RAJALAKSHMI INSTITUTE OF TECHNOLOGY

DEPARTMENT OF HUMANITIES AND SCIENCE

SUBJECT NAME: PROBABILITY AND STATISTICS
SUBJECT CODE:MA3391
UNIT-3
UNIT NAME: ESTIMATION THEORY

2UNIT –III ESTIMATION THEORY

PART – A

1. Write the difference between Point estimate and Interval Estimate of population parameters.

Ans:

Point Estimate of Population Parameters Interval Estimate of Population parameters

A point estimate of a population parameter is a An interval estimate is defined by two numbers,

single value of a statistic. between which a population parameter is said to
lie.

For example, the sample mean 𝑋̿ is a point For example, 𝑎 < 𝑋 < 𝑏 is an interval estimate
estimate of the population mean 𝜇. Similarly, the of the population mean 𝜇 . It indicates that the
sample proportion 𝑝 is a point estimate of the population mean is greater than a but less than b.
population proportion P.

2. What is an Estimator?

Ans:

Estimator (or) Point estimator is a procedure for producing an estimate of a parameter of interest. An
estimator is usually a function of only sample data values, and when these data values are available, it
results in an estimator of the parameter of interest.

3. Define a point estimator.

Ans:

A point estimator of some population parameter 𝜃 is a single numerical values 𝜃̅ of a statistic 𝜃̅ . The
statistic 𝜃̅ is called the point estimator .

4. What are the characteristics that should be satisfied by a good estimator?

Ans:
 RAJALAKSHMI INSTITUTE OF TECHNOLOGY
DEPARTMENT OF HUMANITIES AND SCIENCE
SUBJECT NAME: PROBABILITY AND STATISTICS
SUBJECT CODE:MA3391
UNIT-3
UNIT NAME: ESTIMATION THEORY

(i) Consistency (ii) Unbiasedness (iii) Efficiency (iv) Suffiviency

5. What are the commonly used methods of point estimation?

Ans: 1. Methods of maximum likelihood estimator
2. Methods of minimum variance
3. Methods of moments
4. Method of least squares
5. Method of minimum chi-square
6. Method of inverse probability
6. Define the minimum variance unbiased estimator (MVUE).
Ans:
If all the unbiased estimators of 𝜃 are considered the one with the smallest variance is called the minimum
variance unbiased estimator.
7. Define population estimation.
Ans: Population estimates can describe the total population size as well as demographic characteristics
such as age, sex or education level.
Population estimates are dependent on the demographic components of change : Mortality, Fertility and
Migration.
8. What is called interval estimation?
Ans: In an estimate of a population parameter 𝜃 given by two distinct numbers between which the
parameter may be considered to lie, then the estimate is called an interval estimate of the parameter 𝜃.
9. Define point estimate and interval estimate.
Ans: A point estimate of a population parameter is a single value of a statistic. For example, the sample
mean 𝑋̿ is a point estimate of the population mean 𝜇. Similarly, the sample proportion 𝑝 is a point
estimate of the population proportion P.
An interval estimate is defined by two numbers, between which a population parameter is said to lie. For
example, 𝑎 < 𝑋 < 𝑏 is an interval estimate of the population mean 𝜇. It indicates that the population
mean is greater than a but less than b.
 RAJALAKSHMI INSTITUTE OF TECHNOLOGY
DEPARTMENT OF HUMANITIES AND SCIENCE
SUBJECT NAME: PROBABILITY AND STATISTICS
SUBJECT CODE:MA3391
UNIT-3
UNIT NAME: ESTIMATION THEORY

10. Define unbiased estimator.

Ans:
Let 𝜃̅ be an estimator of the parameter 𝜃 then the estimator 𝜃̅ (𝑥1 , 𝑥2 , … , 𝑥𝑛 ) is said to be an unbiased estimate of
parameter 𝜃. For example 𝐸(𝑥̅ ) = 𝜇, the sample mean is an unbiased estimate of a population mean 𝜇.
11. What is the example of a robust statistic?
Ans:
Using the same data set: 50,52,55,56,59,59,60 if we changed the 60 to 1000, the median is entirely
unaffected. It’s still 56 in both cases. Consequently, the median is a robust statistic for central tendency
while the mean is not.
12. How do you calculate robust mean?
(𝑥1 ,𝑥2 .…,𝑥𝑛 )
Ans: It is given by 𝑛
. You can change the calculated value of a mean by an arbitrary large

amount, simply by changing one of the data points by a large amount. Therefore the breakdown point is
1
just .
𝑛

