Download as pdf or txt
Download as pdf or txt
You are on page 1of 24

Estimation

Estimation
• Statistical inference consists of those methods by which
one makes inferences or generalizations about a
population.
• The classical method of estimating a population parameter
-- inferences are based strictly on information obtained
from a random sample selected from the population
• The Bayesian method -- utilizes prior subjective
knowledge about the probability distribution of the
unknown parameters in conjunction with the information
provided by the sample data.
• Statistical inference may be divided into two major
areas: estimation and tests of hypotheses
Classical Methods Estimation
Unbiased estimator

( )
 = E  = 
Variance of a Point Estimator

( ,  ,  )
1 2 3
Interval Estimation
• Even the most efficient unbiased estimator is unlikely
to estimate the population parameter exactly.
• With large samples, the estimation accuracy increases -
but there is still no reason we should expect a point
estimate from a given sample to be exactly equal to the
population parameter it is supposed to estimate.
• There are many situations in which it is preferable to
determine an interval within which we would expect to
find the value of the parameter. Such an interval is called
an interval estimate.
• The interval estimate indicates, by its length, the
accuracy of the point estimate
Interval Estimation
Interpretation of Interval Estimators
Interpretation of Interval Estimators
Single Sample: Estimating the Mean

 
x − z 2    x + z 2
n n
where z 2 is the z-value leaving an area of  2 to the right
Single Sample: Estimating the Mean
Single Sample: Estimating the Mean

 
x − z 2    x + z 2
n n
 0.3   0.3 
2.6 − z0.05/2      2.6 + z0.05/2  
 36   36 
 0.3   0.3 
2.6 − (1.96 )      2.6 + (1.96 )  
 36   36 
2.50    2.70
Single Sample: Estimating the Mean
Example
The mean of 75 angle measurements is
55°27’23.9’’ with its standard deviation
(computed from the measurements) as 3.1”.
Find the 95% confidence interval for the true
mean.
Single Sample: Estimating the Mean
Solution
x = 5527 '23.9",  = 3.1'',  = 0.05, z /2 = 1.96
 
x − z 2    x + z 2
n n
 3.1"   3.1" 
5527 '23.9"− z0.05/2      5527 '23.9"+ z0.05/2  
 75   75 
 3.1"   3.1" 
5527 '23.9"− 1.96      5527 '23.9"+ 1.96  
 75   75 
5527 '23.9"− 0.7 ''    5527 '23.9"+ 0.7 ''
5527 '23.2 ''    5527 '24.6 ''
Single Sample: Estimating the Mean
2
.


z 2
n

 z 2 
2

n= 
 e 
Single Sample: Estimating the Mean
2
.

X −
Z=

n
as n → , is the standard normal distribution n( z;0,1)
Single Sample: Estimating the Mean
2
.

One-Sided Confidence Bounds


• One-sided confidence bounds are developed in the same
fashion as two-sided intervals. However, the source is a one-
sided probability statement that makes use of the Central Limit
Theorem
 X − 
P  z  = 1 − 
 n 
(
 P   X − z  )
n = 1−
&
 X − 
P  − z  = 1 − 
 n 
(
 P   X + z  )
n = 1−
Single Sample: Estimating the Mean
2
.

upper one-sided bound:


x + z  n
lower one-sided bound:
x − z  n
Single Sample: Estimating the Mean
2
.

upper 95% bound:


x + z  n
6.2 + (1.645 ) 4 25
7.516 seconds
Single Sample: Estimating the Mean
2
.

s s
x − t 2    x + t 2
n n

s s
x + t and x − t
n n
Single Sample: Estimating the Mean
2
.
Single Sample: Estimating the Mean
2
.

Example
The mean of 10 distance measurements is
16183.677m with its standard deviation
(computed from the measurements) as
0.196 m. Find the 95% confidence interval
for the true mean.
Single Sample: Estimating the Mean
2
.

Example
x = 16183.677m
s = 0.196m
t0.025 = 2.262 with v = 9 degrees of freedom
 0.196   0.196 
16183.677 − ( 2.262 )      16183.677 + ( 2.262 )  
 10   10 
16183.677 − 0.140    16183.677 + 0.140
16183.537    16183.817
Single Sample: Estimating the Mean
2
.

x = 10.0
s = 0.283
t0.025 = 2.447 with v = 6 degrees of freedom
 0.283   0.283 
10.0 − ( 2.447 )      10.0 + ( 2.447 )  
 7   7 
9.74    10.26

You might also like