Chapter 8 Confidence Intervals

https://lms.ectmoodle.ae

CLO5 Estimate one population parameters using point and interval

estimation techniques.
CLO9 Solve business problems using appropriate statistical software.

McGraw-Hill/Irwin Copyright © 2018 by The McGraw-Hill Companies, Inc. All rights reserved.
Confidence Intervals
8.1 z-Based Confidence Intervals for a
Population Mean: σ Known
8.2 t-Based Confidence Intervals for a
Population Mean: σ Unknown
8.3 Sample Size Determination
8.4 Confidence Intervals for a Population
Proportion
8.5 Confidence Intervals for Parameters of
Finite Populations (Optional)

8-2
LO8-1: Calculate and
interpret a z-based
confidence interval for a
population mean when
σ is known.
8.1 z-Based Confidence Intervals for a
Mean: σ Known
 Confidence interval for a population mean is
an interval constructed around the sample
mean so we are reasonable sure that it
contains the population mean
 Any confidence interval is based on a
confidence level

8-3
LO8-1

The Car Mileage Case

 Automaker conducted mileage tests on n=50
cars
 Sample mean is 31.56
◦ This is a point estimate of the population mean
 Do not know how good this estimate is
 Will use a confidence interval

8-4
LO8-1

The Car Mileage Case #2

 There were many samples of 50 cars
◦ Each would give different means
 Consider the probability distribution of all
the sample means
◦ Called the sampling distribution
x  
x  
n

8-5
LO8-1

The Car Mileage Case #3

1. Because the sampling distribution of the
sample mean is a normal distribution, we
can use the normal distribution to compute
probabilities about the sample mean
2. Saying x is within ±1.96 σx of μ is the same
as saying the interval [x ±1.96 σx]
contains μ
3. The 95 percent confidence interval is

  
x  1.96 x   x  1.96
 

 n 
8-6
LO8-1
A Confidence Interval for the
Population Mean

Figure 8.1 8-7

LO8-1

Generalizing
 In the example, we found the probability that
μ is contained in an interval of integer
multiples of σx
 More usual to specify the (integer)
probability and find the corresponding
number of σx
 The probability that the confidence interval
will not contain the population mean μ is
denoted by 

8-8
LO8-1

Generalizing Continued
 The probability that the confidence interval
will contain the population mean  is
denoted by 1 - 
◦ 1 –  is referred to as the confidence
coefficient
◦ (1 – )  100% is called the confidence level
 Usual to use two decimal point probabilities
for 1 – 
◦ Here, focus on 1 –  = 0.95 or 0.99

8-9
LO8-1

General Confidence Interval

 In general, the probability is 1 – α that the
population mean μ is contained in the interval

x  z 2 x  
  x  z 2
 

 n

 The normal point zα/2 gives a right hand tail area

under the standard normal curve equal to α/2
 The normal point -zα/2 gives a left hand tail area
under the standard normal curve equal to a/2
 The area under the standard normal curve between
zα/2 and zα/2 is 1 – α

8-10
LO8-1

General Confidence Interval Continued

 If a population has standard deviation σ

(known),
 and if the population is normal or if sample
size is large (n  30), then …
 … a (1-)100% confidence interval for 
is

    
x  z 2   x - z 2 , x  z 2 
n  n n

8-11
LO8-1

95% Confidence Level

 For a 95% confidence level, 1 –  = 0.95, so
 = 0.05, and /2 = 0.025
 Need the normal point z0.025
 The area under the standard normal curve between
z0.025 and z0.025 is 0.95
 Looking up 0.025 gives –1.96
◦ We know other side must be +1.96
 Verify by looking up 0.975

8-12
LO8-1

95% Confidence Interval

  
x  z0.025 x    x  1.96 
 n
   
  x - 1.96 , x  1.96 
 n n

8-13
LO8-1

99% Confidence Interval

 For 99% confidence, need the normal
point z0.005
◦ (1 – 0.99) / 2 = 0.005
◦ z0.005 = 2.575
 The 99% confidence interval is

  
x  z0.025 x    x  2.575 
 n
   
  x - 2.575 , x  2.575 
 n n
8-14
LO8-1
The Effect of a on Confidence Interval
Width