13. Define maximum likelihood estimator of 𝜃.

Ans
The maximum likelihood estimator of 𝜃 is the value of 𝜃 that maximizes the likelihood function 𝐿(𝜃) =
𝑛𝐶𝑃𝑖=1 𝑓(𝑥𝑖 , 𝜃).
14. Mention the properties of the maximum likelihood estimator.
Ans:
Under very general and not restrictive conditions, when the sample size n is large and if 𝜃̅ is the
maximum likelihood estimator of the parameter 𝜃,
(i) 𝜃̅ is an approximately unbiased estimator of 𝜃, [𝐸(𝜃̅ ) = 𝜃].
(ii) The variance of 𝜃̅ is nearly as small as the variance that could be obtained with any other
estimator.
(iii) 𝜃̅ has an approximate normal distribution.
(iv) Invariance property
If 𝜃1̅ , 𝜃̅2 , … , 𝜃̅𝑘 are the maximum likelihood estimators of the parameters 𝜃1 , 𝜃2 , … , 𝜃𝑘 , then the
 RAJALAKSHMI INSTITUTE OF TECHNOLOGY
DEPARTMENT OF HUMANITIES AND SCIENCE
SUBJECT NAME: PROBABILITY AND STATISTICS
SUBJECT CODE:MA3391
UNIT-3
UNIT NAME: ESTIMATION THEORY

maximum likelihood estimator of any function ℎ(𝜃1 , 𝜃2 , … , 𝜃𝑘 ) of these parameters is the same
function ℎ(𝜃1̅ , 𝜃̅2 , … , 𝜃̅𝑘 ) of the estimators 𝜃1̅ , 𝜃̅2 , … , 𝜃̅𝑘 .
15. Define the population moment estimators.
Ans:
Let 𝑋1 , 𝑋2 , … , 𝑋𝑛 be a random sample from either a probability mass function or probability density
function with 𝑚 unknown parameters𝜃1 , 𝜃2 , … , 𝜃𝑘 . The moment estimator 𝜃1̅ , 𝜃̅2 , … , 𝜃̅𝑘 are found by
equating the first m population moments to the first m sample moments and solving the resulting
equations for the unknown parameters.

PART-B
𝑋
1. If 𝑋 is a binomial variate with parameters 𝑛 and 𝑝, then show that 𝑛 , the observed proportion of
successes is an unbiased estimator of the parameter 𝑝.
Ans.

2. Prove that for a random sample (𝑥1 , 𝑥2 , … , 𝑥𝑛 ) of size 𝑛 drawn from a given large population (𝜇, 𝜎 2 ),
1 𝑛𝑠2 1
𝑠 2 = ∑𝑛𝑖=1(𝑥𝑖 − 𝑥̅ )2 is not an unbiased estimator of the parameter 𝜎 2 , but = ∑𝑛 (𝑥 − 𝑥̅ )2 is
𝑛 𝑛−1 𝑛−1 𝑖=1 𝑖
an unbiased estimator of 𝜎 2 .
Ans:
 RAJALAKSHMI INSTITUTE OF TECHNOLOGY
DEPARTMENT OF HUMANITIES AND SCIENCE
SUBJECT NAME: PROBABILITY AND STATISTICS
SUBJECT CODE:MA3391
UNIT-3
UNIT NAME: ESTIMATION THEORY

3. If 𝑠12 , 𝑠22 , … , 𝑠𝑟2 are 𝑟 sample variables based on random samples of sizes 𝑛1 , 𝑛2 , … , 𝑛𝑟 respectively drawn
1
from a large population with variance 𝜎 2 and 𝑇 = 𝑘 ∑𝑟𝑖=1 𝑛𝑖 𝑠𝑖2 = 𝜎 2 is an unbiased estimate of 𝜎 2 , find
the value of 𝑘.
Ans:
 RAJALAKSHMI INSTITUTE OF TECHNOLOGY
DEPARTMENT OF HUMANITIES AND SCIENCE
SUBJECT NAME: PROBABILITY AND STATISTICS
SUBJECT CODE:MA3391
UNIT-3
UNIT NAME: ESTIMATION THEORY

1
4. If 𝑥1 , 𝑥2 , … , 𝑥𝑛 is a random sample from 𝑁(0, 𝜎 2 ) and if 𝑇 = 𝑛 ∑𝑛𝑖=1 𝑥𝑖2 , then 𝑇 is an unbiased estimate of
𝜎 2.
Ans:

5. Below you are given the values obtained from a random sample of observations taken from an infinite
population
32 34 35 39
(a) Find a point estimator for 𝜇. Is this an unbiased estimate of 𝜇? Explain.
(b) Find a point estimator for 𝜎 2 . Is this an unbiased estimate of 𝜎 2 . Explain.
(c) Find the point estimator for 𝜎.
(d) What can be said about the sampling distribution of 𝑥̅ ? Be sure to discuss the expected value, the
standard deviation, and the shape of the sampling distribution of 𝑥̅ ?
Ans:
 RAJALAKSHMI INSTITUTE OF TECHNOLOGY
DEPARTMENT OF HUMANITIES AND SCIENCE
SUBJECT NAME: PROBABILITY AND STATISTICS
SUBJECT CODE:MA3391
UNIT-3
UNIT NAME: ESTIMATION THEORY

6. Let 𝑥1 , 𝑥2 , 𝑥3 , 𝑥4 be a random sample of size 4 from a population with mean value 𝜇 and variance 𝜎 2 . Let
𝑇1 , 𝑇2 , 𝑇3 , 𝑇4 be the estimators used to estimate mean value 𝜇 where
T1 = 𝑥1 + 𝑥2 + 𝑥3 − 2𝑥4
T2 = 𝑥1 + 2𝑥2 + 3 𝑥3 − 5𝑥4
k𝑥1 + 𝑥2 + 𝑥3 + 𝑥4
T3 =
4
(i)Find whether 𝑇1 and 𝑇2 are unbiased estimators?
(ii) Find the value of 𝑘 such that 𝑇2 is unbiased estimator for 𝑚.
(iii) With this values of 𝑘 is 𝑇3 a consistent estimator?
(iv)Which is the best estimator?
Ans:
 RAJALAKSHMI INSTITUTE OF TECHNOLOGY
DEPARTMENT OF HUMANITIES AND SCIENCE
SUBJECT NAME: PROBABILITY AND STATISTICS
SUBJECT CODE:MA3391
UNIT-3
UNIT NAME: ESTIMATION THEORY

7. If 𝑥1 , 𝑥2 , … , 𝑥𝑛 are random observations of a Bernoullli’s variate 𝑥 which assumes values 1 and 0 with
𝑇(𝑛−𝑇)
probabilities 𝜃 and 1 − 𝜃 respectively. Show that 𝑛(𝑛−1) is an unbiased estimator of 𝜃(1 − 𝜃), where 𝑇 =
𝑥1 + 𝑥2 + ⋯ + 𝑥𝑛
Ans:
 RAJALAKSHMI INSTITUTE OF TECHNOLOGY
DEPARTMENT OF HUMANITIES AND SCIENCE
SUBJECT NAME: PROBABILITY AND STATISTICS
SUBJECT CODE:MA3391
UNIT-3
UNIT NAME: ESTIMATION THEORY

8. If {𝑥1 , 𝑥2 , … , 𝑥𝑛 } is a random sample of size 𝑛, drawn from a geometric distribution , the probability mass
function of which is given by 𝑃(𝑥 = 𝑟) = 𝑝𝑞 𝑟−1 ; 𝑟 = 1,2, … , ∞. Prove that the mean of the sample is a
consistent estimator of the population mean.
Ans

9. If 𝑡1 is a most efficient estimator and 𝑡2 is an unbiased estimator (of some population parameter) with
efficiency 𝑒, and if the correlation coefficient 𝜌 between 𝑡1 and 𝑡2 is 𝜌 show that 𝜌 = √𝑒.
Ans
 RAJALAKSHMI INSTITUTE OF TECHNOLOGY
DEPARTMENT OF HUMANITIES AND SCIENCE
SUBJECT NAME: PROBABILITY AND STATISTICS
SUBJECT CODE:MA3391
UNIT-3
UNIT NAME: ESTIMATION THEORY

10. Find the estimator of 𝜃 in the population with density function 𝑓(𝑥, 𝜃) = 𝜃𝑥 𝜃−1 ; 0 < 𝑥 < 1; 𝜃 > 0, by
method of moments.
Ans:
 RAJALAKSHMI INSTITUTE OF TECHNOLOGY
DEPARTMENT OF HUMANITIES AND SCIENCE
SUBJECT NAME: PROBABILITY AND STATISTICS
SUBJECT CODE:MA3391
UNIT-3
UNIT NAME: ESTIMATION THEORY

𝑝𝑥 (1−𝑝)3−𝑥
11. For the probability mass function 𝑓(𝑥, 𝑝) = 3𝐶𝑥 . 1−(1−𝑝)3
; 𝑥 = 1,2,3. Obtain the estimator of 𝑝 by the
method of moments, if the frequencies at 𝑥 = 1,2,3 are respectively 22, 20 and 18.
Ans:
 RAJALAKSHMI INSTITUTE OF TECHNOLOGY
DEPARTMENT OF HUMANITIES AND SCIENCE
SUBJECT NAME: PROBABILITY AND STATISTICS
SUBJECT CODE:MA3391
UNIT-3
UNIT NAME: ESTIMATION THEORY

