RP ch07
RP ch07
The following problems have been reserved for your use in assignments and testing and do not
appear in student versions of the text.
A random sample of 140 in size is taken from a population with a mean of 1540 and unknown
variance. The sample variance was found out to be 130.
(b) Find the mean of the sampling distribution of the sample mean.
SOLUTION
(a)
(b)
Service time for a customer coming through a checkout counter in a retail store is a random
variable with the mean of 4.0 minutes and standard deviation of 1.5 minutes. Suppose that the
distribution of service time is fairly close to a normal distribution. Suppose there are two
counters in a store, customers in the first line and customers in the second line.
Find the probability that the difference between the mean service time for the shorter line and
the mean service time for the longer one is more than 0.4 minutes. Assume that the service
times for each customer can be regarded as independent random variables.
SOLUTION
A random sample of is selected from this distribution. Find the probability that the
sample mean is greater than 4.8.
SOLUTION
In order to find out the defect rate of the manufactured components a random sample of
was selected. Four specimens were found to be defective. Estimate the proportion of defective
components in the population.
SOLUTION
Consider a normal population with the mean of 40 and standard deviation of 10. A random
sample of was selected:
39.2, 45.7, 27.4, 25.9, 25.1, 46.3, 42.9, 49.0, 40.6, 47.0.
Find the probability that the point estimate of the population mean based on the second sample
of would be more accurate.
SOLUTION
A normal population has the mean of 20 and the variance of 100. A random sample of size
is selected.
(b) How large must the sample be if you want to halve the standard deviation of the sample
mean?
SOLUTION
(a)
(b)
The lamps of type A have the average lifetime of 2000 hours with the variance of 3500. The
lamps of type B have the average lifetime of 2100 hours with the same variance. A random
sample of lamps of each type is selected. Let and be the two sample means.
Find the probability that .
SOLUTION
is approximately normal with mean hours and variance
hours.
Chest pain 7
Difficulty breathing 7
Numbness in extremities 3
Broken bones 11
Abrasions 16
Cuts 21
Stab wounds 9
Gunshot wounds 4
Blunt force trauma 10
Fainting, loss of consciousness 5
Other 9
Estimate the proportion of patients who arrive at this emergency department experiencing chest
pain.
SOLUTION
The proportion of arrivals for chest pain is 8 among 103 total arrivals. The proportion
.
A consumer electronics company is comparing the brightness of two different types of picture
tubes for use in its television sets. Tube type A has mean brightness of 100 and standard
deviation of 16, and tube type B has unknown mean brightness, but the standard deviation is
assumed to be identical to that for type A. A random sample of tubes of each type is
selected, and is computed. If equals or exceeds , the manufacturer would like to
adopt type B for use. The observed difference is .
What is the probability that exceeds by 3.0 or more if and are equal?
SOLUTION
Then, .
The probability that exceeds by 3.0 or more is not that unusual when and equal.
Therefore, there is not strong evidence that is greater than .
Consider a Weibull distribution with shape parameter 1.5 and scale parameter 2.0.
2.39 1.14 0.56 3.48 1.57
1.53 2.78 3.01 0.55 1.29
2.22 0.64 0.49 0.56 0.11
2.59 1.01 0.43 1.62 3.43
5.50 1.55 0.59 0.61 0.68
0.54 0.99 1.48 2.23 6.25
1.23 2.52 1.27 1.01 6.26
2.43 0.27 1.33 1.27 2.72
0.26 3.59 1.91 0.02 2.94
2.47 0.85 1.58 2.40 2.06
C
Normal probability plot: Does it look very much like a normal distribution?
The table constructed by drawing 10 samples of size n=5 from this distribution.
Compute the sample average from each sample.
