LAISHA
Open Laisha

ICAR AICE-JRF/SRF Sampling Theory I: Simple, Stratified, Systematic, Ratio & Regression Estimation: practice questions

ICAR AICE-JRF/SRF - Agricultural Statistics, Computer Application, Bioinformatics (PhD admission and fellowship) · India · National Testing Agency for ICAR

Original practice questions written to the published syllabus · not past papers
10worked here, free
70written to this exam in this subject
10syllabus units

About ICAR AICE-JRF/SRF

ICAR AICE-JRF/SRF - Agricultural Statistics, Computer Application, Bioinformatics (PhD admission and fellowship) is a PhD, fellowship and lectureship exam run by National Testing Agency for ICAR, for candidates in India. Computer-based test, 2 hours, 120 MCQs, +4 / -1 (Part A general, Part B core group, Part C subject). 2026 exam held with AIEEA-PG in July 2026.

Source: icar.org.in.

Checked against the exam body's published information. Formats and fees change; confirm the current edition there before you book.

Sampling Theory I: Simple, Stratified, Systematic, Ratio & Regression Estimation in ICAR AICE-JRF/SRF

Sampling versus complete enumeration, probability sampling, SRS, stratified sampling with allocation, choice and construction of strata and collapsing of strata, ratio and regression estimation and systematic sampling: estimator properties, variance formulas and efficiency conditions.

Probability sampling from first principles: sampling versus complete enumeration, simple random sampling with and without replacement, stratification and allocation, systematic sampling, and the ratio and regression estimators that use auxiliary information such as last year's area.

Our 70 ICAR AICE-JRF/SRF questions in this subject: 5 easy, 39 medium, 26 hard, across 10 units.

10 practice questions, worked

Choose an answer, then open the working. Each explanation says why the right answer is right and why the others are not.

These 10 were written to ICAR AICE-JRF/SRF and are not shown on any other exam's page.

Question 1 · medium

Milk yield per animal has a coefficient of variation of 40%. How many animals must be sampled (fpc ignored) to estimate the mean within 5% of its value with 95% confidence (z = 1.96)?

  1. 615
  2. 16
  3. 246
  4. 64
Answer and working

C. 246

n0 = z^2 C^2 / r^2 = 3.8416 x 0.16 / 0.0025 = 245.86, rounded up to 246. Dropping z^2 gives 64; taking square roots throughout gives 16; not squaring C gives 615.

Question 2 · medium

Under optimum allocation with costs, a stratum receives a larger sample when it is:

  1. Smaller, less variable or dearer to enumerate
  2. Smaller, more variable or cheaper to enumerate
  3. Larger, less variable or dearer to enumerate
  4. Larger, more variable or cheaper to enumerate
Answer and working

D. Larger, more variable or cheaper to enumerate

n_h is proportional to N_h S_h / sqrt(c_h): it rises with stratum size and standard deviation and falls with the cost per unit.

Question 3 · medium

Why are strata sometimes collapsed in pairs at the analysis stage?

  1. One unit per stratum leaves no within-stratum variance estimate
  2. Collapsing always gives an unbiased and smaller variance estimate
  3. Collapsing removes the bias of the stratified estimator of the mean
  4. Collapsing is required whenever Neyman allocation has been used
Answer and working

A. One unit per stratum leaves no within-stratum variance estimate

With a single unit per stratum, s_h^2 cannot be computed; pairing similar strata lets the variance be estimated from differences within pairs. The resulting estimate is conservative, not unbiased.

Question 4 · medium

Under which model is the ratio estimator the best linear unbiased estimator?

  1. A curved relation between y and x with variance proportional to x^2
  2. No relation at all between y and x, with constant variance of y
  3. A line with a large intercept and constant variance of y about it
  4. A line through the origin with the variance of y proportional to x
Answer and working

D. A line through the origin with the variance of y proportional to x

The ratio estimator is BLUE when E(y) = beta x and V(y) is proportional to x, a model that often suits crop production against area. With a large intercept the regression estimator is better; with no relation the simple mean is.

Question 5 · medium

For an SRS of 20 (fpc negligible) with S_y^2 = 80 and correlation rho = 0.75 between y and x, what is the approximate variance of the regression estimator of the mean?

  1. 2.250
  2. 4.000
  3. 1.000
  4. 1.750
Answer and working

D. 1.750

V(y-bar_lr) = S_y^2 (1 - rho^2) / n = 80 x (1 - 0.5625) / 20 = 1.750. Without the adjustment it is 4.000; using 1 - rho gives 1.000; rho^2 instead of 1 - rho^2 gives 2.250.

Question 6 · medium

For an SRS of 20 (fpc negligible) with S_y^2 = 80 and correlation rho = 0.75 between y and x, what is the approximate variance of the regression estimator of the mean?

  1. 2.250
  2. 4.000
  3. 1.000
  4. 1.750
Answer and working

D. 1.750

V(y-bar_lr) = S_y^2 (1 - rho^2) / n = 80 x (1 - 0.5625) / 20 = 1.750. Without the adjustment it is 4.000; using 1 - rho gives 1.000; rho^2 instead of 1 - rho^2 gives 2.250.

