Interval Estimation
Interval Estimation
Interval Estimation
Statistics (OA3102)
Revision: 1-12 3
Objective for Interval Estimation
Revision: 1-12 4
Why Interval Estimation?
Revision: 1-12 5
Terminology
(Unobserved) mY
y 95% confidence
interval for mY
(Unobserved) population
distribution (pdf of Y)
mY 2 Y n 7
In General
Pr qˆL q qˆU 1 a
Target Confidence
parameter coefficient
Revision: 1-12 10
Example: Constructing a
95% CI for m, known (2)
Revision: 1-12 11
Example: Constructing a
95% CI for m, known (3)
Y - mY
Pr -1.96 1.96 0.95
Y / n
Revision: 1-12 12
Example: Constructing a
95% CI for m, known (4)
Revision: 1-12 14
Example 8.4
Revision: 1-12 15
Example 8.4 (continued)
Revision: 1-12 16
Example 8.5
Revision: 1-12 17
Example 8.5 (continued)
Revision: 1-12 18
Large-Sample Confidence Intervals
Revision: 1-12 19
Example 8.6
Revision: 1-12 20
Example 8.6 (continued)
Revision: 1-12 21
One-Sided Limits
Revision: 1-12 22
Example 8.7
Revision: 1-12 23
Example 8.7 (continued)
Revision: 1-12 24
Example 8.8
Revision: 1-12 25
Example 8.8 (continued)
Revision: 1-12 26
Example 8.8 (continued)
Revision: 1-12 27
What is a Confidence Interval?
• Simulated 20 95%
confidence intervals
with samples of size
n=10 drawn from
N(40,1) distribution
• One failed to cover
the true (unknown)
parameter, which is
what is expected on
average
Revision: 1-12 29
Another CI Simulation
TO DEMO
Revision: 1-12 31
Summary: Constructing a Two-sided
Large-Sample Confidence Interval
Revision: 1-12 32
E.g., Constructing a Two-sided
Large-Sample 95% CI for m
Revision: 1-12 33
E.g., Constructing a Two-sided
Large-Sample 95% CI for p
Y
• Width of CI’s: w 2 za /2
n
Y
• Margin of error: E za /2
n
– Bigger s.d. bigger s.e. wider intervals
– Bigger sample size smaller s.e. narrower
intervals
– Higher confidence bigger z-values wider
intervals
Revision: 1-12 35
Sample Size Calculations
n
w
Revision: 1-12 36
Example
Revision: 1-12 37
Example 8.9
Revision: 1-12 38
Example 8.9 (continued)
Revision: 1-12 39
Example 8.10
Revision: 1-12 40
Example 8.10 (continued)
Revision: 1-12 41
Small-Sample Confidence
Interval for m ( Unknown)
Revision: 1-12 45
Example 8.11 (continued)
Revision: 1-12 46
Small-Sample Confidence
Interval for m1-m2
Z
Y Y m
1 2 1 m2
~ N (0,1)
1 1
n1 n2
• But if is unknown, then need to appropriately
estimate it
• To do so, first estimate the two sample means
n1 n2
1 1
Y1 Y1i Y2 Y2i
Revision: 1-12
n1 i 1 n2 i 1 48
Pooled Estimate of the Variance
i 1 1i 1 i 1 2i 2
n1 n2
( y y )2
( y y ) 2
s 2p
n1 n2 2
Average squared deviation
from different means
2
• Can also express as a weighted average of s 1
and s22 :
(n1 1) s1 (n2 1) s2
2 2
s
2
n1 n2 2
p
Revision: 2-10 49
Small-Sample Confidence
Interval for m1-m2 , continued
Z Y1 Y2 m1 m2 1 2 p
n n 2 S 2
W / 1 n1 1 n2 2 n1 n2 2
Y Y m
1 2 1 m2
~ T n 1
1 1
Sp
n1 n2
Revision: 1-12 50
Example 8.12
Revision: 1-12 52
Example 8.12 (continued)
Revision: 1-12 53
CI for the Variance
2
• Then a confidence interval for the variance is:
(n 1) S 2 ( n 1) S 2
Pr 2 2 2 1 a
a /2, n 1 1a /2, n 1
Revision: 1-12 54
Example: 95% CI for Variance
Revision: 1-12 56
Example 8.13 (continued)
Revision: 1-12 57
Why Calculate CIs for ?
Revision: 1-12 60
What We Covered in this Module
Revision: 1-12 62