SESSION-4

CONFIDENCE INTERVAL
ESTIMATION
 CONFIDENCE INTERVAL
ESTIMATION
 Estimators and Their Properties

 Confidence Interval for the Population Mean µ

When the Population Standard Deviation ơ is
Known

 Confidence Intervals for µ When ơ is Unknown -

The t Distribution

 Large-Sample Confidence Intervals for the

Population Proportion P

 Sample Size Determination

 LEARNING OBJECTIVES
After studying this module you should be able to:
 Explain why sample statistics are good estimators of
population parameters

 Judge one estimator as better than another based on

desirable properties of estimators

 Explain confidence intervals

 Compute confidence intervals for population means

 Compute confidence intervals for population

proportions

 Compute minimum sample sizes needed for an

estimation
Fuel Usage of “Ultra-Green” Cars
 A car manufacturer advertises that its new “ultra-
green” car obtains an average of 100 mpg and,
based on its fuel emissions, has earned an A+
rating from the Environmental Protection Agency.

 Pinnacle Research, an independent consumer

advocacy firm, obtains a sample of 25 cars for
testing purposes.

 Each car is driven the same distance in identical

conditions in order to obtain the car’s mpg.
Fuel Usage of “Ultra-Green” Cars
 The mpg for each “Ultra-Green” car is given below.

 Need to use the data in this sample to:

 Estimate with 90% confidence
 The mean mpg of all ultra-green cars.
 The proportion of all ultra-green cars that
obtain over 100 mpg.
 Determine the sample size needed to achieve a
specified level of precision in the mean and
proportion estimates.
 The Literary Digest Poll (1936)

Unbiased,
Unbiased representative sample
Sample drawn at random from
the entire population.
Democrats Republicans
Population

People who have Biased Biased, unrepresentative

phones and/or cars
and/or are Digest Sample sample drawn from
readers.
people who have cars
Democrats Republicansand/or telephones
Population and/or read the Digest.
Sample Statistics as Estimators of
Population Parameters
 A sample statistic is A population
a numerical measure parameter is a
of a summary numerical measure of a
characteristic of a summary characteristic
sample. of a population.
• An estimator of a population parameter is a sample
statistic used to estimate or predict the population
parameter.
• An estimate of a parameter is a particular numerical
value of a sample statistic obtained through sampling.
• A point estimate is a single value used as an
estimate of a population parameter.
Estimators and Their Properties
An estimator of a population parameter is a sample
statistic used to estimate the parameter. The most
commonly-used estimator of the:
Population Parameter Sample Statistic
Mean (µ) is the Mean (X)
Variance (ơ2) is the Variance (S2)
Standard Deviation (ơ) is the S.D (S)
Proportion (P) is the Proportion (p)

Desirable properties of estimators include:

• Unbiasedness
• Efficiency
• Consistency
• Sufficiency
Sufficiency & Consistency
An estimator is sufficient if it contains all the
information in data about the parameter it estimates.
An estimator is consistent if its probability of
being close to the parameter it estimates
increases as the sample size increases.

Consistency

n = 10 n = 100
 ESTIMATES – CONSISTENT
 A statistic t is a consistent estimate of the population
parameter θ,
if E(t) ► θ and V(t) ► 0 as n ► ∞.

 Several consistent estimator may exist for the same

parameter

 E.g.
X is a consistent estimator of µ: V(X)= σ2/n

► as n grows larger, the variance of X grows smaller.

• Sample median is a consistent estimator of µ :

V(Sample median) = 1.57σ2/n ► as n grows larger,
the variance of the sample median grows smaller.
Point Estimators and Their Properties
 Consistent Estimator-The distribution of a
consistent estimator X for various sample sizes.
 Unbiasedness
•An estimator is unbiased if its expected value is
equal to the population parameter it estimates.

•E.g., E(X)=µ ► sample mean is an unbiased

estimator of the population mean.
• Unbiasedness is an average or long-run property.
• Mean of any single sample will probably not
equal the population mean, but the average of the
means of repeated independent samples from a
population will equal the population mean.