Obs Mean
1 2.72 1.27 1.01 6.26 0.55 2.36 ? 0.01
2 0.99 2.59 5.50 1.27 0.64 2.20 ? 0.01
3 6.25 0.61 2.43 6.26 0.68 3.25 ? 0.01
4 0.26 1.29 1.23 1.14 1.57 1.10 ? 0.01
5 1.57 1.01 2.43 0.26 1.58 1.37 ? 0.01
6 1.62 2.72 2.78 2.39 2.94 2.49 ? 0.01
7 0.56 2.47 1.91 0.99 0.27 1.24 ? 0.01
8 2.06 0.59 2.59 1.14 0.54 1.38 ? 0.01
9 3.48 1.55 1.14 3.43 0.68 2.06 ? 0.01
10 1.23 1.01 2.47 0.56 3.59 1.77 ? 0.01
A
B
SOLUTION
The histogram of the data:
Obs Mean
1 2.72 1.27 1.01 6.26 0.55 2.36
2 0.99 2.59 5.50 1.27 0.64 2.2
3 6.25 0.61 2.43 6.26 0.68 3.25
4 0.26 1.29 1.23 1.14 1.57 1.1
5 1.57 1.01 2.43 0.26 1.58 1.37
6 1.62 2.72 2.78 2.39 2.94 2.49
7 0.56 2.47 1.91 0.99 0.27 1.24
8 2.06 0.59 2.59 1.14 0.54 1.38
9 3.48 1.55 1.14 3.43 0.68 2.06
10 1.23 1.01 2.47 0.56 3.59 1.77
The normal probability plot of sample mean from each sample is much more normally
distributed than the raw data.
SOLUTION
The expected value of X for continuous uniform distribution:
On the other side, we know that the sample mean is the unbiased estimator of .
Thus,
At the candle factory, 10 out of 100 produced candles in the sample are defective. Find a point
estimate of the probability that a fault free candle is produced.
SOLUTION
The unbiased estimator of the probability that a candle without defects is produced is ,
where X is the number of fault free candles, n is the total number.
Therefore,
The number of passengers for a particular bus route was counted, and data for 3 weeks are
shown in the table:
(a) Calculate a point estimate of the mean number of passengers and its standard error. Consider
the unbiased estimator .
(b) Calculate a point estimate of the mean number of passengers and its standard error on
weekdays and weekends separately.
SOLUTION
(a)
where
.
(b)
for weekdays.
for weekends.
The diameter of the cylinder is 52 cm, its height was measured 7 times. Measurements are as
follows:
58.3, 58.1, 57.9, 57.7, 58.2, 57.8, 58.1cm. Calculate a point estimate of the cylinder volume.
Consider the unbiased estimator . Use .
SOLUTION
SOLUTION
Energy deviation from the mean is larger than the standard deviation for ball throws whose
, , .
or
If then use .
Let three random samples of sizes , , and be taken from a population with
mean and variance . Let , , and be the sample variances.
SOLUTION
Suppose that the random variable X has a lognormal distribution with parameters and
. A sample of size is drawn from this distribution. In order to find the standard
error of the sample median of this distribution with the bootstrap method bootstrap
samples are generated.
Sample
1 7.01 3.58 7.04 3.58 7.86 14.68 3.01 8.56 7.66 10.84
2 4.75 14.66 4.76 7.66 5.29 4.48 4.98 6.07 6.37 1.50
3 23.72 2.80 6.03 5.89 3.58 2.22 6.50 1.52 3.19 9.59
4 1.50 4.75 5.63 1.87 5.27 1.83 7.66 5.63 4.55 4.20
5 6.98 10.21 1.50 6.03 4.97 3.19 10.86 6.37 6.33 4.98
Find the standard error of the sample median of this distribution with the bootstrap method.
SOLUTION
Sample Sample median
1 7.35
2 5.14
3 4.74
4 4.65
5 6.18
Here the sample median is computed for each of the bootstrap samples. The standard error is
estimated as the standard deviation of these sample medians, and in this case we obtain 1.15.
An exponential distribution is known to have a mean of 10. You want to find the standard error
of the median of this distribution if a random sample of size 8 is drawn. In order to use the
bootstrap method bootstrap samples are generated.
Sample
1 29.86 7.71 7.57 5.32 7.40 10.51 11.26 12.85
2 0.50 20.91 10.61 13.02 1.81 14.62 43.43 12.92
3 3.60 36.86 11.26 2.34 10.18 10.51 1.33 0.58
4 0.58 3.97 18.10 8.57 11.63 8.57 5.70 4.47
5 10.99 4.16 0.85 0.50 7.74 18.10 3.95 1.02
Find the standard error of the median with the bootstrap method.
SOLUTION
SOLUTION
Find the maximum likelihood estimator for if is known. Use variable “i” as sum
index in your answer.
SOLUTION
SOLUTION
a) If and , then .
If , then .
b) If and , then .
If , then .
c) Similarly, if , then .
(b) Find the moment estimator for if is known. Use M as the symbol of sample
mean.
SOLUTION
(a)
(b)
The time in minutes between customer arrivals at a store has an exponential distribution with
parameter . The prior distribution for is exponential with the mean of 2. A random sample
of gives the average time between arrivals minutes. Find the Bayes estimate for .
SOLUTION
and .
