Chapter 6:
Estimation
Chapter 6. Estimation
Concepts: Estimation; point estimator;
point estimate, and interval estimate.
Sampling distribution.
Interval estimation:
Interval estimates of population mean
Interval estimates of population proportion
Determining the sample size.
2
Process of Estimation
1. Population
consists of all bulbs
Manufactured with 2. A sample of 200
the new filament. bulbs is manufactured
Average lifetime is with the new filament.
unknown.
3. The sample data
4. The sample average
provide a sample
is used to estimate the average lifetime
population average. of 76 hours per bulb.
3
3
Concepts
• Estimation (Ước lượng): is the statistical
process in which sample statistics are used to
estimate population parameters.
4
Concepts (cont)
4
• Process of Statistical Inference
Process of Estimation -1
• Process of Estimation of mean
Population A simple random sample
with mean of n elements is selected
=? from the population.
The value of x is used to The sample data
make inferences about provide a value for
the value of . the sample mean x
6
Process of Estimation -2
• Process of Estimation of proportion
Population A simple random sample
With proportion of n elements is selected
p=? from the population.
The value of is used The sample data
to make inferences provide a value for
about the value of p. the sample proportion
.
7
Interval Estimation
9
Interval Estimation
9
Unbiased estimator -1
(Ước lượng không chệch)
Definition: An estimator of a parameter is said to be
unbiased if the mean of its distribution is equal to the
true value of the parameter. For instance, )= .
Otherwise, the estimator is said to be biased.
10
Unbiased estimator -2
11
Sampling Distribution -2
• When you draw a sample from a population, the
numerical value of the mean of the sample is a
random variable that estimates the population
mean ( . The value of will vary because the
sample data varies from sample to sample.
• In this chapter, the central limit theorem
(Định lý giới hạn trung tâm) and confidence
intervals for estimating unknown population
parameters are discussed and explained.
12
Sampling Distribution -3
For example, suppose you want to select a sample
of size n = 2 from a population containing N = 4
objects.
If the four objects are identified by the symbols
X1, X2, X3, and X4, there are six distinct pairs
that could be selected, as listed in following
Table.
13
Sampling Distribution -4
If the sample of n = 2 observations is selected so that each of
these six samples has the same chance of selection, given by
1/6, then the resulting sample is called a simple random
sample, or just a random sample.
14
Sampling Distributions -5
2
Theorem 1: If X N ; 2 then X N;
n
X
and Z n N0;1.
15
Sampling Distributions -5
Theorem 2 (Central limit theorem - CLT):
Suppose that E(X ) and var(X ) (finite)
2
2
then X N; when n 30.
n
16
Sampling Distribution -8
For the central limit theorem to apply, a sample of
at least 30 is considered large enough.
In practice, only one sample is taken and one
sample mean, is calculated.
17
Illustration of the Central limit theorem
18
Sampling Distribution -15
19
Sampling Distribution -9
Suppose that you’re interested in the age that people retire in the
United States.
The population is all retired Americans, and the distribution of the
population might look something like this:
19
Sampling Distribution -10
Now we take a small sample of the population. You
randomly select five retirees and ask them what age they
retired.
A sample of n = 5:
68; 73; 70; 62; 63
This sample has the mean and standard deviation are
Mean = 67.2
Sd = 4.66
The mean of the sample is an estimate of the population
mean. It might not be a very precise estimate, since the
sample size is only 5.
20
Sampling Distribution -11
Suppose that you repeat this procedure 10 times, taking
samples of five retirees, and calculating the mean of
each sample. The means of 10 small samples:
60.8; 57.8; 62.2; 68.6; 67.4; 67.8; 68.3; 65.6; 66.5; 62.1
If you repeat the procedure many times, a histogram of
the sample means will look something like this. The
distribution is a little left-skewed.
21
Sampling Distribution -12
22
Sampling Distribution -13
Now, imagine that you take a large sample of
the population. You randomly select 50
retirees and ask them what age they retired.
Again, you can repeat this procedure many
more times and calculating the mean of each
sample:
23
Sampling Distribution -14
24
Examples -1
Example 1: A random sample of size
from a population with
.
1/ Describe the sampling distribution of in term
of its shape, mean, and standard deviation.
2/ Find the probability that the mean of the
sample will be greater than 78.92.
25
Examples -2
Example 1: Sol
26
Examples -3
• Example 2: IQ score for adults are normally
distributed, with mean and standard
deviation sample of 25
adults is selected.
• Find the probability that the mean IQ score of the
sample will be less than or equal to 94.
27
Examples -4
Sol:
28
Interval estimation
(Ước lượng khoảng)
• The probability that a confidence interval will
contain the estimated parameter is called the
confidence coefficient.
Co
confidence
coefficient.
29
Margin of Error
and the interval estimate -1
A point estimator cannot be expected to provide the
exact value of the population parameter.
An interval estimate can be computed by adding and
subtracting a margin of error to the point estimate.
Point Estimate +/ Margin of Error
30
Margin of Error
and the interval estimate -2
The purpose of an interval estimate is to provide
information about how close the point estimate is to
the value of the parameter.