Question 7 · hard

How is the variance of the regression estimator estimated from an SRS of n units?

  1. [(1 - f)/n] times the residual sum of squares divided by n - 2
  2. [(1 - f)/n] times the total sum of squares of y divided by n - 1
  3. [(1 - f)/n] times the residual sum of squares divided by n + 2
  4. [(1 - f)/n] times the regression sum of squares divided by n - 2
Answer and working

A. [(1 - f)/n] times the residual sum of squares divided by n - 2

The residual mean square, sum of squared residuals over n - 2 (two parameters estimated), estimates S_y^2(1 - rho^2). The total SS over n - 1 estimates S_y^2 and ignores the regression; the regression SS is the explained part.

Question 8 · medium

What do calibration and GREG estimators used by statistical offices generalise?

  1. Regression estimation with several auxiliary variables of known totals
  2. Systematic sampling with several random starts in each stratum
  3. Ratio estimation in which the auxiliary total is itself estimated
  4. Collapsing of strata when one unit is drawn from each stratum
Answer and working

A. Regression estimation with several auxiliary variables of known totals

Calibration adjusts weights so that weighted sample totals of auxiliaries match known population totals; GREG is the corresponding generalised regression estimator.

Question 9 · medium

For the difference estimator y-bar + k(X-bar - x-bar), the population covariance S_yx = 36 and S_x^2 = 24. What value of k minimises the variance?

  1. 7.35
  2. 0.67
  3. 1.00
  4. 1.50
Answer and working

D. 1.50

V is minimised at k = S_yx / S_x^2 = 36/24 = 1.50, the population regression coefficient; the minimum equals the regression estimator's variance. k = 1 is a convenient choice, not the optimum here.

Question 10 · medium

Which statement about the product estimator y-bar x-bar / X-bar is correct?

  1. It is useful only when y and x are positively correlated
  2. It is exactly unbiased under simple random sampling
  3. Biased, with first-order bias proportional to S_yx / X-bar
  4. It is biased, with bias that does not depend on S_yx at all
Answer and working

C. Biased, with first-order bias proportional to S_yx / X-bar

E(y-bar x-bar) = Y-bar X-bar + Cov(y-bar, x-bar), so the bias is Cov(y-bar, x-bar)/X-bar = [(1 - f)/n] S_yx / X-bar. It is meant for negative correlation, where it reduces variance.

A study plan for Sampling Theory I: Simple, Stratified, Systematic, Ratio & Regression Estimation in ICAR AICE-JRF/SRF

This plan follows where our questions actually fall, so the time goes where the marks are likely to be. It is our reading of the syllabus, not the exam body's weighting.

  1. First, the heavy units (56% of the 70 questions): Stratified sampling: estimation and allocation (proportional, Neyman, optimum) (11, 16%); Choice of strata, construction of strata boundaries and collapsing of strata (10, 14%); Ratio estimators: bias, MSE and comparison (9, 13%); Regression estimators (9, 13%).

    Read the manual chapters for these first and do every worked question you can find on them.

  2. Then the middle band: Product and difference estimators (8, 11%); Systematic sampling and its variants (7, 10%); Estimation of proportions and sample-size determination (5, 7%); Sampling versus complete enumeration; sampling and non-sampling errors (5, 7%).

    Aim for one sitting per unit, then mixed questions across them.

  3. Then the lighter units: Probability sampling, sampling frames and inclusion probabilities (3, 4%); Simple random sampling with and without replacement (3, 4%).

    Learn the definitions, classifications and standard numbers; these units are more often recalled than worked.

  4. Leave time for the hard ones: Probability sampling, sampling frames and inclusion probabilities (2 hard of 3), Stratified sampling: estimation and allocation (proportional, Neyman, optimum) (6 hard of 11), Choice of strata, construction of strata boundaries and collapsing of strata (5 hard of 10).

    Come back to these after a first pass, untimed, and read every explanation, including for the options you rejected.

  5. Bank the easy marks: Sampling versus complete enumeration; sampling and non-sampling errors (1 easy of 5); Product and difference estimators (1 easy of 8).

    Do these early in revision so they are fast on the day.

  6. Finish timed. Sit the subject as a timed set without notes, mark it, and send each wrong answer back to its unit above.

Last updated · How Laisha writes and checks its pages · Report a mistake

Ask Laisha about this

Opens Laisha's chat with your question ready to send. Sign in or start free.

Unlock every question — ICAR AICE-JRF/SRF Sampling Theory I: Simple, Stratified, Systematic, Ratio & Regression Es

US$10 a month · one price worldwide · cancel any time

  • Every practice question in this subject, with full working
  • Timed exam papers and progress by unit
  • Ask Laisha to explain any answer — up to 1,000 questions a month
Free or Smarter
FreeSmarter
Grow guides, pest pages, articlesRead allRead all
Ask Laisha5 a dayUp to 1,000 a month
Exam practiceThe sample on each pageEvery question, timed papers
Crop calendar and pest alerts—For your own fields
Calculators and tools—All
Uploads and reports—100 a month, real files
10 days free for every new account, no card.