Interval Estimate of a Population Mean:

s Unknown
 If an estimate of the population standard deviation s
cannot be developed prior to sampling, we use the
sample standard deviation s to estimate s .
 This is the s unknown case.
 In this case, the interval estimate for m is based on the
t distribution.
 (We’ll assume for now that the population is
normally distributed.)
t Distribution

William
William Gosset,
Gosset, writing
writing under
under the
the name
name “Student”,
“Student”,
is
is the
the founder
founder of
of the
the tt distribution.
distribution.

Gosset
Gosset was
was an
an Oxford
Oxford graduate
graduate in
in mathematics
mathematics and
and
worked
worked for
for the
the Guinness
Guinness Brewery
Brewery in
in Dublin.
Dublin.

He
He developed
developed the
the tt distribution
distribution while
while working
working on
on
small-scale
small-scale materials
materials and
and temperature
temperature experiments.
experiments.
t Distribution

The
The tt distribution
distribution is
is aa family
family of
of similar
similar probability
probability
distributions.
distributions.

A
A specific
specific tt distribution
distribution depends
depends on
on aa parameter
parameter
known
known asas the
the degrees
degrees of
of freedom.
freedom.

Degrees
Degrees of
of freedom
freedom refer
refer to
to the
the number
number of
of
independent
independent pieces
pieces of
of information
information that
that go
go into
into the
the
computation
computation ofof s.
s.
t Distribution

AA tt distribution
distribution with
with more
more degrees
degrees of
of freedom
freedom has
has
less
less dispersion.
dispersion.

As
As the
the degrees
degrees ofof freedom
freedom increases,
increases, the
the difference
difference
between
between the
the tt distribution
distribution and
and the
the standard
standard normal
normal
probability
probability distribution
distribution becomes
becomes smaller
smaller and
and
smaller.
smaller.
 t Distribution

t distribution
Standard (20 degrees
normal of freedom)
distribution

t distribution
(10 degrees
of freedom)

z, t
0
t Distribution

For
For more
more than
than 100
100 degrees
degrees ofof freedom,
freedom, the
the standard
standard
normal
normal zz value
value provides
provides aa good
good approximation
approximation to
to
the
the tt value.
value.

The
The standard
standard normal
normal zz values
values can
can be
be found
found in
in the
the
infinite degrees (()) row
infinite degrees row of
of the
the tt distribution
distribution table.
table.
t Distribution

Degrees Area in Upper Tail

of Freedom .20 .10 .05 .025 .01 .005
. . . . . . .
50 .849 1.299 1.676 2.009 2.403 2.678
60 .848 1.296 1.671 2.000 2.390 2.660
80 .846 1.292 1.664 1.990 2.374 2.639
100 .845 1.290 1.660 1.984 2.364 2.626
 .842 1.282 1.645 1.960 2.326 2.576

Standard normal
z values
Interval Estimate of a Population Mean:
s Unknown
• Interval Estimate
s
x  t /2
n

where: 1 - = the confidence coefficient

t/2 = the t value providing an area of /2
in the upper tail of a t distribution
with n - 1 degrees of freedom
s = the sample standard deviation
Interval Estimate of a Population Mean:
s Unknown
 Example: Apartment Rents
A reporter for a student newspaper is writing an
article on the cost of off-campus housing. A sample
of 16 efficiency apartments within a half-mile of
campus resulted in a sample mean of $750 per month
and a sample standard deviation of $55.
Let us provide a 95% confidence interval estimate
of the mean rent per month for the population of
efficiency apartments within a half-mile of campus.
We will assume this population to be normally
distributed.
Interval Estimate of a Population Mean:
s Unknown
At 95% confidence,  = .05, and /2 = .025.
t.025 is based on n - 1 = 16 - 1 = 15 degrees of freedom.
In the t distribution table we see that t.025 = 2.131.
Degrees Area in Upper Tail
of Freedom .20 .100 .050 .025 .010 .005
15 .866 1.341 1.753 2.131 2.602 2.947
16 .865 1.337 1.746 2.120 2.583 2.921
17 .863 1.333 1.740 2.110 2.567 2.898
18 .862 1.330 1.734 2.101 2.520 2.878
19 .861 1.328 1.729 2.093 2.539 2.861
. . . . . . .
Interval Estimate of a Population Mean:
s Unknown
 Interval Estimate
s
x  t.025 Margin
n of Error

