Estimation
Confidence
Intervals
Learning Objectives
1. State What Is Estimated
2. Distinguish Point & Interval Estimates
3. Explain Interval Estimates
4. Compute Confidence Interval
Estimates for Population Mean &
Proportion
5. Compute Sample Size
Thinking Challenge
Suppose you’re
interested in the
average amount of
money that students in
this class (the
population) have on
them. How would you
find out?
Statistical Methods
Statistical
Methods
Descriptive Inferential
Statistics Statistics
Hypothesis
Estimation
Testing
Estimation Process
Population Random Sample
I am 95%
Mean confident that m
Mean, m, is
`X = 50 is between 40 &
unknown 60.
Unknown Population
Parameters Are Estimated
Estimate Population with Sample
Parameter... Statistic
Mean m `x
Proportion p p
2
s
2
Variance s
Differences m1 - m2 `x1 -`x2
Estimator and Estimate
1. The Estimator is a Random Variable
Used to Estimate a Population Parameter
Sample Mean, Sample Proportion, Sample
Median
Sample Mean X is an Estimator of Population
Mean m
2. The estimate is the numerical value of
the estimator
If X = 3 then 3 Is the Estimate of m
Properties of Mean
Unbiasedness
Mean of Sampling Distribution Equals Population
Mean
Efficiency
Sample Mean Comes Closer to Population Mean
Than Any Other Unbiased Estimator
Consistency
As Sample Size Increases, Variation of Sample Mean
from Population Mean Decreases
Unbiasedness
P(`X)
Unbiased Biased
A C
`X
mx= mx A mx C
Efficiency
Sampling
P(`X) Distribution
of Mean
B
Sampling
Distribution
A of Median
`X
mx
Consistency
Larger
P(`X) Sample
Size
B
Smaller
Sample
A Size
`X
mx
Estimation Methods
Estimation
Point Interval
Estimation Estimation
Confidence Boot- Prediction
Interval strapping Interval
Point Estimation
Provides Single Value
Based on Observations from 1 Sample
Gives No Information about How
Close Value Is to the Unknown
Population Parameter
Sample Mean`X = 3 Is Point Estimate
of Unknown Population Mean
Estimation Methods
Estimation
Point Interval
Estimation Estimation
Confidence Boot- Prediction
Interval strapping Interval
Interval Estimation
Provides Range of Values
Based on Observations from 1 Sample
Gives Information about Closeness to
Unknown Population Parameter
Stated in terms of Probability
– Knowing Exact Closeness Requires
Knowing Unknown Population Parameter
e.g., Unknown Population Mean Lies
Between 50 & 70 with 95%
Confidence
Key Elements of
Interval Estimation
A Probability That the Population Parameter Falls
Somewhere Within the Interval.
Sample Statistic
Confidence Interval
(Point Estimate)
Confidence Limit Confidence Limit
(Lower) (Upper)
Confidence Limits
for Population Mean
Parameter =
Statistic ± Error (1) m X Error
(2) Error X - m or X m
X -m Error
(3) Z
sx sx
(4) Error Zs x
(5) m X Zs x
© 1984-1994 T/Maker Co.
Many Samples Have Same
Confidence Interval
X = m ± Zs`x
sx_
`X
m-2.58s`x m-1.65s`x m m+1.65s`x m+2.58s`x
m-1.96s`x m+1.96s`x
90% Samples
95% Samples
99% Samples
Level of Confidence
Probability that the Unknown
Population Parameter Falls Within
Interval
Denoted (1 - a) %
a Is Probability That Parameter Is Not
Within Interval
Typical Values Are 99%, 95%, 90%
Intervals &
Level of Confidence
s_
Sampling x
Distribution a/2 1-a a/2
of Mean _
X
m =m
x
Intervals (1 - a) % of
Extend from Intervals
`X - Zs`X to Contain m .
`X + Zs`X a % Do Not.
Large Number of Intervals
Factors Affecting
Interval Width
Data Dispersion Intervals Extend from
Measured by s `X - Zs`X to`X + Zs`X
Sample Size
sx = s / n
Level of Confidence
(1 - a)
Affects Z
© 1984-1994 T/Maker Co.