Any systematic deviation of the estimator from the

population parameter of interest is called a bias.
Unbiased and Biased Estimators

{
Bias

An unbiased estimator A biased estimator is

is on target on average. off target on average.
Point Estimators and Their Properties
 Unbiased Estimators
 The distributions of unbiased (U1) and biased
(U2) estimators.
 ESTIMATES – UNBIASED
 A statistic is an unbiased estimate of population
parameter θ if E (t) = θ
 If E (t) ≠ θ ► biased estimator
 Bias (of a statistic in estimating θ ) = E (t) – θ

 Sample variance s2 = ∑(Xi-X)2/n is a biased

estimator of the population variance ơ2 because
E(s2) =( (n-1)/n) ơ2 ≠ ơ2

 An unbiased estimator of population variance ơ2

S2 = ∑(Xi – X)2/(n-1) because E(S2) = ơ2

 s2 is the variance of the sample observations,

but S2 is the ‘unbiased estimator’ of the variance ơ2
in the population
 Efficiency
An estimator is efficient if it has a relatively small
variance (and standard deviation).

An efficient estimator An inefficient estimator is,

is, on average, closer on average, farther from
to the parameter being the parameter being
estimated.. estimated.
Point Estimators and Their Properties
 Efficient Estimators
 The distributions of efficient (V1) and less
efficient (V2) estimators.
 Estimators
 For a normally distributed population, both sample
mean and sample median are consistent & unbiased
estimators of population mean μ.

 Sample mean is more efficient than sample median.

 Variance of sample median happens to be 1.57

times as large as variance of sample mean.

 Sample mean is a sufficient estimator (in computing

it, the entire data set is used). Sample median is not
sufficient (it is the point in the middle of the data
set, regardless of exact magnitudes of all other data
elements).

 Sample mean is the best estimator of the

population mean because it is consistent ,
unbiased ,efficient & sufficient estimator.
Properties of the Sample Variance
The sample variance (the sum of the squared
deviations from the sample mean divided by (n-1)) is
consistent & an unbiased estimator of the
population variance. In contrast, the average
squared deviation from the sample mean is a
biased (though consistent) estimator of the
population variance.


E (S ) = E 
2  ( x - x ) 2

÷ =s2
 (n - 1) 

  ( x - x )2 
E ÷<s
2

 n 
 Example: St. Andrew’s College
 St. Andrew’s College received 900 applications from
prospective students. The application form contains a
variety of information including the individual’s
Scholastic Aptitude Test (SAT) score and whether or not
the individual desires on-campus housing.
 At a meeting in a few hours, the Director of Admissions
would like to announce the average SAT score and the
proportion of applicants that want to live on campus, for
the population of 900 applicants.
 However, the necessary data on the applicants have not
yet been entered in the college’s computerized database.
 So, the Director decides to estimate the values of the
population parameters of interest based on sample
statistics. The sample of 30 applicants is`selected using
computer-generated random numbers
 Example: St. Andrew’s College
 x as Point Estimator of µ

x=  x
=
50, 520
i
= 1684
30 30
 S as Point Estimator of Ơ

s= (x - x )
i
2

=
210,512
= 85.2
29 29
 p as Point Estimator of P
p=20/30 =0.67
Note: Different random numbers would have identified a
different sample which would have resulted in different point
estimates.
 Estimators-Concepts
 1) Suppose that you have an estimator with a relatively
large bias. The estimator is consistent and efficient,
however. If you had a generous budget for your sampling
survey , would you use this estimator?

 2) Suppose that you have 2 biased estimators of the

population parameter. Estimator A has a bias equal to 1/n
(that is the mean of the estimator is 1/n unit away of the
parameter it estimates), where n is the sample size used.
Estimator B has a bias equal to 0.01 (the mean of the
estimator is 0.01 unit away from the parameter of
interest).Under what conditions is estimator A better than
B?

 3) Suppose that you have two statistics A & B as possible

estimators of the same population parameter. Estimator A is
unbiased, but has a large variance . Estimator B has a small
bias, but has only 1/100th the variance of estimator A. If
you had a generous budget for your sampling survey ,
which estimator is better for you? Explain.
 Estimators-Concepts
 4)A statistic A is a sufficient estimator of a
population parameter. Why should you use
it as a possible estimate? Is there any
reason of not using it?

 5) Suppose that in a sampling survey to

estimate the population variance , the
biased estimator is used instead of unbiased
one. The sample size used was n=100 &
the estimate obtained was 1287. Can you
find the value of the unbiased estimate of
the population variance?