55
750  2.131  650  29.30
16

We are 95% confident that the mean rent per month

for the population of efficiency apartments within a
half-mile of campus is between $720.70 and $779.30.
Interval Estimate of a Population Mean:
s Unknown
 Adequate Sample Size

In
In most
most applications,
applications, aa sample
sample size
size of
of nn == 30
30 is
is
adequate
adequate when
when using
using the expression x  t / 2 s n to
the expression to
develop
develop an
an interval
interval estimate
estimate of
of aa population
population mean.
mean.

If
If the
the population
population distribution
distribution is
is highly
highly skewed
skewed oror
contains
contains outliers,
outliers, aa sample
sample size
size of
of 50
50 or
or more
more is
is
recommended.
recommended.
Interval Estimate of a Population Mean:
s Unknown
 Adequate Sample Size (continued)

If
If the
the population
population is
is not
not normally
normally distributed
distributed but
but is
is
roughly
roughly symmetric,
symmetric, aa sample
sample size
size as
as small
small as
as 15
15
will
will suffice.
suffice.

If
If the
the population
population is
is believed
believed to
to be
be at
at least
least
approximately
approximately normal,
normal, aa sample
sample size
size of
of less
less than
than 15
15
can
can be
be used.
used.
Summary of Interval Estimation Procedures
for a Population Mean

Yes
Can the No
population standard
deviation s be assumed
known ?
Use the sample
standard deviation
s Known s to estimate s
Case
Use Use
 s Unknown s
x  z /2 Case x  t /2
n n
Sample Size for an Interval Estimate
of a Population Mean

Let
Let EE == the
the desired
desired margin
margin of
of error.
error.

EE is
is the
the amount
amount added
added to
to and
and subtracted
subtracted from
from the
the
point
point estimate
estimate to
to obtain
obtain an
an interval
interval estimate.
estimate.

If
If aa desired
desired margin
margin of
of error
error is
is selected
selected prior
prior to
to
sampling,
sampling, thethe sample
sample size
size necessary
necessary to
to satisfy
satisfy the
the
margin
margin of of error
error can
can be
be determined.
determined.
Sample Size for an Interval Estimate
of a Population Mean
 Margin of Error

E  z /2
n

 Necessary Sample Size

( z / 2 ) 2  2
n
E2
Sample Size for an Interval Estimate
of a Population Mean

The
The Necessary
Necessary Sample
Sample Size
Size equation
equation requires
requires aa
value
value for
for the
the population
population standard deviation ss ..
standard deviation

If ss is
If is unknown,
unknown, aa preliminary
preliminary or
or planning
planning value
value
for ss can
for can be
be used
used in
in the
the equation.
equation.

1.
1. Use
Use the
the estimate
estimate of
of the
the population
population standard
standard
deviation
deviation computed
computed in in aa previous
previous study.
study.

2.
2. Use
Use aa pilot
pilot study
study to
to select
select aa preliminary
preliminary study
study and
and
use
use the
the sample
sample standard
standard deviation
deviation from
from the
the study.
study.

3.
3. Use
Use judgment
judgment or
or aa “best
“best guess”
guess” for
for the
the value of ss ..
value of
Sample Size for an Interval Estimate
of a Population Mean
 Example: Discount Sounds
Recall that Discount Sounds is evaluating a
potential location for a new retail outlet, based in
part, on the mean annual income of the individuals in
the marketing area of the new location.
Suppose that Discount Sounds’ management team
wants an estimate of the population mean such that
there is a .95 probability that the sampling error is
$500 or less.
How large a sample size is needed to meet the
required precision?
Sample Size for an Interval Estimate
of a Population Mean

z /2  500
n

At 95% confidence, z.025 = 1.96. Recall that = 4,500.

