LOYOLA COLLEGE (AUTONOMOUS), CHENNAI – 600 034
M.Sc. DEGREE EXAMINATION – STATISTICS
|
SECOND SEMESTER – APRIL 2006
ST 2810 – SAMPLING THEORY
Date & Time : 24-04-2006/9.00-12.00 Dept. No. Max. : 100 Marks
Section A (10 x 2 =20)
Answer ALL the questions. Each carries TWO marks.
- Define : Midzuno sampling design
- State the identity which relates sample size of a sampling design with its first order inclusion probabilities
- Give the formula for unbiased estimator of under Warner’s RR
- Define balanced systematic sampling
- Mention the situations in which product and ratio estimators can be used instead of .
- When do you recommend “Two phase sampling”?
- Name an estimator which uses selection probabilities.
- Give any two limitations of “Linear Systematic Sampling “
- Name any one sampling-estimating strategy in which no unbiased estimator for variance of estimator can be found.
- Write the variance of Yates corrected estimator under LSS when there is a linear trend in the population
Section B (5 x 8 = 40)
Answer any Five. Each carries Eight marks.
- Prove the following identities : and verify the same in the case of following sampling design
- From a population containing N units a sample of n units is drawn using SRS and from the drawn sample a subsample of n’ units. Suggest an unbiased estimator for the population total based on the subsample and obtain its variance
- Describe modified systematic sampling and show that under the model
- Describe Desraj ordered estimator and obtain an unbiased estimator of
- Explain proportional allocations (1) for a given cost (2) for a given sample size. Derive the variance of under the above cases assuming simple random sampling is used in all strata.
- Explain Warner’s randomized response model in detail.
- Define product estimator . Obtain an expression for its bias under simple random sampling and hence develop an unbiased estimator for the population total.
- Derive the approximate mean square error of estimators in the class also obtain the minimum mean square error in the class.
Section C (2 x 20 =40)
Answer any TWO. Each carries TWENTY marks
- Define : Horvitz-Thompson estimator. Show that it is unbiased for the population total and derive its variance in Yates-Grundy form
- Derive the first and second order inclusion probabilities under Midzuno sampling scheme and show that under this design the Yates-Grundy estimator is non-negative
- Develop Yates corrected estimator under Linear Systematic Samping
- Develop Hartley-Ross ratio type unbiased estimator under simple random sampling.
Latest Govt Job & Exam Updates: