STATISTICAL ESTIMATION OF

PARAMETERS

Copyright © 2005 Brooks/Cole, a division of Thomson Learning, Inc.

Copyright © 2005 Brooks/Cole, a division of Thomson Learning, Inc.
 Statistics
There are two branches of Statistics:
1.Descriptive Statistics, and
2.Inferential Statistics: the part of statistics that
allows researchers to generalize their findings
beyond data collected.

Statistical inference: is a procedure for making

inferences or generalizations about a larger
population from a sample of that population.

Copyright © 2005 Brooks/Cole, a division of Thomson Learning, Inc.

 Inferential Statistics
And Inferential Statistics is of two types:
1.Estimation
2.Hypothesis Testing
• Statistical Estimation procedures provide us with
the means to estimate population parameters with
desired degrees of precision.
• The objective of estimation is to determine the
approximate value of a population parameter on
the basis of a sample statistic.

Copyright © 2005 Brooks/Cole, a division of Thomson Learning, Inc.

 Estimation…

E.g., the sample mean ( ) is employed to estimate the

population mean ( ).

Copyright © 2005 Brooks/Cole, a division of Thomson Learning, Inc.

 Estimation…

There are two types of estimators:

•Point Estimators

•Interval Estimators

Copyright © 2005 Brooks/Cole, a division of Thomson Learning, Inc.

 Estimate and Estimator
Estimate:
1.the numerical value used in place of the unknown
parameter, or
2.a number computed by using the data collected
from a sample.
Estimator:
1.it is the statistical measure (the statistic or rule)
used to obtain the estimate
2.or the formula used to compute an estimate
Copyright © 2005 Brooks/Cole, a division of Thomson Learning, Inc.
 Point Estimation…
A point estimator draws inferences about a
population by estimating the value of an unknown
parameter using a single value or point.

A point estimate:
1.It is a single number calculated from sample data
and used in place of the unknown population
parameter.
2.It is also a single statistic value that is the “best
guess” for the parameter value.
Copyright © 2005 Brooks/Cole, a division of Thomson Learning, Inc.
 Interval Estimation

• Interval Estimation: an inferential statistical

procedure used to estimate population parameters
from sample data through the building of
confidence intervals.

• Confidence Interval: a range of values computed

from sample data that has a known probability of
capturing some population parameter of interest.

Copyright © 2005 Brooks/Cole, a division of Thomson Learning, Inc.

 Interval Estimation…
An interval estimator draws inferences about a population by
estimating the value of an unknown parameter using an
interval.

An interval estimate of a population parameter is a statement

of two values between which we have some confidence that
the parameter lies.

Interval estimate: An interval of numbers around the point

estimate, that has a fixed “confidence level” of containing the
parameter value. Called a confidence interval.
Copyright © 2005 Brooks/Cole, a division of Thomson Learning, Inc.
 Point & Interval Estimation…

Copyright © 2005 Brooks/Cole, a division of Thomson Learning, Inc.

 Properties of good Estimators…

• Statisticians have already determined the “best”

way to estimate a population parameter.

• A "Good" estimator is the one which provides an

estimate with the following qualities:
Unbiasedness, Consistency and Efficiency.

Copyright © 2005 Brooks/Cole, a division of Thomson Learning, Inc.

 Properties of good Estimators…
1. Unbiasedness:
• The bias of a point estimator is defined as the
difference between its expected value and the
value of the parameter being estimated. When the
estimated value shows zero bias, it is considered
to be unbiased.
• Therefore an estimator is said to be an unbiased
estimator of a given parameter when the expected
value of that estimator is equal to the parameter
being estimated.
Copyright © 2005 Brooks/Cole, a division of Thomson Learning, Inc.
 Comparing sample statistics
Sample Sample Sample
mean median mode
Week 1 76 48 42 9 27 40.4 42 None
Week 2 140 10 75 24 4 50.6 24 None
Week 3 14 87 68 94 120 76.6 87 None
Week 4 3 73 24 39 160 59.8 39 None
Week 5 52 13 4 30 13 22.4 13 13

• Sample mode, not a useful estimator.