Confidence Interval Estimates
Confidence
Intervals
Mean Proportion Variance
Finite
s Known s Unknown
Population
Confidence Interval Estimate
Mean (sX Known)
Assumptions
Population Standard Deviation Is Known
Population Is Normally Distributed
If Not Normal, Can Be Approximated by
Normal Distribution (n 30)
Confidence Interval Estimate
s s
X - Za / 2 m X Za / 2
n n
Estimation Example
Mean (sX Known)
The mean of a random sample of n = 25 is`X =
50. Set up a 95% confidence interval estimate
for mX if s = 10.
s s
X- Z m X Z
n n
10 10
50 - 196
. m 50 196
.
25 25
46.08 m 53.92
Thinking Challenge
You’re a Q/C inspector
for Gallo. The s for 2-
liter bottles is .05 liters.
A random sample of 100
bottles showed`X = 1.99
liters. What is the 90%
confidence interval
estimate of the true
mean amount in 2-liter 2 liter
bottles?
© 1984-1994 T/Maker Co.
Confidence Interval
Solution*
s s
X- Z m X Z
n n
.05 .05
. - 1645
199 . m 199
. 1645
.
100 100
1982
. m 1998
.
Confidence Interval Estimates
Confidence
Intervals
Mean Proportion Variance
Finite
sx Known sx Unknown
Population
Confidence Interval Estimate
Mean (s Unknown)
Assumptions
Population Standard Deviation Is Unknown
Population Must Be Normally Distributed
n<30 (See comment)
Use Student’s t Distribution
Confidence Interval Estimate
S S
X - t m X t
n n
Student’s t Distribution
Standard
Normal
Bell-Shaped
t (df = 13)
Symmetric
‘Fatter’ Tails t (df = 5)
Z
t
0
Student’s t Table
Assume:
a n=3
Area in Both Tails df = n - 1 = 2
a = .10
df .50 .20 .10 a/2 =.05
1 1.000 3.078 6.314
.05
2 0.817 1.886 2.920 .05
3 0.765 1.638 2.353
0 t
t Values 2.920
Degrees of Freedom (df)
Number of Observations that Are
Free to Vary After Sample Statistic
Has Been Calculated degrees of freedom
Example = n -1
= 3 -1
Sumof 3 Numbers Is 6 =2
X1 = 1 (or Any Number)
X2 = 2 (or Any Number)
X3 = 3 (Cannot Vary)
Sum = 6
Estimation Example
Mean (sX Unknown)
A random sample of n = 25 has`X = 50
& S = 8. Set up a 95% confidence
interval estimate for m.
S S
X -t m X t
n n
8 8
50 - 2.064 m 50 2.064
25 25
46.69 m 53.30
Thinking Challenge
You’re a time study analyst in
manufacturing. You’ve recorded
the following task times (min.):
3.6, 4.2, 4.0, 3.5, 3.8, 3.1.
What is the 90% confidence
interval estimate of the
population mean task time?
Confidence Interval Solution*
S S
X -t m X t
n n
X = (3.6+4.2+4.0+3.5+3.8+3.1)/6 = 3.7
S = .38987
n = 6, df = n -1 = 6 -1 = 5
Sx=S / n = 3.8987 / 6 = .1592
t.05,5 = 2.0150
3.7 - (2.015)(.1592) m 3.7 + (2.015)(.1592)
3.38 m 4.02
Computer Printout
De scriptives
St atis tic St d. Error
MINUTES Mean 3. 700 .159
90% Confidence Lower
3. 379
Int erval for Mean Bound
Upper
4. 021
Bound
5% Trimmed Mean
3. 706
Median 3. 700
Variance .152
St d. Deviation
.390
Minimum 3. 1
Maximum 4. 2
Range 1. 1
Int erquartile Range
.650
Sk ewness -.364 .845
Kurtos is -.130 1. 741
Confidence Interval Estimates
Confidence
Intervals
Mean Proportion Variance
Finite
sx Known sx Unknown
Population
Estimation for
Finite Populations
Assumptions
Sample Is Large Relative to Population
– n / N > .05
Use Finite Population Correction Factor
Confidence Interval (Mean, s Unknown)
S N-n S N-n
X - t m X t
n N -1 n N -1
Confidence Interval Estimates
Confidence
Intervals
Mean Proportion Variance
Finite
sx Known sx Unknown
Population
Confidence Interval Estimate
Proportion
Assumptions
Two Categorical Outcomes
Population Follows Binomial Distribution
Normal Approximation Can Be Used
– n·p 5 & n·(1 - p) 5
Confidence Interval Estimate
p (1 - p ) p (1 - p )
p -Z p p Z
n n
Estimation Example
Proportion
A random sample of 400 graduates
showed 32 went to grad school. Set up a
95% confidence interval estimate for p.