Reserve Problems Chapter 7 Section 4 Problem 6
The length of the manufactured component is a normal random variable with an unknown mean
and the known variance of . The prior distribution for µ is normal with and
. A random sample of 10 components was taken. Their lengths in centimeters are
20.05, 19.93, 20.00, 19.93, 20.06, 20.00, 20.05, 20.04, 20.10, 19.99.
SOLUTION
(a)
If the prior distribution for is normal with mean and variance , then is
posterior variance .
Is an unbiased estimator of ?
SOLUTION
SOLUTION
Reserve Problems Chapter 7 Section 4 Problem 9
SOLUTION
The parameter cannot be estimated by setting the derivative of the log likelihood with respect
to to zero because the log likelihood is linear function of . The range of the likelihood is
important.
The joint density function and therefore the likelihood is zero for so that
.
, , .
(a) It can be shown that . Use this information to construct an unbiased estimator for
.
(b) Find the maximum likelihood estimator of .
(c) Select the right expression for the median of the Rayleigh distribution.
(d) Can we estimate the median a by substituting our estimate for into the equation for a?
SOLUTION
(a)
so
(b)
.
(c)
(d)
According to the invariance property of the maximum likelihood estimator, we can estimate the
median a by substituting our estimate for into the equation for a.
Suppose that X is a normal random variable with unknown mean and known variance .
The prior distribution for is a normal distribution with mean and variance . Does the
Bayes estimator for become the maximum likelihood estimator when the sample size n is
large?
SOLUTION
The posterior distribution for is normal with mean . The Bayes estimator
for goes to the MLE as n increases. This follows because goes to 0, and the estimator
Suppose that X is a normal random variable with unknown mean and known variance .
The prior distribution for is a uniform distribution defined over the interval .
SOLUTION
(a)
for and .
Then, ,
where is the standard normal cumulative distribution function. Then
.
(b)
The Bayes estimator is
Suppose that X is a Poisson random variable with parameter . Let the prior distribution for
be a gamma distribution with parameters and .
SOLUTION
for ,
and for .
Then, .
This last density is recognized to be a gamma density as a function of . Therefore, the posterior
A norm population has a known mean 50 and known variance . A random sample of
is selected from this population, and the sample mean is .
How unusual is this result?
SOLUTION
SOLUTION
Making the last equation equal to zero and solving for theta, we obtain the maximum likelihood
estimate
You plan to use a rod to lay out a square, each side of which is the length of the rod. The length
of the rod is , which is unknown. You are interested in estimating the area of the square, which
is . Because is unknown, you measure it n times, obtaining observations .
Suppose that each measurement is unbiased for with variance .
(a) Is a biased or an unbiased estimate of the area of the square?
(b) Is a biased or an unbiased estimate of the area of the square?
SOLUTION
(a)
When the sample standard deviation is based on a random sample of size n from a normal
population, it can be shown that S is a biased estimator for . Specifically,
.
(a) Use this result to obtain an unbiased estimator for of the form , when the constant
depends on the sample size n.
(b) Find the value of for and .
SOLUTION
(a)
(b)
When , . When , . Therefore, S is a reasonably good
estimator for the standard deviation even when relatively small sample sizes are used.
(a) Find the cumulative distribution functions of these two order statistics, denoted respectively
by and .
(b) If X is continuous with probability density function , find the probability distributions of
and .
(c) Let be a random sample of a Bernoulli random variable with parameter P. Find
the following probabilities.
(d) Let be a random sample of a normal random variable with mean and
variance . Derive the probability density functions of and .
SOLUTION
(a)
for
for
Then, .
(b)
(c)
because .
(d)
(e)
is sometimes used to estimate the population standard deviation. This estimator is more robust to
outliers than the usual sample standard deviation and usually does not differ much from S when
there are no unusual observations.
(a) Calculate and S for the data 10, 12, 9, 14, 18, 15, and 16.
(b) Replace the first observation in the sample (10) with 50 and recalculate both S and .
SOLUTION
(a)
The traditional estimate of the standard deviation, S, is 3.26. The mean of the sample is 13.43 so
the values of corresponding to the given observations are 3.43, 1.43, 4.43, 0.57, 4.57,
1.57 and 2.57. The median of these new quantities is 2.57 so the new estimate of the standard
deviation is 3.81 and this value is slightly larger than the value obtained from the traditional
estimator.
(b)
Making the first observation in the original sample equal to 50 produces the following results.
The traditional estimator, S, is equal to 13.91. The new estimator is 7.62.