• The sample medians (mean=41, s=28.26) are more
variable than the mean (mean=49.96, s=20.36), but we
want an estimator that yields values that are not more
variable.
Copyright © 2005 Brooks/Cole, a division of Thomson Learning, Inc.
 Sampling Dist. Of Sample Proportion
Probability distribution of the proportion of girls in a class
with 5 students. P(girl) = 0.1
x Proportion of girls Probability
p  x
n P( p)    p  P( p)
0 0.00 5
C0*(0.1)0*(0.9)5 = 0.59
1 0.20 5
C1*(0.1)1*(0.9)4 = 0.33 = 0.10 = p
2 0.40 5
C2*(0.1)2*(0.9)3 = 0.07
3 0.60 5
C3*(0.1)3*(0.9)2 = 0.01
4 0.80 5
C4*(0.1)4*(0.9)1 = 0.00
5 1.00 5
C5*(0.1)5*(0.9)0 = 0.00

2

   ( p  P( p )   2  0.018
2
 2
 
pq
 
pq n
n
Copyright © 2005 Brooks/Cole, a division of Thomson Learning, Inc.
 Egs. Of Unbiased Estimators…
• Sample mean is an unbiased estimator of the population
mean.
• Sample variance for population variance.
• Sample proportion for population proportion.

Copyright © 2005 Brooks/Cole, a division of Thomson Learning, Inc.

 Properties of good Estimators…
2. Consistency:
• Closeness of the estimator to the parameter is of
primary importance.
• Consistency tells us how close the point estimator
stays to the value of the parameter as it increases
in size.
• The point estimator requires a large sample size
for it to be more consistent and accurate.

Copyright © 2005 Brooks/Cole, a division of Thomson Learning, Inc.

 Properties of good Estimators…
2. Consistency:
• You can also check if a point estimator is
consistent by looking at its corresponding
expected value and variance.
• For the point estimator to be consistent, the
expected value should move towards the true
value of the parameter.
• Thus an unbiased estimator is said to be
consistent if increasing the sample size produces
an estimate with smaller standard error.
Copyright © 2005 Brooks/Cole, a division of Thomson Learning, Inc.
 Properties of good Estimators…

Copyright © 2005 Brooks/Cole, a division of Thomson Learning, Inc.

 Properties of good Estimators…
3. Efficiency:
• The most efficient point estimator is the
one with the smallest variance of all the
unbiased and consistent estimators.
• The variance measures the level of
dispersion from the estimate, and the
smallest variance should vary the least
from one sample to the other.

Copyright © 2005 Brooks/Cole, a division of Thomson Learning, Inc.

 Properties of good Estimators…

Copyright © 2005 Brooks/Cole, a division of Thomson Learning, Inc.

 QUESTIONS
1. A researcher would like to know the average price of a
house in a region. A random sample of 100 houses was
taken and the mean price was found to be GH¢
120,128.00, median price, GH¢ 123,025.00 and the
modal price GH¢ 119,958.00 with a standard deviation
of GH¢ 50,324. Use the data to provide an estimated
average price.
2. 829 adult Ghanaians were surveyed, and 51% of them
are opposed to the use of the juvenile-cop for issuing
traffic tickets. Using these survey results, find the best
point estimate of the proportion of all adult Ghanaians
opposed to juvenile-cop use.
Copyright © 2005 Brooks/Cole, a division of Thomson Learning, Inc.
 QUESTIONS
3. A study found the body temperatures of 106 healthy
adults. The sample mean was 98.2 degrees and the
sample standard deviation was 0.62 degrees. Find the
point estimate of the population mean of all body
temperatures.

Copyright © 2005 Brooks/Cole, a division of Thomson Learning, Inc.

 Interval Estimation
One of the limitations of simply reporting a point estimate is
the lack of information concerning the estimator’s
accuracy.

Example: If 33.2 is a point estimate of the population mean,

how good is this estimate?

Interval estimates, however, are constructed to provide

additional information about the precision of the estimate.

Copyright © 2005 Brooks/Cole, a division of Thomson Learning, Inc.