(1.96)2 (4, 500)2
n 2
 311.17  312
(500)

A sample of size 312 is needed to reach a desired

precision of + $500 at 95% confidence.
Interval Estimate
of a Population Proportion
The
The general
general form
form of
of an
an interval
interval estimate
estimate of
of aa
population
population proportion
proportion is
is
p  Margin of Error
Interval Estimate
of a Population Proportion

The
The sampling
sampling distribution of p plays
distribution of plays aa key
key role
role in
in
computing
computing the
the margin
margin ofof error
error for
for this
this interval
interval
estimate.
estimate.

The
The sampling
sampling distribution of p can
distribution of can be
be approximated
approximated
by
by aa normal
normal distribution
distribution whenever
whenever np
np >> 55 and
and
n(1
n(1 –– p)
p) >> 5.
5.
Interval Estimate
of a Population Proportion
 Normal Approximation of Sampling Distribution of p

Sampling p(1  p)
distribution p 
n
of p

/2 1 -  of all /2

p values
p
p
z /2 p z /2 p
 Interval Estimate
of a Population Proportion

• Interval Estimate

p (1  p )
p  z / 2
n

where: 1 - is the confidence coefficient

z/2 is the z value providing an area of
/2 in the upper tail of the standard
normal probability distribution
is thep sample proportion
Interval Estimate
of a Population Proportion
 Example: Political Science, Inc.
Political Science, Inc. (PSI) specializes in voter polls
and surveys designed to keep political office seekers
informed of their position in a race.
Using telephone surveys, PSI interviewers ask
registered voters who they would vote for if the
election were held that day.
Interval Estimate
of a Population Proportion
 Example: Political Science, Inc.
In a current election campaign, PSI has just found
that 220 registered voters, out of 500 contacted, favor
a particular candidate. PSI wants to develop a 95%
confidence interval estimate for the proportion of the
population of registered voters that favor the
candidate.
Interval Estimate
of a Population Proportion

p (1  p )
p  z / 2
n
where: n = 500, p= 220/500 = .44, z/2 = 1.96

.44(1  .44)
.44  1.96 = .44 + .0435
500

PSI is 95% confident that the proportion of all voters

that favor the candidate is between .3965 and .4835.
Sample Size for an Interval Estimate
of a Population Proportion
 Margin of Error

p (1  p )
E  z / 2
n

Solving for the necessary sample size, we get

( z / 2 ) 2 p (1  p )
n
E2
However,p will not be known until after we have selected the
sample. We will use the planning value
p* for .p
Sample Size for an Interval Estimate
of a Population Proportion
 Necessary Sample Size

( z / 2 ) 2 p* (1  p* )
n
E2

The planning value p* can be chosen by:

1. Using the sample proportion from a previous
sample of the same or similar units, or
2. Selecting a preliminary sample and using the
sample proportion from this sample.
3. Use judgment or a “best guess” for a p* value.
4. Otherwise, use .50 as the p* value.
 Sample Size for an Interval Estimate
of a Population Proportion
 Example: Political Science, Inc.
Suppose that PSI would like a .99 probability that
the sample proportion is within + .03 of the
population proportion.
How large a sample size is needed to meet the
required precision? (A previous sample of similar
units yielded .44 for the sample proportion.)
Sample Size for an Interval Estimate
of a Population Proportion
p(1  p )
z /2  .03
n

At 99% confidence, z.005 = 2.576. Recall that p = .44.

( z /2 )2 p(1  p) (2.576)2 (.44)(.56)
n   1817
E2 (.03) 2

A sample of size 1817 is needed to reach a desired

precision of + .03 at 99% confidence.
Sample Size for an Interval Estimate
of a Population Proportion

Note: We used .44 as the best estimate of p in the

preceding expression. If no information is available
about p, then .5 is often assumed because it provides
the highest possible sample size. If we had used
p = .5, the recommended n would have been 1843.