Figures 8.3 and 8.4 8-15

LO8-2: Describe the
properties of the t
distribution and use a t
table. 8.2 t-Based Confidence Intervals for a
Mean: σ Unknown
 If σ is unknown (which is usually the case),
we can construct a confidence interval for μ
based on the sampling distribution of
x -
t
s n

 If the population is normal, then for any

sample size n, this sampling distribution is
called the t distribution

8-16
LO8-2

The t Distribution
 The curve of the t distribution is similar to
that of the standard normal curve
 Symmetrical and bell-shaped
 The t distribution is more spread out than the
standard normal distribution
 The spread of the t is given by the number
of degrees of freedom
◦ Denoted by df
◦ For a sample of size n, there are one fewer
degrees of freedom, that is, df = n – 1

8-17
LO8-2
Degrees of Freedom and the
t-Distribution

As the number of degrees of freedom increases, the spread

of the t distribution decreases and the t curve approaches
the standard normal curve

Figures 8.6 8-18

LO8-2

The t Distribution and Degrees of Freedom

 As the sample size n increases, the degrees

of freedom also increases
 As the degrees of freedom increase, the
spread of the t curve decreases
 As the degrees of freedom increases
indefinitely, the t curve approaches the
standard normal curve
◦ If n ≥ 30, so df = n – 1 ≥ 29, the t curve is very
similar to the standard normal curve

8-19
LO8-2

t and Right Hand Tail Areas

 Use a t point denoted by t
 t is the point on the horizontal axis under
the t curve that gives a right hand tail equal
to α
 So the value of t in a particular situation
depends on the right hand tail area α and the
number of degrees of freedom
◦ df = n – 1
◦  = 1 – a , where 1 – a is the specified confidence
coefficient
8-20
LO8-2

t and Right Hand Tail Areas

Top of Table 8.3 8-21

LO8-2

Using the t Distribution Table

Part of Table 8.3 8-22

LO8-3: Calculate and
interpret a t-based
confidence interval for a
population mean when
σ is unknown.
t-Based Confidence Intervals for a Mean:
σ Unknown
 If the sampled population is normally distributed
with mean , then a (1)100% confidence interval
for  is

s
x  t 2
n

 t/2 is the t point giving a right-hand tail area of /2

under the t curve having n1 degrees of freedom

Figure 8.10 8-23

LO8-4: Determine the
appropriate sample size
when estimating a
population mean.
8.3 Sample Size Determination (z)
If σ is known, then a sample of size

2
 z 2 
n   

 B 
so that x is within B units of , with 100(1)%
confidence

8-24
LO8-4

Sample Size Determination (t)

 If σ is unknown and is estimated from s, then a
sample of size
2
 t 2 s 
n   
 B 
so that x is within B units of , with 100(1-)%
confidence
 The number of degrees of freedom for the t/2 point
is the size of the preliminary sample minus 1

8-25
LO8-5: Calculate and
interpret a large sample
confidence interval for a
population proportion. 8.4 Confidence Intervals for a Population
Proportion
 If the sample size n is large, then a (1a)100%
confidence interval for ρ is

p̂1 - p̂ 
p̂  z  2
n
 Here, n should be considered large if both
◦ n · p̂ ≥ 5
◦ n · (1 – p̂) ≥ 5

8-26
LO8-6: Determine the
appropriate sample size
when estimating a
population proportion. Determining Sample Size for
Confidence Interval for ρ
 A sample size given by the formula…
2
 z 2 
n  p1 - p  

 B 
will yield an estimate p̂, precisely within B units of
ρ, with 100(1-)% confidence

 Note that the formula requires a preliminary

estimate of p
◦ The conservative value of p=0.5 is generally used when
there is no prior information on p

8-27