 Interval Estimation …
• An interval estimate is made by developing an upper and
a lower boundary for an interval that will hopefully
contain the population parameter.
• It would be easy to construct an interval estimate that
would definitely contain a population parameter, namely
minus infinity to positive infinity. (,)

• However, this does not give any useful information about

the location of the population parameter.
• In interval estimation, the smaller the interval for a given
amount of confidence, the better.
Copyright © 2005 Brooks/Cole, a division of Thomson Learning, Inc.
 Central Limit Theorem (CLT)

Copyright © 2005 Brooks/Cole, a division of Thomson Learning, Inc.

 Definitions
• Point estimate: a single number, calculated from a
set of data, that is the best guess for the parameter.
• Point estimator: the statistic used to produce the
point estimate.
• Interval estimate: a range of numbers around the
point estimate within which the parameter is believed
to fall.
• It is also a guess of a range of potential values for the
population parameter, based on the sample.
• When a probability is attached it is called a
confidence interval.
Copyright © 2005 Brooks/Cole, a division of Thomson Learning, Inc.
 Interval Estimate for the mean (large sample)

Copyright © 2005 Brooks/Cole, a division of Thomson Learning, Inc.

 Interval Estimate for the mean …

Copyright © 2005 Brooks/Cole, a division of Thomson Learning, Inc.

 CONFIDENCE LEVEL

Copyright © 2005 Brooks/Cole, a division of Thomson Learning, Inc.

 CONFIDENCE LEVEL
A confidence level refers to the percentage of all possible
samples that can be expected to include the true
population parameter. For example, suppose all possible
samples were selected from the same population, and a
confidence interval were computed for each sample. A
95% confidence level implies that 95% of the confidence
intervals would include the true population parameter

Copyright © 2005 Brooks/Cole, a division of Thomson Learning, Inc.

 Confidence Interval Estimator for :


upper confidence
Usually represented limit (UCL)
with a “plus/minus”
( ± ) sign

lower confidence
limit (LCL)

Copyright © 2005 Brooks/Cole, a division of Thomson Learning, Inc.

 Graphically…
…the actual location of the population mean …

…may be here… …or here… …or possibly even here…

The population mean is a fixed but unknown quantity. Its incorrect to interpret the
confidence interval estimate as a probability statement about . The interval acts as the
lower and upper limits of the interval estimate of the population mean.
Copyright © 2005 Brooks/Cole, a division of Thomson Learning, Inc.
 Four commonly used confidence levels…
Confidence Level

 cut & keep handy! 

Table 10.1
Copyright © 2005 Brooks/Cole, a division of Thomson Learning, Inc.
 Example 10.1…
A computer company samples demand during lead time over
25 time periods:
235 374 309 499 253
421 361 514 462 369
394 439 348 344 330
261 374 302 466 535
386 316 296 332 334

Its is known that the standard deviation of demand over lead

time is 75 computers. We want to estimate the mean demand
over lead time with 95% confidence in order to set inventory
levels…

Copyright © 2005 Brooks/Cole, a division of Thomson Learning, Inc.

 Example 1…
“We want to estimate the mean demand over lead time with
95% confidence in order to set inventory levels…”

IDENTIFY

•Thus, the parameter to be estimated is the population

mean:

And so our confidence interval estimator will be:

Copyright © 2005 Brooks/Cole, a division of Thomson Learning, Inc.

 Example 1… CALCULATE

In order to use our confidence interval estimator, we need the

following pieces of data:

370.16 Calculated from the data…

1.96

75
Given
n 25

therefore:

The lower and upper confidence limits are 340.76 and 399.56.

Copyright © 2005 Brooks/Cole, a division of Thomson Learning, Inc.

 Maximum Error of estimate …

Copyright © 2005 Brooks/Cole, a division of Thomson Learning, Inc.

 Interval Width…
A wide interval provides little information.
•For example, suppose we estimate with 95%
confidence that an accountant’s average starting salary
is between GH¢15,000.00 and GH¢ 100,000.00.
•Contrast this with: a 95% confidence interval estimate
of starting salaries between GH¢ 42,000.00 and GH¢
45,000.00.
•The second estimate is much narrower, providing
accounting students more precise information about
starting salaries.

