10/21/2015

OPRE 6301/SYSM 6303

Quantitative Introduction to Risk and
Uncertainty in Business

10-1

Chapter Ten
Introduction to Estimation

10-2

1
 10/21/2015

Two Types of Inference

Estimation

Hypothesis Testing

10-3

Estimation
Objective:
to determine
the approximate value
of a population parameter
on the basis of
a sample statistic.

10-4

2
 10/21/2015

Two Types of Estimators

Point Estimator

Interval Estimator

10-6

Point Estimator
Draws inferences about a population by
estimating the value of an unknown parameter
using a single value or point

10-7

3
 10/21/2015

Point Estimator
Recall:
Point probabilities in continuous distributions were
essentially equal to zero.

As the sample size used to determine the point

estimator increases, we expect the point
estimator to get closer to the population
parameter.

10-9

Point Estimator

However, regardless of the sample size, a point

estimator is still just a point value.

10-10

4
 10/21/2015

Interval Estimator
Draws inferences about a population by
estimating the value of an unknown parameter
using an interval.

10-11

Interval Estimation
With an interval, we say:

With some ___% certainty, the population

parameter of interest is between some lower
bound and some upper bound.

10-12

5
 10/21/2015

Two Types of Estimators

Suppose we want to estimate the mean summer
income of a class of business students.

For n=25 students,

x  $400 / week
or
The mean income is between
$380/week and $420/week.

10-15

Qualities of Estimators
Unbiasedness

Consistency

Relative efficiency

10-16

6
 10/21/2015

Unbiased Estimator

An estimator whose expected value is

equal to the parameter.

10-17

Unbiased Estimator

The sample mean is an unbiased estimator

of the population mean

E x   

10-18

7
 10/21/2015

Unbiased Estimator

The sample median is an unbiased

estimator of the population mean

E sample median  

10-19

Consistency

An unbiased estimator is said to be

consistent if the difference between the
estimator and the parameter grows smaller
as the sample size grows larger.

10-20

8
 10/21/2015

Consistency

The sample mean is a consistent estimator

of the population mean
2
V x  
n

10-21

Consistency

The sample median is a consistent estimator

of the population mean
2
V sample median  1.57
n

10-22

9
 10/21/2015

Relative Efficiency

If there are two unbiased estimators of a

parameter, the one whose variance is
smaller is said to be relatively efficient.

10-23

Relative Efficiency
The sample mean and sample median
are both unbiased estimators of the
population mean.

However, the sample median has a greater

variance than the sample mean.

10-25

10
 10/21/2015

Relative Efficiency
So we choose the sample mean since it is
relatively efficient when compared to the
sample median.

As it turns out, the sample mean is the

“best” estimator of the population mean.

10-27

Estimating  when
 is known
Recall:

 
P  Z 2  Z  Z 2  1  

x 
Z
 n

10-29

11
 10/21/2015

Estimating  when
 is known
Substitute into the probability equation
   
P  x  Z 2    x  Z 2   1 
 n n

This equation provides us a confidence

interval estimate of 

10-33

Estimating  when
 is known
Substitute into the probability equation
   
P  x  Z 2    x  Z 2   1 
 n n


Lower Confidence Limit: x  Z 2
n

Upper Confidence Limit: x  Z 2
n
10-35

12
 10/21/2015

Estimating  when
 is known
Substitute into the probability equation
   
P  x  Z 2    x  Z 2   1 
 n n

The probability (1-) is the confidence level,

which is a measure of how frequently the
interval will include .

10-36

Example: Doll Computers

The Doll Computer Company makes its own
computers and delivers them directly to customers
who order them via Internet.

Demand during lead time is normally distributed. The

Operations manager needs to know the mean to
compute the optimum inventory level.

10-37

13
 10/21/2015

Example: Doll Computers

He observes 25 lead time periods. Use file Xm10-01

The manager would like a 95% confidence

interval estimate of the mean demand during
lead time. Assume that the standard deviation is
75 computers.

10-38

Example: Doll Computers

The estimation for the mean demand during lead
time lies between 340.76 and 399.56.

This estimator is correct 95% of the time. That also

means that 5% of the time the estimator will be
incorrect.

We often refer to the 95% figure as “19 times out

of 20,” which emphasizes the long-run aspect of
the confidence level.

10-39

14
 10/21/2015

Determining a sample size

In Chapter 5 we pointed out that sampling error is
the difference between an estimator and a
parameter.

We can also define this difference as the error of

estimation.

In this chapter this can be expressed as the

difference between 𝑋 and µ.

10-40

Determining sample size

With a little algebra we find the sample size to
estimate a mean.

2
z 
n    / 2 
 B 

Where B: the bound on the error of estimation

10-41

15
 10/21/2015

Determining sample size

The manager has decided that the estimate of
the mean demand during lead time should be
within 16 units.

10-42

16