation (tolerable error)
• Estimated Sample Size
• Estimated
ZX
n
E X
nZ
EZ
E
2
2 2
2
2
2
1
4range
© 2002 Thomson / South-Western Slide 8-27
Example: Sample Size when Estimating
nZ
E
2
2 2
2
2 2
2
1645 41
4330 44
( . ) ( )
. or
E
Z
1 4
90% 1645
,
.
confidence
© 2002 Thomson / South-Western Slide 8-28
Solution for Demonstration Problem 8.6
n ZE
2 2
2
2 2
2
196 6252
37 52 38
( . ) ( . )
. or
E range
Z
estimated range
2 25
95% 196
1
4
1
425 6 25
,
.
: .
confidence
© 2002 Thomson / South-Western Slide 8-29
Determining Sample Size when Estimating P
Determining Sample Size when Estimating P
• Z formula
• Error of Estimation (tolerable error)
• Estimated Sample Size
Zp P
P Qn
E p P
nPQZE
2
2
© 2002 Thomson / South-Western Slide 8-30
Solution for Demonstration Problem 8.7
nPQ
or
ZE
2
2
2
2
2 33003
0 40 0 60
1 447 7 1 448
( . ).
. .
, . ,
E
Confidence Z
estimated P
Q P
0 03
98% 2 33
0 40
1 0 60
.
.
.
.
© 2002 Thomson / South-Western Slide 8-31
Determining Sample Size when Estimating P with No Prior Information
P
n
0
50
100
150
200
250
300
350
400
0 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9 1
Z = 1.96E = 0.05
nZE
2
2
14
P
0.5
0.4
0.3
0.2
0.1
PQ
0.25
0.24
0.21
0.16
0.09
© 2002 Thomson / South-Western Slide 8-32
Solution for Demonstration Problem 8.8
nPQ
or
ZE
2
2
2
2
164505
0 50 0 50
270 6 271
( . ).
. .
.
E
Confidence Z
with no prior of P use P
Q P
0 05
90% 1645
050
1 050
.
.
, .
.
estimate