Copyright © 2005 Brooks/Cole, a division of Thomson Learning, Inc.

 Interval Width…
The width of the confidence interval estimate is a function of
the confidence level, the population standard deviation, and
the sample size…

Copyright © 2005 Brooks/Cole, a division of Thomson Learning, Inc.

 Interval Width…
The width of the confidence interval estimate is a function of
the confidence level, the population standard deviation, and
the sample size…

A larger confidence level

produces a w i d e r
confidence interval:

Copyright © 2005 Brooks/Cole, a division of Thomson Learning, Inc.

 Interval Width…
The width of the confidence interval estimate is a function of
the confidence level, the population standard deviation, and
the sample size…

Larger values of (1-α)

produce w i d e r
confidence intervals

Copyright © 2005 Brooks/Cole, a division of Thomson Learning, Inc.

 Interval Width…
• The width of the confidence interval estimate is a
function of the confidence level, the population
standard deviation, and the sample size…

Increasing the sample size decreases the width of the

confidence interval while the confidence level can
remain unchanged.
Note: this also increases the cost of obtaining additional
data.

Copyright © 2005 Brooks/Cole, a division of Thomson Learning, Inc.

 Selecting the Sample Size…
• We can control the width of the interval by determining
the sample size necessary to produce narrow intervals.
• Suppose we want to estimate the mean demand “to
within 5 units”; i.e. we want the interval estimate to be:

• Since:

• It follows that

Solve for n to get requisite sample size!

Copyright © 2005 Brooks/Cole, a division of Thomson Learning, Inc.
 Selecting the Sample Size…
• Solving the equation…

• That is, to produce a 95% confidence interval estimate

of the mean (±5 units), we need to sample 865 lead
time periods (vs. the 25 data points we have
currently).

Copyright © 2005 Brooks/Cole, a division of Thomson Learning, Inc.

 Sample Size to Estimate a Mean…
• The general formula for the sample size needed to
estimate a population mean with an interval estimate of:

Requires a sample size of at least this large:

Copyright © 2005 Brooks/Cole, a division of Thomson Learning, Inc.

 Example 10.2…
• A lumber company must estimate the mean diameter
of trees to determine whether or not there is sufficient
lumber to harvest an area of forest. They need to
estimate this to within 1 inch at a confidence level of
99%. The tree diameters are normally distributed with
a standard deviation of 6 inches.
• How many trees need to be sampled?

Copyright © 2005 Brooks/Cole, a division of Thomson Learning, Inc.

 Example 10.2…
Things we know:

Confidence level = 99%, therefore =.01

We want 1 , hence W=1.

We are given that = 6.

Copyright © 2005 Brooks/Cole, a division of Thomson Learning, Inc.

 Example 10.2…
• We compute…

• That is, we will need to sample at least 239 trees to

have a 99% confidence interval of 1

Copyright © 2005 Brooks/Cole, a division of Thomson Learning, Inc.

 Example 8-1
• A publishing company has just published a new college
textbook. Before the company decides the price at which
to sell this textbook, it wants to know the average price of
all such textbooks in the market. The research department
at the company took a sample of 36 comparable textbooks
and collected information on their prices. This information
produces a mean price of GH¢ 70.50 for this sample. It is
known that the standard deviation of the prices of all such
textbooks is GH¢ 4.50.
(a) What is the point estimate of the mean price of all such
textbooks? What is the margin of error for the estimate?
(b) Construct a 90% confidence interval for the mean price of
all such college textbooks.

Copyright © 2005 Brooks/Cole, a division of Thomson Learning, Inc. 50

 Example 8-2
• According to a report by the Consumer Federation
of America, National Credit Union Foundation,
and the Credit Union National Association,
households with negative assets carried an average
of GH¢ 15,528.00 in debt in 2002. Assume that
this mean was based on a random sample of 400
households and that the standard deviation of debts
for households in this sample was GH¢ 4200.00.
Make a 99% confidence interval for the 2002 mean
debt for all such households.

Copyright © 2005 Brooks/Cole, a division of Thomson Learning, Inc.