12. The time to failure of an electronic component follows an exponential distribution with parameter 𝜆.
Eight units are randomly selected and tested resulting in the following failure time (in hours):
13.03, 6.07, 68.44, 17.11, 32.54, 8.77, 12.14, 23.42
Find the moment estimate of 𝜆.
Ans:

1 𝛼
13. A random variable 𝑋 takes the values 0,1,2 with respective probabilities 2 − 𝜃, 2 + 2(1 − 𝛼)𝜃 and
1−𝛼
( )+ (2𝛼 − 1)𝜃, where 𝛼 and 𝜃 are the parameters. If a sample of size 75 drawn from the population
2
yielded the values 0,1,2 with respective frequencies 27,38,10 respectively, find the estimators of 𝛼 and 𝜃
by the method of moments.
Ans:
 RAJALAKSHMI INSTITUTE OF TECHNOLOGY
DEPARTMENT OF HUMANITIES AND SCIENCE
SUBJECT NAME: PROBABILITY AND STATISTICS
SUBJECT CODE:MA3391
UNIT-3
UNIT NAME: ESTIMATION THEORY

14. Consider a characteristic that occurs in proportion 𝑝 of a population. Let 𝑋1 , 𝑋2 , … , 𝑋𝑛 be a random

sample of size 𝑛 so 𝑃(𝑋𝑖 = 0) = 1 − 𝑝 and 𝑃(𝑋𝑖 = 1) = 𝑝 for 𝑖 = 1,2, … , 𝑛 where 0 ≤ 𝑝 ≤ 1. Obtain
the maximum likelihood estimator of 𝑝.
 RAJALAKSHMI INSTITUTE OF TECHNOLOGY
DEPARTMENT OF HUMANITIES AND SCIENCE
SUBJECT NAME: PROBABILITY AND STATISTICS
SUBJECT CODE:MA3391
UNIT-3
UNIT NAME: ESTIMATION THEORY

Ans:

15. The number of defective hard drives produced daily by a production line can be modeled as a Poisson
distribution. The counts of 10 days are 7,3,1,2,4,1,2,3,1,2. Obtain the maximum likelihood estimate of the
probability of 0 and 1 defectives on one day.
Ans:
 RAJALAKSHMI INSTITUTE OF TECHNOLOGY
DEPARTMENT OF HUMANITIES AND SCIENCE
SUBJECT NAME: PROBABILITY AND STATISTICS
SUBJECT CODE:MA3391
UNIT-3
UNIT NAME: ESTIMATION THEORY

16. For random sampling from a normal population 𝑁(𝜇, 𝜎 2 ), find the maximum likelihood estimators for
(i) 𝜇, when 𝜎 2 is known.
(ii) 𝜎 2 , when 𝜇 is known.
(iii) The simultaneous estimation of 𝜇 and 𝜎 2 .
Ans:
 RAJALAKSHMI INSTITUTE OF TECHNOLOGY
DEPARTMENT OF HUMANITIES AND SCIENCE
SUBJECT NAME: PROBABILITY AND STATISTICS
SUBJECT CODE:MA3391
UNIT-3
UNIT NAME: ESTIMATION THEORY

17. Find the maximum likelihood estimator of 𝜃 in the population with density function 𝑓(𝑥, 𝜃) =
(1 + 𝜃)𝑥 𝜃 ; 0 ≤ 𝑥 ≤ 1; 𝜃 > 0; based on the random sample of size 𝑛. Test whether this estimator is a
sufficient estimator of 𝜃.
Ans:
 RAJALAKSHMI INSTITUTE OF TECHNOLOGY
DEPARTMENT OF HUMANITIES AND SCIENCE
SUBJECT NAME: PROBABILITY AND STATISTICS
SUBJECT CODE:MA3391
UNIT-3
UNIT NAME: ESTIMATION THEORY

18. An industrial engineer intends to use the mean of a random sample of size 𝑛 = 150 to estimate the
average mechanical aptitude (as measured by a certain test) of assembly line workers in a large industry.
If on the basis of experience the engineer can assume that 𝜎 = 6.2 for such that , what can assert with
probability 0.99 about the maximum size of his error?
Ans

