CHAPTER 9: ESTIMATING

THE VALUE OF A
PARAMETER USING
CONFIDENCE INTERVALS

1 By: Wandi Ding

 9.1 WHEN THE POPULATION STANDARD
DEVIATION KNOWN
1. Point estimate: is the value of a statistic that estimates the value of
a parameter. For example, the sample mean
of the population mean,  .
x is a point estimate

Suppose: we want to estimate the average weight for all students in

MTSU for this semester, we could take a random sample of 100
students and find the average weight of these students, say, 130
pounds, this kind of estimate is called a point estimate. Often,
there is another question to be asked, it is, how good is a point
estimate? There is no way of knowing how close a particular point
estimate is to the population mean if the population is large. For
this reason, statisticians prefer another type of estimate, called
interval estimate.
2. Interval estimate: an interval for unknown parameter is an interval
or a range of values used to estimate the parameter with the
specific confidence level of estimate. It is also called confidence
interval. 2
 9.1 WHEN THE POPULATION STANDARD
DEVIATION KNOWN
To make our interval estimate more reasonable and confident, we
usually use a degree of confidence to describe interval estimate, like
95%, 98%, 99%...
3. The level of confidence: represents the expected proportion of
intervals that will contain the parameter if a large number of
different samples is obtained. The level of confidence is denoted (1-
α)*100%. For example, a 95% level of confidence (α=0.05) implies
that if 100 different confidence intervals are constructed, each based
on a different sample from the same population, then we will expect
95 of the intervals to include the parameter and 5 to not include the
parameter.
4. Formula for the confidence interval of the population mean for a
specific α, where  is known and population is normally
distribution or sample size n≥30
 
x  z ( )    x  z ( ) 3
2 n 2 n
 9.1 WHEN THE POPULATION STANDARD
DEVIATION KNOWN
Ex: for 95% confidence interval for a population mean:
α=1-95%=5%; α/2=0.05/2=0.025,
z  z0.025  1.96 (Based on the standard normal table)
2

α/2 α/2

-1.96 0 1.96
4
 9.1 WHEN THE POPULATION STANDARD
DEVIATION KNOWN
Confidence interval estimates for the population mean can be
written in this form, too.
point estimate margin of error

z ( )
2 n =E is margin of error, also called maximum error of
estimate. There are three factors which affect the margin of
error.
1) level of confidence . Note: α=1-level of confidence.
2) sample size, n.
3) standard deviation of the population.
Note: The value of z 2 is called critical value of the distribution
and the next slide shows common critical values used lot in
confidence intervals. 5
 9.1 WHEN THE POPULATION STANDARD
DEVIATION KNOWN
The common critical value for 90%, 95%, 99% confidence
level:
Level of confidence Area in each tail, Critical vale
(1-α)*100% z
α/2 2

90% 0.05 1.645

95% 0.025 1.96

99% 0.005 2.575

Interpretation of a confidence interval: A (1-α)*100%

confidence interval indicates that (1-α)*100% of all
simple random samples of size n from the population 6
whose parameter is unknown will contain the parameter.
 9.1 WHEN THE POPULATION STANDARD
DEVIATION KNOWN
Comments for confidence interval:

 
x  z ( )    x  z ( )
2 n 2 n

Lower bound:

x  z ( )
2 n

Upper bound:

x  z ( )
2 n
7
 9.1 WHEN THE POPULATION STANDARD
DEVIATION KNOWN
Ex: a survey of 30 adults found that the mean age of a person’s
primary vehicle is 5.6 years. Assuming the standard
deviation of the population is 0.8 year, find the 99%
confidence interval of the population mean and interpret it.
Ans:  
x  z ( )    x  z ( )
2 n 2 n

x  5.6 based on the 30 adults sample; n=30;

  0.8 is the standard deviation of population.
confidence level is 99% and α=1-99%=1%,

z  z0.01  z0.005  2.575 8

2 2
 9.1 WHEN THE POPULATION STANDARD
DEVIATION KNOWN
and the final answer is:
 
x  z ( )    x  z ( )
2 n 2 n
0.8 0.8
5.6  2.575( )    5.6  2.575( )
30 30
5.6  0.376    5.6  0.376
5.224    5.976 or 5.22    5.98
Interpretation: one can be 99% confident that the mean age of
all primary vehicles is between 5.2 years and 6.0 years,
based on 30 vehicles.
Comments: the margin of error in this example is 0.376, if we
increase sample size, and the margin of error will decreasing.
If possible, collecting more data to reduce the margin of 9
error.
 9.1 WHEN THE POPULATION STANDARD
DEVIATION KNOWN
5. Calculating the necessary sample size:


E  za
2 n

E n  za *
2

za *
n  2
E
za *
n( 2
)2 10
E
 9.1 WHEN THE POPULATION STANDARD
DEVIATION KNOWN
Ex: the college president asks the statistics teacher to estimate
the average age of the students at their college. How large a
sample is necessary? The statistics teacher would like to be
99% confident that the estimate should be accurate within 1
year. (the standard deviation of the age is known to be 3
years.)
Ans:
α=1-99%=1%=0.01, α/2=0.01/2=0.005, Za/2 =2.575,
E=1
z a *
n( 2
)2
E
2.575 * 3 2
( )
1
 59.67 so, round up to 60
11
The sample size at least is 60 students.
 9.2 WHEN THE POPULATION STANDARD
DEVIATION UNKNOWN
As we know, if the standard deviation of population is known
and
1)the sample is drawn from a normal distribution
or
2) sample size n≥30 when parent population is unknown.

We will use z-value based on standard normal distribution to

construct confidence interval.

If the population standard deviation is unknown and sample

size n<30, then we will use t-value based on student’s t
distribution NOT use z-value based on standard normal 12
distribution.
 9.2 WHEN THE POPULATION STANDARD
DEVIATION UNKNOWN
Student’s t-distribution:
Suppose that a simple random sample of size n is taken from a
population. If the population from which the sample is
drawn follows a normal distribution. The distribution of
x  
t 
s follows a student’s t-distribution with n-1
n

Degree of freedom, where x is the sample mean and s is the

sample standard deviation.
Note: the t-statistic represents the number of sample standard
errors x is from the population mean,  .
13
 9.2 WHEN THE POPULATION STANDARD
DEVIATION UNKNOWN
Properties of the t-distribution:
1) The t-distribution is different for different degree of
freedom.
2) The t-distribution is centered at 0 and is symmetric about 0.
3) The area under the curve is 1. The area under the curve to
the right of 0 equals to the area under the curve to the left
of 0, which equals ½=0.5.
4) As t increases without bound, the graph approaches, but
never equals, zero. As t decreases without bound, the graph
approaches, but never equals, zero.
5) The area is the tails of the t-distribution is a little greater
than the area in the tails of the standard normal distribution,
because we are using s as an estimate of  , thereby
introducing further variability into the t-statistic. 14
 9.2 WHEN THE POPULATION STANDARD
DEVIATION UNKNOWN
6) As the sample size n increases, the density curve of t gets
closer to the standard normal density curve. This result
occurs because, as the sample size increases, the values of
s get closer to the value of , by the law of large
numbers.
Page 426, figure 8 shows these properties.

A. How to find t-values:

Let’s go over the example 2 on page 426. After this example,
you should know how to find the t-values.

15
 9.2 WHEN THE POPULATION STANDARD
DEVIATION UNKNOWN
Constructing a (1-α)*100% confidence interval for  , 
unknown:

s s
x  t 2 ( )    x  t 2 ( )
n n

s
lower bound : x  t 2 ( )
n

s
upper bound : x  t 2 ( )
n 16
 9.2 WHEN THE POPULATION STANDARD
DEVIATION UNKNOWN
Ex: the below data represents a sample of the number of home
fires started by candles for the past several years, find the
99% confidence interval for the mean number of home fires
started by candles each year.
5460, 5900, 6090, 6310, 7160, 8440, 9930
Answer: step 1: find the sample mean and standard deviation
based on the sample
x  7041.4 s  1610.3
Step 2: find the tα/2
sample size n=7, so degree of freedom is n-1=7-1=6
tα/2 =3.707
17
 9.2 WHEN THE POPULATION STANDARD
DEVIATION UNKNOWN
Step 3: formula used:
s s
x  t 2 ( )    x  t 2 ( )
n n

1610.3 1610.3
7041.4  3.707( )    7041.4  3.707( )
7 7
4785.2    9297.6

How to interpret this result? 18

 9.2 WHEN THE POPULATION STANDARD
DEVIATION UNKNOWN
Summary:
1) If population standard deviation  is known, and
a) sample size n ≥30, using z-interval.
b) sample size n <30, but the sample is drawn from a
normal population, using z-interval. If the sample not from
normal population, using non-parametric method.
2) If population deviation  unknown, and
a) sample size n≥30, using t-interval.
b) sample size n<30, if sample is from normal population,
then using t-interval, if not from normal population, using
non-parametric method.
19