p (1 - p ) p (1 - p )
p - Za / 2 p p Za / 2
n n
.08 (1-.08 ) .08 (1-.08 )
.08 - 196
. p .08 196
.
400 400
.053 p .107
Thinking Challenge
You’re a production
manager for a
newspaper. You want to
find the % defective. Of
200 newspapers, 35 had
defects. What is the
90% confidence interval
estimate of the
population proportion
defective?
Confidence Interval
Solution*
n·p 5
n·(1 - p) 5
p (1 - p ) p (1 - p )
p - Za / 2 p p Za / 2
n n
.175 (.825) .175 (.825)
.175 - 1645
. p .175 1645
.
200 200
.1308 p .2192
Confidence Interval of the
Difference between Two Means
• Two independent samples
• Two large samples - both samples >= 30
• Population standard deviations are unknown
• Answer finds the interval:
u1 - u2
Confidence Interval of the
Difference between Two Means
n1 n 2
s x1 - x2
s1 s 2
2 2
where
(x - x ) z s
1 2 x1 - x2
Example 6.3, Page 283
Sample 1 Sample 2
x1 = $76 x2 = $65
s1 = $25 s2 = $22
n1 = 100 n2 = 100
n1 n2 Sample 1
s x1 - x2
2 Sample 2
s1 s
2 2 x1 = $76 x2 = $65
where s1 = $25 s2 = $22
n1 = 100 n2 = 100
( x1 - x ) z s
2 x1 - x2
(25) 2 (22) 2
sx1 )- x 2 3.33
100 100
(76 - 65) 3(3.33) 11 9.99
$1 u1 - u2 $21
Confidence Interval of the Difference
between Two Proportions
• Two independent samples
• Two large samples - both samples >= 30
• Answer finds the interval:
p1 - p2
Confidence Interval of the Difference
between Two Proportions
p - p ) z s
1 2 p1 - p 2
where
p1 q1 p 2 q 2
sp -p
1 2
n1 n2
Selecting a Sample Size
Selecting a Sample Size
The Degree of Confidence
Selected
The Maximum Allowable Error
The Population Standard
Deviation
Finding Sample Sizes
I don’t want to
X - mx Error sample too much
(1) Z or too little!
sx sx
sx
(2) Error Zs x Z
n
2
Z sx
2
(3) n 2
Error
Sample Size for Means
z s z s
2 2 2
n
E 2
E
E is the allowable error
z is the z score associated with degree of confidence
s is the population standard deviation
The marketing manager
would like to estimate the
population mean annual
usage of home heating oil
to within 50 gallons of the
true value and desires to be 95% confident of
correctly estimating the true mean. Based on a
previous study taken last year,the marketing
manager feels that the standard deviation can be
estimated as 325 gallons. What is the sample
size need to obtain these results?
Confidence = 95% z = 1.96
E = 50
s = 325
196
. ) (325)
2
z s
2 2 2
(384
. )(105,625)
n 2 2 162.31
E (50) 2500
n 163 homes need to be sampled
Sample Size for Proportions
p 1 - p) z 2
n 2
E
E is the maximum allowable error
z is the z value associated with the degree of confidence
p is the estimated proportion
A political pollister would like to
estimate the proportion of voters who
will vote for the Democratic candidate
in a presidential campaign. The
pollster would like 95% confidence
that her prediction is correct to within
.04 of the true proportion. What
sample size is needed?
Confidence = 95% Z=1.96
E = .04
p = unknown use p = .5
p(1 - P) z .5(1-.5)(196
2
. ) 2
n 2 2 600.25
E (.04)
n = 601 voters
Conclusion
Stated What Is Estimated
Distinguished Point & Interval Estimates
Explained Interval Estimates
Computed Confidence Interval Estimates
for Population Mean & Proportion
Computed Sample Size