19. A research worker wants to determine the average time it takes a mechanic to rotate the tyres of the car
and he wants to be able to assert with 95% confidence that the mean of his sample is of atmost 0.5
minutes. If he can presume from past experience that 𝜎 = 1.6 𝑚𝑖𝑛𝑢𝑡𝑒𝑠 , how large a sample will have to
take?
Ans:
 RAJALAKSHMI INSTITUTE OF TECHNOLOGY
DEPARTMENT OF HUMANITIES AND SCIENCE
SUBJECT NAME: PROBABILITY AND STATISTICS
SUBJECT CODE:MA3391
UNIT-3
UNIT NAME: ESTIMATION THEORY

20. In six determinants of the melting point of an aluminum alloy, a chemist obtained a mean of 532.26
degrees Celsius with a standard deviation of 1.14 degree. If he uses this mean to estimate the actual
melting point of the alloy, what can the chemist assert with 98% confidence about the maximum error?
Ans:

21. In order to introduce some incentive for higher balance in savings accounts a random sample size of 64
savings accounts at a bank’s branch was studied to estimate the average monthly balance in saving bank
accounts. The mean and standard deviation were found to be 𝑅𝑠. 8500 and 𝑅𝑠. 2000 respectively.
Find (i) 90%
(ii)95% and
(iii) 99% confidence intervals for the population mean
Ans:
 RAJALAKSHMI INSTITUTE OF TECHNOLOGY
DEPARTMENT OF HUMANITIES AND SCIENCE
SUBJECT NAME: PROBABILITY AND STATISTICS
SUBJECT CODE:MA3391
UNIT-3
UNIT NAME: ESTIMATION THEORY

22. With reference to the nanopillar height data 𝑛 = 50, 𝑥̅ = 305.58 nm, and 𝑠 2 = 1366.86( hence 𝑠 =
36.97 𝑚𝑚), construct 99% confidence interval for the population mean of all nanopillers.
Ans:
 RAJALAKSHMI INSTITUTE OF TECHNOLOGY
DEPARTMENT OF HUMANITIES AND SCIENCE
SUBJECT NAME: PROBABILITY AND STATISTICS
SUBJECT CODE:MA3391
UNIT-3
UNIT NAME: ESTIMATION THEORY

23. Ten ball bearings made by certain process have a mean diameter of 0.5060 cm with the standard
deviation of 0.0040 𝑐𝑚. Assuming that the data may be taken as a random sample from a normal
population, construct a 95% confidence interval for the actual average diameter of the ball bearings?
Ans:

24. In a certain factory there are two independent processes manufacturing the same item. The average
weight in a sample of 250items produced from one process is found to be 120 𝑂𝑍𝑆 , with the standard
deviation 12 𝑂𝑍𝑆 . While the corresponding figures in a sample of 400 items from the other process are
124 𝑂𝑍𝑆 and 14 𝑂𝑍𝑆 . Find the 99% confidence limits for the difference in the average weight of items
produced by the two processes respectively.
Ans:
 RAJALAKSHMI INSTITUTE OF TECHNOLOGY
DEPARTMENT OF HUMANITIES AND SCIENCE
SUBJECT NAME: PROBABILITY AND STATISTICS
SUBJECT CODE:MA3391
UNIT-3
UNIT NAME: ESTIMATION THEORY

25. In a test given to two groups of students the marks obtained were as follows:
First 18 20 36 50 49 36 34 49 61
group
Second 29 28 26 35 30 44 46
group
Construct a 95% confidence interval on the mean marks secured by students of the above two groups.
Ans:

26. In 16 test runs the gasoline consumption of an experimental engine had a standard deviation of 2.2
gallons. Construct a 99% confidence interval for 𝜎 2 which measures the true variability of the gasoline
consumption of the engine.
Ans:

27. A study has been made to compare the nicotine contents of two brands of cigarettes. Ten cigarettes of
 RAJALAKSHMI INSTITUTE OF TECHNOLOGY
DEPARTMENT OF HUMANITIES AND SCIENCE
SUBJECT NAME: PROBABILITY AND STATISTICS
SUBJECT CODE:MA3391
UNIT-3
UNIT NAME: ESTIMATION THEORY

brand 𝐴 had an average nicotine content of 3.1 milligrams with a standard deviation of 0.5 milligram ,
while eight cigarettes of brand 𝐵 had an average nicotine content of 2.7 milligrams with a standard
deviation of 0.7 milligram. Assuming that the two sets of data are independent random samples from
normal populations with equal variances, construct a 95% confidence interval for the difference between
𝜎2
the mean nicotine contents of the two brands of cigarettes. Find a 98% confidence interval for 𝜎12 .
2
Ans: