LOYOLA COLLEGE (AUTONOMOUS), CHENNAI – 600 034
M.Sc. DEGREE EXAMINATION – STATISTICS
|
FOURTH SEMESTER – APRIL 2006
ST 4804 – STATISTICS FOR COMPETITIVE EXAMINATIONS
Date & Time : 25-04-2006/9.00-12.00 Dept. No. Max. : 100 Marks
SECTION A
Answer ALL the Questions (40 ´1 = 40 Marks)
- If the difference between two numbers is 1.2, then the variance of them is
(A) 0.18 (B) 1.44 (C) 0.72 (D) 0.36
- To test the hypothesis that the variance of a normal distribution is 2, the test procedure used is
(A) Normal test (B) Chi-square test (C) F-test (D) t-test
- To test which one of the following hypothesis, F-test is used?
(A) Goodness of fit (B) equality of means of two normal populations
(C) Significance of correlation coefficient (D) Equality of Variances of two normal populations
- If X has Poisson distribution with 3P[X = 2] = 2P[X ≤ 1], then the expected value of X is
(A) 3 (B) -2/3 (C) 2 (D) 3/2
- X1, X2 and X3 are independent observations on a normal random variable with
mean μ and variance σ2.What is the efficiency of (3X1+2X2+X3 ) / 6 as an estimator of μ ?
(A) 6/7 (B) 1 (C) 1/3 (D) 1/12
- If E(Y/X) = α X + β and X has standard normal distribution, then E(Y) is
(A) 0 (B) 1 (C) β (D) α
∞
- If P ( An) = 1, n=1, 2, 3… then the value of P (An) is
n=1
(A) 0 (B) 1 (C) 1/2 (D) ¼
- A random variable X has characteristic function
Φ (t) = (sin t)/t, t ≠0
1 otherwise
Then, Var(X) is equal to
(A) 1 (B) 0 (C) 1/6 (D) 1/3
- If X1 and X2 are independent and identically distributed random variables with p(x) = qx.p, x = 0, 1, 2, 3… and (p+q) = 1, then the distribution of (X1+X2) is
(A) Geometric (B) degenerate (C) Negative Binomial (D) Hyper- geometric
- In a random sample of size n from the distribution
dF (x) = e-x.dx, 0<x<∞,
the mean of the smallest sample value is
(A) 1/n (B) 1/n2 (C) 0 (D) 1
- If the degrees of freedom for error in the analysis of Variance for a Latin square design is 30, the number of treatments is
(A) 5 (B) 6 (C) 7 (D) not possible to determine
- If a population consists of 10 units and the population Variance is 20, the Variance of the sample mean of a simple random sample pf size 4 without replacement is
(A) 5 (B) 2 (C) 20 (D) 3
- The number of simple random samples of size 4 that can be drawn without replacement from a population with 12 units is
(A) 124 (B) 495 (C) 11,880 (D) 48
- The standard deviation of a symmetric distribution is 4. The value of the fourth moment about the mean in order that the distribution be leptokurtic is
(A) greater than 768 (B) equal to 768 (C) equal to 256 (D) less than 48
- Given Maximize subject to
For what values of the above problem will have several optimum solutions?
(A) 2 (B) 3 (C) 6 (D) 1
- The objective function in the phase-I (when we use two phase simplex method) is formed by
- summing all the variables
- summing all the artificial variables
(C) taking the product of artificial variables
- subtracting the sum of artificial variables from the sum of other variables
- The following set of constraints require x artificial variables
where x is
(A) 0 (B) 1 (C) 2 (D) 3
- Given the following simplex table (associated with a maximization problem)
Basic z x1 x2 x3 x4 Solution
z 1 -4 -2 0 0 8
x3 0 4 3 1 0 1
x4 0 -1 1 0 1 2
The leaving and entering variables are
(A) x1, x3 (B) x1, x4 (C) x2,x3 (D) x2,x4
- An LPP has 4 variables and 2 constraints. How many sets of basic variables are possible?
(A) 10 (B) 6 (C) 3 (D) 20
- The power function associated with the UMPT for testing against the alternative in is always
(A) Strictly increasing in (B) Strictly decreasing
(C) Periodic in (D) can’t say
- Which of the following is the form of UMPT for testing against the
alternative in
(A) (B)
(C) (D)
- Choose the correct statement
(A) Power functions of UMPTs are always monotone
(B) A UMPT is always UMPUT
(C) MPT’s are not unique
(É)All similar tests will have Neyman structure
- Choose the correct statement
(A) RR methods are not associated with sensitive attributes
(B)Yates Grundy estimator is non-negative under Midzuno scheme
(C) HTE can not be used under PPSWOR
(D)Balanced systematic sampling is not recommended for populations with linear
trend.
