LECTURE 7

Inference About
a Population:
Estimation
 Introduction
Statistical inference is the process by which we
acquire information and draw conclusions about
populations from samples.

The sampling distribution will be used to draw

inferences about the unknown population
parameters.

There are two general procedures for making

inferences:

 Estimation
 Hypotheses testing
 Concepts of Estimation
The objective of estimation is to determine the
unknown value of a population parameter
( and p) on the basis of a sample statistic.

Estimator is a statistic or function used to estimate

the unknown value of a parameter

There are two types of estimators:

• Point estimator
• Interval estimator
 Point estimator draws inference by estimating the value
of an unknown parameter using a single value.

Interval estimator draws inference by estimating the

value of an unknown parameter using a range of values.

Estimate is a numerical value calculated from the

estimator.

Point estimate is a single values that estimates the

actual value of the population parameter of interest.

Interval estimate is a range of values within which

the actual value of the population parameter may fall.
 Estimation…
The objective of estimation is to determine
the approximate value of a population
parameter on the basis of a sample statistic.
There are two types of estimators:
Point Estimator estimate the value of an
unknown parameter using a
single value or point.

Interval Estimator estimate the value of an

unknown parameter using an
interval; between lower &
upper bound
Point & Interval Estimation…
For example, suppose we want to estimate the mean summer
income of a class of business students. For n = 25 students, is
calculated to be 400 $/week.

point estimate interval estimate

An alternative statement is:

The mean income is between 380 and 420 $/week.
 Qualities of Estimators
An important consideration in choosing a sample
statistic as a point estimate of the value of a
population parameter is that the sample statistic be an
unbiased estimator. An estimator is unbiased if the
expected value of the sample statistic is equal to the
parameter it estimates.

The other two desirable qualities of unbiased

estimator are consistent - the difference between the
estimator and the parameter grows smaller as the
sample size grows larger) and relatively efficient estimator
with smaller variance.
 Population
Point Estimator
Parameter

Mean , 

Variance ,  2

Proportion, p , x is the number of successes

 Confidence Interval Estimates
Confidence interval is an interval estimate that
encloses an unknown population parameter with a
certain level of confidence.

Confidence limits are the lower and upper values

of the interval estimate.

Confidence level is (1 – ) is the probability that

the interval would include the actual value of the
population parameter if the process leading to the
interval were repeated a great many times.

Note:  is critical value

 What is Confidence Level?
Confidence Level
 How many percent you confidence that the
interval estimate will contain the unknown
population parameter
 You cannot confidence 100%
 So the percentage of confidence must less
than 100%
 What is Confidence Level?
Suppose confidence level = 95%
Also written (1 - ) = 0.95, (so  = 0.05)
A relative frequency interpretation:
 95% of all the confidence intervals that can be
constructed will contain the unknown true
parameter
 General Formula
The general formula for all confidence intervals
is:
Point Estimate ± (Critical Value)(Standard Error)
Where:
• Point Estimate is the sample statistic estimating the population
parameter of interest ()

• Critical Value is a table value based on the sampling distribution of

the point estimate and the desired confidence level ()

• Standard Error is the standard deviation of the point estimate (

 Confidence Intervals

Confidence
Intervals

Population Population
Mean Proportion

σ Known σ Unknown
 (i) Confidence Interval for μ
(σ Known)
Assumptions
 Population standard deviation σ is known
 Population is normally distributed
 If population is not normal, use large sample

Confidence interval estimate:

σ
X  Z α/2
n
where X is the point estimate
Zα/2 is the normal distribution critical value for a probability of /2 in each tail
is the standard error
σ/ n
 Finding the Critical Value, Zα/2
Z α/2  1.96
Consider a 95% confidence interval:
1  α  0.95so α  0.05
Must write ±
because there are
two tail (positive
and negative)
α α
 0.025  0.025
2 2

Z units: Zα/2 = -1.96 0 Zα/2 = 1.96

Lower Upper
X units: Confidence Point Estimate Confidence
Limit Limit
 Common Levels of Confidence
Commonly used confidence levels are 90%,
95%, and 99%
No need to
remember
Confidence
Confidence Coefficient, Zα/2 value
this, you
Level may refer
1 
80% 0.80 1.28 to Z Table
90% 0.90 1.645 Right Tail
95% 0.95 1.96
98% 0.98 2.33
99% 0.99 2.58
99.8% 0.998 3.08
99.9% 0.999 3.27
 Refer to α value

Z0.025 = 1.96

The Right Tail Z distribution -- this table is

included in the statistical table provided to you.
Let say the confidence interval is 90%
So what is the value for ?
 Example

A sample of 11 circuits from a large normal

population has a mean resistance of 2.20
ohms. We know from past testing that the
population standard deviation is 0.35 ohms.

Determine a 95% confidence interval for the

true mean resistance of the population.
 Example
A sample of 11 circuits from a large normal
population has a mean resistance of 2.20 ohms.
We know from past testing that the population
standard deviation is 0.35 ohms.
σ
X  Zα/2
Solution: n
 2.20  1.96 (0.35/ 11 )
 2.20  0.2068
1.9932  μ  2.4068

Interpretation:
We are 95% confident that the true mean resistance is between
1.9932 and 2.4068 ohms
 (ii) Confidence Interval for μ
(σ Unknown)
If the population standard deviation σ is
unknown, we can substitute the sample standard
deviation, S
This introduces extra uncertainty, since S is
variable from sample to sample
So we use the t distribution instead of the normal
distribution
 Confidence Interval for μ
(σ Unknown)
Assumptions
 Population standard deviation is unknown
 Population is normally distributed

 If population is not normal, use large sample

Use Student’s t Distribution

Confidence Interval Estimate:
S
X  tα / 2
n
(where tα/2 is the critical value of the t distribution with n -1 degrees of freedom and an area
of α/2 in each tail)
 Student’s t Distribution
The t is a family of distributions
The tα/2 value depends on degrees of freedom (d.f.)
 Number of observations that are free to vary after sample mean
has been calculated

d.f. = n - 1
Degree of
Freedom
Student’s t Table
Upper Tail Area
α Let: n = 3
df .10 .05 .025 df = n - 1 = 2
 = 0.10
1 3.078 6.314 12.706 /2 = 0.05

2 1.886 2.920 4.303

3 1.638 2.353 3.182 /2 = 0.05

The body of the table

contains t values, not 0 2.920 t
probabilities
Example of t distribution confidence interval

A random sample of n = 25 has X = 50 and

S = 8. Form a 95% confidence interval for μ

 d.f. = n – 1 = 24, so t/2  t 0.025  2.064

The confidence interval is

S 8
X  t/2  50  (2.064)
n 25
46.698 ≤ μ ≤ 53.302
𝐭 𝟎 .𝟎𝟐𝟓 , 𝟐𝟒 =𝟐 . 𝟎𝟔𝟒
 More Example: Confidence Interval for μ
(σ Unknown)
The following data represent the rental car cost (X, in $) for
12 cities during a week in October 2005.
47 41 49 38 32 48
49 41 55 50 45 45
Construct the 90% confidence interval estimate of the
population mean car rental rate.

 point estimate of 
 Þ point
estimate of 

41.8 ≤ µ ≤ 48.2
The 90% confidence interval estimate of the population mean
car rental rate is from $41.8 to $48.2
𝐭 𝟎 .𝟎𝟓 ,𝟏𝟏 =𝟏. 𝟕𝟗𝟔
 Confidence Intervals for the
Population Proportion, p
An interval estimate for the population proportion ( p )
can be calculated by adding an allowance for
uncertainty to the sample proportion ( )
(iii) Confidence Intervals for the
Population Proportion, p
Recall that the distribution of the sample proportion is
approximately normal if the sample size is large, with
standard deviation

p (1  p )
σp 
n
We will estimate this with sample data (if there is no data
for population proportion)
p̂(1  p̂)
n
 Confidence Interval Endpoints
Upper and lower confidence limits for the population
proportion are calculated with this formula:

p̂(1  p̂)
p̂  Z/2
n
where
 Zα/2 is the standard normal value for the level of confidence desired
 is the sample proportion
 n is the sample size
 Example

A random sample of 100 people shows that

25 are left-handed.
Form a 95% confidence interval for the true
proportion of left-handers
𝐙 𝟎 . 𝟎𝟐𝟓= ± 𝟏 . 𝟗𝟔
 Example
A random sample of 100 people shows that
25 are left-handed. Form a 95% confidence
interval for the true proportion of left-handers.
p̂  Z/2 p̂(1  p̂)/n
 25/100  1.96 0.25(0.75)/100
 0.25  1.96 (0.0433)
0.1651  p  0.3349

Interpretation:
We are 95% confident that the true percentage of left-handers
in the population is between 16.51% and 33.49%.
 Example …..continued
A random sample of 100 people shows that 25
are left-handed. Form a 95% confidence interval
for the true proportion of right-handers.
=
p̂  Z/2 p̂(1  p̂)/n
 0.75  1.96 0.25(0.75)/100
 0.75  1.96 (0.0433)
0.6651  p  0.8349
Interpretation:
We are 95% confident that the true percentage of left-handers
in the population is between 66.51% and 83.49%.
Determining Sample Size
Determining
Sample Size

For the For the

Mean Proportion
 Sampling Error
The required sample size can be found to obtain a
desired margin of error/bounded error (B) with a
specified level of confidence (1 - )

The margin of error is also called sampling error

 the amount of imprecision in the estimate of the
population parameter
 the amount added and subtracted to the point estimate
to form the confidence interval
 Determining Sample Size
Determining
Sample Size

For the
Mean Sampling error

σ σ
X  Zα / 2 B  Z / 2
n n
 Determining Sample Size
Determining
Sample Size

For the
Mean

σ 2
Z / 2 σ 2
B  Z / 2 Now solve
for n to get
n
n B 2
 Example: Required Sample Size
If  = 45, what sample size is needed to
estimate the mean if the sampling error is
within ± 5 with 90% confidence?

2 2 2 2
Z σ (1.645) (45)
n 2
 2
 219.19
B 5

So the required sample size is n = 220

(Always round up) to one
value greater than the
initial value.
 Determining Sample Size
Determining
Sample Size

For the
Proportion

√
2
𝑝 (1 − 𝑝) Now solve Z 𝑝 (1− 𝑝)
B=Z for n to get n= 2
n B
 Required Sample Size Example

How large a sample would be necessary to

estimate the true proportion defective in a large
population within ±3%, with 95% confidence?
(Assume a pilot sample yields = 0.12)
 Required Sample Size Example
Solution:
For 95% confidence, use Zα/2 = 1.96
B = 0.03
= 0.12

2
Z/2 pˆ (1  pˆ ) (1.96) (0.12)(1  0.12)
2
n 2
 2
 450.74
B (0.03)
So use n = 451
Exercise 1
From past experience, the population standard deviation of
rod diameters produced by a machine has been found to be
0.053 inches. For a simple random sample of 30 rods, the
average diameter is found to be 1.4 inches.

(i) Find the 95% confidence interval for the population

mean.
(ii) What sample size is necessary to have 95% confidence
that sample mean will be within 0.01 inch of the
actual population mean?
ANSWER : EXERCISE 1
From past experience, the population standard deviation of
rod diameters produced by a machine has been found to be
0.053 inches. For a simple random sample of 30 rods, the
average diameter is found to be 1.4 inches.
(i) Find the 95% confidence interval for the population
mean.

LCL= 1.381, UCL = 1.419

1.381 ≤ µ ≤ 1.419
We have 95% confidence that the population mean length
falls between 1.381 and 1.419 inches

LCL = lower confidence limit ; UCL = upper confidence limit

ANSWER EXERCISE 1

(ii) What sample size is necessary to have 95% confidence

that sample mean will be within 0.01 inch of the actual
population mean?

( ) [ ]
2 2
𝑍 𝛼/ 2 𝜎 1.96 (0.053)
𝑛= = =107.9 ≈108
𝐵 0.01
Exercise 2

In an April 2007 NBC News / Wall Street Journal poll, 1008 adults were
randomly sampled from across the United States.
In response to the question, “All in all, do you think that things in the
nation are generally headed in the right direction, or do you feel that
things are off on the wrong track?” 22% responded “headed in the right
direction”.
(i) What is the 90% confidence interval for the population proportion
who would have answered “headed in the right direction” to
the question posed?
(ii) Determine the sample size necessary to estimate the population
proportion to within 0.015 with 90% confidence if we believe that
the estimated value of the population proportion is approximately
0.30.
ANSWER EXERCISE 2

LCL = 0.199, UCL = 0.241

0.199 ≤ p ≤ 0.241

The 90% confidence interval estimate of the population

proportion who would have said “headed in the right
direction” is from 0.199 (19.9%) to 0.241 (24.1%)

** = 0.22 is the point estimate of p

 ANSWER EXERCISE 2
(ii) Determine the sample size necessary to estimate the
population proportion to within 0.015 with 90%
confidence if we believe that the estimated value of
the population proportion is approximately 0.30.

[ ]
2
1.6449 √ 0.3( 0.7)
𝑛= = 2525.3 ≈ 2526
0.015