1

BADM 221 Statistics for Business

Unit 7
Interval Estimation
Confidence interval
 2
Introduction

Statistical Methods

Descriptive Statistics Inferential Statistics

Estimation Hypothesis Testing

Point Interval
Estimation Estimation
 3
Introduction

Estimation – A process whereby we select a random

sample from a population and use a sample statistic to
estimate a population parameter.

Point Estimate – A single number, calculated from a

set of sample data, that can be used as an estimate of the
target population parameter.

Example: Sample mean x  3 is the point estimate of the

 mean ; and
(unknown) population
p '  0.56
sample proportion is the
point estimate of the (unknown) population
proportion p .
 4
Introduction
Interval Estimate – An interval, calculated from a set
of sample data, that estimates the target parameter. Such
interval estimate is called confidence interval.
Example: The (unknown) population mean lies between 50
and 70, with 95% confidence.
     
confidence level

A confidence interval provides a range of reasonable

values for the population parameter.
 5
Introduction

Confidence Level – The likelihood, expressed as a

percentage or a probability, that a specified interval will
contain the population parameter.
95% confidence level – there is a .95 probability that a
specified interval DOES contain the population mean.
In other words, there are 5 chances out of 100 (or 1
chance out of 20) that the interval DOES NOT contain
the population mean.
99% confidence level – there is 1 chance out of 100
that the interval DOES NOT contain the population
mean.
 6
Confidence Interval for Population Mean

Case I : Popn std. dev. ( ) is known / Large sample size

The general formula for the confidence interval for the

population mean  is:
* 
xz
n

 
i.e. xz *
xz *

n n

*  
Margin of Error (ME): z Standard Error:
n n
*
Critical Value: z (Depends on the confidence level)
 7
Confidence Interval for Population Mean

Case I : Popn std. dev. ( ) is known / Large sample size

Commonly used confidence levels are 90%, 95%, and 99%.

Confidence Level Confidence z*
Coefficient
value 1
(
80% 0.80 1.28
)
90% 0.90 1.645
92% 0.92 1.75
95% 0.95 1.96
98% 0.98 2.33
99% 0.99 2.58 (2.
99.8% 0.998 3.08
99.9% 0.999 3.27
 8
Confidence Interval for Population Mean

Example:
Scores on an exam are normally distributed with a
population standard deviation of 5.6. A random sample of
40 scores on the exam has a mean of 32.
Find a 90% confidence interval for the true (population)
mean of the exam scores.
 9
Confidence Interval for Population Mean


Solutions: xz *

n
x  32   5.6 n  40 0.05
0.90 0.05

 z* 0 z*
90% CI:
5.6
32  (1.645)
40
 32  1.4565 z *  1.645
 (32  1.4565,32  1.4565)
 (30.54,33.46)  30.54    33.46
 10
Confidence Interval for Population Mean

With the same set of values, x  32,   5.6, n  40 ,

verify that:
95% CI: 30.26    33.74
98% CI: 29.94    34.06
99% CI: 29.72    34.28

Observation:
The interval is getting wider as the confidence level
increases.  Increasing the confidence level makes the
confidence interval wider.
 11
Confidence Interval for Population Mean

Now, with x  32,   5.6, CL  0.95, verify that:

n = 64: 30.63    33.37

n = 100: 30.90    33.10
n = 225: 31.27    32.73

Observation:
The interval is getting narrower as the sample size
increases.  Increasing the sample size makes the
confidence interval narrower.
 12
Confidence Interval for Population Mean

Case II : Popn std. dev. (  ) unknown

AND small sample size

If the population standard deviation  is unknown, we can

substitute the sample standard deviation, s.
This introduces extra uncertainty, since s is a variable from
sample to sample.
In this case, we cannot use the normal distribution.
Instead, we use the Student’s t distribution which
is “approximately” normal.
 13
Confidence Interval for Population Mean

The t-distribution: Degree of freedom

df = n – 1

Sample size: n = 14

Sample size: n = 6
 14
Confidence Interval for Population Mean

Case II : Popn std. dev. (  ) unknown

AND small sample size
The general formula for the confidence interval for the
population mean  is:
* s
x t
n

s * s
i.e. x t *
   x t
n n

* s s
Margin of Error (ME): t Standard Error:
n n
*
Critical Value: t (Depends on the confidence level)
 15
Confidence Interval for Population Mean

Example:
The average earnings per share (EPS) for 10 industrial
stocks randomly selected from those listed on the Dow-
Jones Industrial Average (DJIA) was found to be 1.85 with
a standard deviation of 0.395.
Calculate a 90% confidence interval for the average EPS of
all the industrials listed on the DJIA.
 16
Confidence Interval for Population Mean

s
Solutions: x t *

n 0.90
0.05 0.05
x  1.85 s  0.395 n  10
t * 0 t*
90% CI:
df  10  1  9
0.395 t *  3.25
1.85  (1.833)
10
 1.85  0.2290
 (1.85  0.2290,1.85  0.2290) t *  1.833
 (1.62,2.08)  1.62    2.08
 17
Confidence Interval for Population Mean

Use z or t ?

Population Std. Dev. known?

YES NO

 Large sample size?

xz *

n YES NO

s s
xz *
x t *

n n
 18
Confidence Interval for Population Proportion

The general formula for the confidence interval for the

population proportion p is:
p '(1  p ')
p ' z *

p '(1  p ') p '(1  p ')

i.e. p ' z  p  p ' z
* *

n n

* p '(1  p ')
Margin of Error (ME): z
n
p '(1  p ')
Standard Error:
n
 19
Confidence Interval for Population Proportion

Example:
Suppose that a market research firm is hired to estimate the
percent of adults living in a large city who have cell
phones. Five hundred randomly selected adult residents in
this city are surveyed to determine whether they have cell
phones. Of the 500 people sampled, 421 responded yes -
they own cell phones.
Using a 95% confidence level, compute a confidence
interval estimate for the true proportion of adult residents of
this city who have cell phones.
 20
Confidence Interval for Population Proportion

Solutions: p '(1  p ') 421

p ' z * p'   0.842
n 500
n  500

95% CI:
(0.842)(1  0.842)
0.842  (1.96)
500
 0.842  0.03197
 (0.842  0.03197,0.842  0.03197)
 (0.810,0.874)  0.810  p  0.874