- Lahiri’s method
(A) is a PPS selection method involving a given number of attempts
(B) is a PPS selection method involving unknown number of attempts
(C) is an equal probability selection method involving a given number of attempts
(D) is an equal probability selection method involving unknown number of
attempts
- Ratio estimator is
(A) a particular case of regression estimator
(B) an unbiased estimator
(C)more suitable when y and x have high negative correlation
(D) more suitable when y and x have no correlation
- Random group method is due to
(A) Desraj (B) Murthy (C) Hartley-Ross (D) Rao-Hartley-Cochran
- Randomised response methods are meant for
(A) homogeneous data
(B) heterogeneous data
(C) sensitive data
(D) stratified populations
- Which name is associated with shortest route problems
(A) Kuhn-Tucker
(B) Floyd
(C) Charnes
(D) Karmakar
- Which of the following functions is NOT continuous at 0?
(A) |x| (B) ex (C) x – [x] (D)Sin x
- A tosses a fair coin twice and B throws a fair die twice. Let
a = Probability of getting at least two heads
b = Probability that the sum of the numbers that show up is less than 6
Then
(A) a > b (B) a < b (C) a = b (D) a + b > 1
31.The system of equations
2x + 4y – z = 3
x + 2y +2z = 2
x + (m2+1) y + 7z = 4m – 1
has infinitely many solutions if m equals
(A)0 (B) – 1 (C) 1 (D)2
- The mean and variance of 8 items are 10 and 100 respectively. An observation 3
is deleted from the data. The variance of the remaining 7 observations is
(A)100 (B)106 (C)112 (D)120
- Let T: R3 ® R2 be defined as T(x, y, z) = (3x + y – z , x + 5z). The matrix
corresponding to this linear transformation is
(A) (B) (C) (D)
- Which of the following is NOT true of a normal variable with mean 0?
(A) E(X2) = 1, E(X3) = 0 (B) E(X2) = 1, E(X4) = 2
(C) E(X2) = 2, E(X4) = 12 (D) E(X2) = 1/2 , E(X4) = 3/4
- If X and Y are uncorrelated random variables with equal means and variances,
then
(A) X + Y and X – Y are identically distributed
(B) X + Y and X – Y are independent
(C) X + Y and X – Y are negatively correlated
(D) X + Y and X – Y have equal variance
- In a bivariate dataset {(Xi, Yi), i =1, 2, …,n}, X assumed only two values namely 0 and – 1 and the correlation coefficient was found to be –0.3. Then , the correlation coefficient for the transformed data {(Ui, Vi), i =1, 2, …,n}, where Ui = 3 – 5 Xi2 and Vi = 2Yi –3 is
(A) –0.3 (B) 0.3 (C) 0 (D) cannot be determined
- If X1, X2,…, Xn is a random sample from U( 0, q), which of the following is a biased estimator of q?
(A) 2 (B) X(n) (C)X1 + Xn (D) (n+1)X(n) / n
- The Cramer-Rao lower bound for estimating the parameter l of a Poisson distribution based on a random sample of size n is
(A) l (B) nl (C) l / n (D) l1/2
- The lower control limit of a c-chart is 4. The upper control limit is
(A)16 (B)20 (C)24 (D) none of these
- In a 24 factorial experiment with 4 blocks the degree of freedom for Error Sum of Squares is
(A) 25 (B)35 (C)45 (D)55
SECTION B
Answer any SIX questions (6 X 10 = 60 Marks)
- Explain the procedure for solving a game theory problem graphically
- Show that family of Uniform densities binomial densities has
MLR in
- A sample has two strata with relative sizes and . He believes
that . For a given cost , show that (assuming stratum
sizes are large)
- The exponent of a bivariate normal density is given below:
– ⅔(x2+9y2-13x-3xy+60y+103)
Find μ1, μ2, σ1, σ2 and ρ.
- The number of accidents in a town follows a Poisson process with the mean of 2
accidents per day and the number of people involved in ith accident has the
distribution
P[X1=k] = 1/ 2k, k≥1.
Find the mean and variance of the number of people involved in accidents per
week.
- If Φ is a characteristic function, show that e λ (Φ -1) is a characteristic function for
all λ>0.
- (a)Let X1, …,Xn, Xn+1 be a random sample from N(m, s2). Let M be the average of the first ‘n’ observations and S2 be the unbiased estimator of the population variance based on the first ‘n’ observations. Find the constant ‘k’ so that the statistic k( M – Xn+1) /S follows a t- distribution.
(b) Let X have a Poisson distribution with parameter q. Assume that the
unknown q is a value of a random variable which follows Gamma distribution
with parameters a = a / ( 1- a) and p = r, where ‘r’ is a positive integer. Show
that the marginal distribution of X is Negative Binomial. (5 + 5)
- (a) Let X1,…,Xn be a random sample from Poisson distribution with parameter l. Starting with the initial estimator X12 – X1 for l2, use Rao-Blackwellization to get an improved estimator by conditioning on the sufficient statistic S Xi. State whether the resulting estimator is UMVUE and justify.
(b) Let X1, …, Xn be a random sample from N(m, s2). Obtain an unbiased and
consistent estimator of s4. (6 + 4)
- (a) Derive an expression for E(Mean Treatment Sum of Squares) in LSD.
(b) Consider four quantities T1, …,T4 and let T1 – 2T2 + T3 be a contrast. Find
two other contrasts so that all the three are mutually orthogonal. (7 + 3)