National Institute of Technology Rourkela

End-Semester Examination
Session 2017-2018 (Spring)

Sub. Code: MA 324 Subject Name: Probability Department Code: MA

No. of Pages: 1 Full Marks: 50 Duration: 180 Minutes
• Answer all the questions. Figures at the right hand margin indicate marks.
• Marks will not be awarded without proper justification in support of your answers.

Q1. Let X1 , X2 , . . . , Xn be independent and identically distributed N (µ, σ 2 ) random variables.

∑n Then,
show that X and (X1 − X, X2 − X, . . . , Xn − X) are independent, where X = n−1 i=1 Xi . [5]
Q2. A company sells toasters along with a warranty for one year against all repairs. It has been estimated
that the probability of no repairs in the first year is 95%. In the case of repairs, it has been found
that the total payout in a year is distributed as an exponential with mean of $15. Obtain the
distribution function of the payout under the warranty. Also, find its expectation and variance. [5]
Q3. (i) State and prove weak law of large numbers.
(ii) Let X1 , X2 , . . . be a sequence of independent identically distributed random variables following
Binomial(1, p). Using weak law of large numbers, show that X converges to p in probability as n
tends to ∞. [5]
Q4. (i) Let X be uniformly distributed over (1, 4). Use Markov’s inequality to estimate P (X ≥ a),
where 1 ≤ a ≤ 4 and compare your estimate with exact answer. (Take any five values of a in the
given interval).
(ii) Find the value of a ∈ (1, 4) that minimizes the difference between the bound and the exact
probability computed in (i). [3+2]
Q5. Let X1 , X2 , . . . , Xn be a random sample drawn from a distribution with cumulative distribution
function
∫ x
F (x) = (B(p, q))−1 tp−1 (1 − t)q−1 dt, 0 ≤ x ≤ 1, p, q > 0,
0
where B(., .) is the beta function. Then, obtain method of moments estimators of the unknown
parameters p and q. [5]
Q6. Let X1 , X2 , X3 be independent identically distributed random variables with common probability
density function
√
f (x) = ( 2π)−1 e−x /2 , − ∞ < x < ∞.
2

√ √ √
Further, let Y1 = (X1 − X2 )/ 2, Y2 = (X1 + X2 − 2X3 )/ 6 and Y3 = (X1 + X2 + X3 )/ 3. Then,
obtain the joint probability density function of Y1 , Y2 and Y3 . [5]
 ∑ 
 n 
Q7. Let X1 , X2 , . . . , Xn be a random sample from a N (0, 1) population. Define Y1 =  n1 i=1 Xi , Y2 =
∑n
i=1 |Xi |. Calculate E(Y1 ) and E(Y2 ), and establish the inequality between them.
1
n [5]
Q8. Derive moment generating function of a normal distribution with mean µ and variance σ 2 . Hence
obtain the mean and variance of this distribution. [5]
Q9. The blood type distribution in the Odisha state is type A, 41%; type B, 9%; type AB, 4% and
the type O, 46%. It is estimated that during an accident, 4% of inductees with type O blood were
typed as having type as A; 88% of those with type A were correctly typed ; 4% with type B blood
were typed as A; and 10% with type AB were typed as A. A person was wounded and brought to
surgery. He was typed as having type A blood. What is the probability that this is his true blood
type? [5]
Q10. Let X1 , X2 , . . . , Xn be independent identically distributed N (µ, σ 2 ) random variables. If S 2 is the
sample variance, then show that S 2 is unbiased and consistent of σ 2 . Is S an unbiased estimator of
σ? Give explanation. [5]

—————————–
Best of luck!