How often will this interval work properly and
enclose the parameter of interest? Refer to following Figs
31
Margin of Error
and the interval estimate -1
32
6.3 Interval estimation
33
Margin of Error and the interval estimate -1
interval
does not
include
true value
34
Interval estimate of a population mean-1
The general form of an interval estimate of a
population mean ( ) is
x Margin of Error
35
Interval estimate of a population mean -2
• In order to develop an interval estimate of a
population mean, the margin of error must be
computed using either:
– the population standard deviation, , or
– the sample standard deviation, s
• is rarely known exactly, but often a good
estimate can be obtained based on historical data
or other information.
36
This section explains how to construct a
confidence interval for the population mean
when the population standard deviation is
known. Here, there are three possible cases, as
follows
37
Case #1: n 30 and is known.
Suppose that X~N
is given.
A sample of n elements (n 30) is taken from
the population, then a 100% confidence
interval about (population mean) under this
case is determined:
Note: Using theorem 1 (page#16) or theorem 2
(CLT) for proof.
38
39
Case #2: n 30 and is known.
Suppose that X~N is given.
A sample of n elements (n 30) is taken from the
population, then a 100% confidence
interval about (population mean) under this case
is determined:
Using theorem 1 (page 16) for proof.
40
Case #3: n 30 and is unknown.
Suppose that X~N is
unknown.
A sample of n elements (n 30) is taken from the
population, then a 100% confidence
interval about under this case is determined:
Note: Using theorem 3 (page #20) for proof.
41
Case #4: n 30 and is unknown.
Suppose that X~N is unknown.
A sample of n elements (n 30) is taken from the
population, then a 100% confidence
interval about under this case is determined:
42
43
When to use Normal or t-Distribution?
40
Sol
41
Examples
41
Examples
42
Sol
42
Example 3 : A travel agent wants to gather information on the
per-night cost at hotels in Caribbean countries. She took a
random sample of 52 rooms from various hotels in those
countries. The sample produced a mean cost for the 52 rooms to
be $208.35 per night.
If the population standard deviation of costs for a one-night
stay in Caribbean hotels is $47.45, find a 99% confidence
interval for the average cost per night in Caribbean hotels.
43
43
Examples
44
Examples
Suppose that CEO compensation for all large
companies in the United States in 2010 is
normally distributed.
Question: Find a 95% confidence interval for the
average CEO compensation for all large companies
in United State in 2010.
45
Interval Estimate
of a Population Proportion -1
46
Interval Estimate
of a Population Proportion -2
Example: In a sample of 400 registered voters,
204 were Democrats.
a/ Provide a 95% confidence for the proportion
of registered Democrats voters in the population.
b/ There are 169 million registered voters in the
US. Determine an interval for the number (how
many) of registered Democrats in the
population with 95% confidence level.
47
Sample size for an interval estimate of a
population mean -1
E z /2
n
(z/2 ) 2 2
n
E2
48
Sample size for an interval estimate
of a population mean -2
The necessary sample size equation requires a value for
the population standard deviation .
If is unknown, a preliminary or planning value for s can
be used in the equation.
1. Use the estimate of the population standard deviation
computed in a previous study.
2. Use a pilot study to select a preliminary study and
use the sample standard deviation from the study.
3. Use judgment or a “best guess” for the value of s .
49
Sample size for an interval estimate
of a population mean -3
Adequate Sample Size:
In most applications, a sample size of n = 30 is
adequate.
If the population distribution is highly skewed or contains
outliers, a sample size of 50 or more is recommended.
50
Sample size for an interval estimate
of a population mean -4
Example 1: A marketing researcher wants to find a
95% confidence interval for the mean amount that
visitors to a theme park spend per person per day. She
knows that the standard deviation of the amounts spent
per person per day by all visitors to this park is $11. How
large a sample should the researcher select so that the
estimate will be within $2 of the population mean?
51
Sample size for an interval estimate
of a population mean -4
Example 1: Sol
51
Sample size for an interval estimate
of a population mean -5
Example 2: A machine that is programmed to package
1.20 pounds of cereal is being tested for its accuracy. In a
sample of 36 cereal boxes, the sample mean filling weight
is calculated as 1.22 pounds. The population standard
deviation is known to be 0.06 pound.
a/ Identify the relevant parameter of interest for these
quantitative data and compute its point estimate as well as
the margin of error with 95% confidence.
b/ Can we conclude that the packaging machine is operating
improperly? How large a sample must we take if we want
the margin of error to be at most 0.01 pound with 95%
confidence?
52
Sample Size for an Interval Estimate of a
Population Proportion -1
p(1 p)
E z /2
n
Solving for the necessary sample size, we get
However, will not be known until after we have
selected the sample. We will use the planning value p*
for .
53
Sample Size for an Interval Estimate
of a Population Proportion -2
• 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 0.50 as the p* value.
54
Sample Size for an Interval Estimate
of a Population Proportion -3
• Some Possible Values for p*(1 − p*)
55
End of Chapter 6
65
