LAISHA
Open Laisha

ICAR AICE-JRF/SRF Statistical Inference II: Testing of Hypotheses & Sequential Analysis: 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
44written to this exam in this subject
11syllabus 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.

Statistical Inference II: Testing of Hypotheses & Sequential Analysis in ICAR AICE-JRF/SRF

Neyman-Pearson lemma, UMP and likelihood-ratio tests, the standard tests, and Wald's SPRT with OC and ASN functions; numerical boundaries and statements of conditions.

The logic and optimality of tests: errors and power, the Neyman-Pearson lemma, uniformly most powerful and unbiased tests, likelihood-ratio tests and their large-sample forms, and Wald's sequential probability ratio test.

Our 44 ICAR AICE-JRF/SRF questions in this subject: 8 easy, 18 medium, 18 hard, across 11 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 · easy

For simple H₀: θ = θ₀ against simple H₁: θ = θ₁, what form does the most powerful test of size α take?

  1. Reject H₀ when the p-value of a two-sided z-test is below α
  2. Reject H₀ when L(θ₀; x)/L(θ₁; x) > k, with k fixed by the size
  3. Reject H₀ when L(θ₁; x)/L(θ₀; x) > k, with k fixed by the size
  4. Reject H₀ when the MLE of θ is closer to θ₁ than to θ₀
Answer and working

C. Reject H₀ when L(θ₁; x)/L(θ₀; x) > k, with k fixed by the size

Neyman-Pearson lemma: put into the critical region the points with the largest ratio of likelihoods under H₁ to H₀, until the size reaches α. The inverted ratio would reject points that favour H₀.

Question 2 · medium

Under a monotone likelihood ratio in T, what does the Karlin-Rubin theorem give for H₀: θ ≤ θ₀ against H₁: θ > θ₀?

  1. A UMP level-α test that rejects for small T
  2. An LRT that is UMP only as n becomes large
  3. A UMPU test, though no UMP test exists here
  4. A UMP level-α test that rejects for large T
Answer and working

D. A UMP level-α test that rejects for large T

Karlin-Rubin: rejecting when T > c with P_θ₀(T > c) = α is UMP for the one-sided problem, and its power function is non-decreasing in θ.

Question 3 · medium

Which optimality property does the one-way analysis-of-variance F-test have under normal errors?

  1. It is UMPU among all tests of equal treatment means
  2. It is the score test, and it is exact only for balanced data
  3. It is UMP among all tests of equal treatment means
  4. It is UMP among tests invariant under the natural group of transformations
Answer and working

D. It is UMP among tests invariant under the natural group of transformations

The F-test is UMP invariant (and is also the likelihood-ratio test); it is not UMPU in general. It is exact under normality for balanced and unbalanced one-way data.

Question 4 · easy

An F₂ population of 400 plants gives 290 tall and 110 dwarf. What is the χ² statistic for a 3:1 segregation ratio?

  1. 0.500
  2. 0.333
  3. 0.133
  4. 1.333
Answer and working

D. 1.333

Expected 300 and 100. χ² = 10²/300 + 10²/100 = 0.333 + 1.000 = 1.333, with 1 df; well below 3.841, so the 3:1 ratio is not rejected. Using only the tall class gives 0.333.

Question 5 · medium

Two one-sided tests (TOST) at level 0.05 are used to show that a new variety's yield is within ±Δ of a reference. Which confidence-interval statement is equivalent?

  1. The 95% confidence interval for the difference contains zero
  2. The 90% confidence interval for the difference lies entirely inside (−Δ, Δ)
  3. The 95% confidence interval for the difference lies entirely inside (−Δ, Δ)
  4. The 90% confidence interval for the difference contains both −Δ and Δ
Answer and working

B. The 90% confidence interval for the difference lies entirely inside (−Δ, Δ)

Each one-sided test at α corresponds to a one-sided 1 − α bound; together they give the 1 − 2α = 90% interval. A 95% interval containing zero only shows that a difference was not detected.

Question 6 · medium

Why can a Wald confidence interval and a score test for the same proportion disagree about whether p₀ is plausible?

  1. They invert different tests, with standard errors evaluated at p̂ and at p₀
  2. The score test uses the t distribution while the Wald interval uses z
  3. The score test is one-sided while every confidence interval is two-sided by definition
  4. Confidence intervals and tests can never be made to agree in principle
Answer and working

A. They invert different tests, with standard errors evaluated at p̂ and at p₀

A test and an interval correspond only when one is the inversion of the other. The Wald interval inverts the Wald test (SE at p̂); the score test uses the SE at p₀; near 0 or 1 they can disagree.

Question 7 · medium

In Wald's SPRT with boundaries B < 1 < A on the likelihood ratio Λₙ = L₁/L₀, what is the rule after n observations?

  1. Reject H₀ if Λₙ ≤ B, accept H₀ if Λₙ ≥ A, otherwise take another observation
  2. Accept H₀ if Λₙ ≤ A, otherwise reject H₀, after a fixed number of steps
  3. Accept H₀ if Λₙ ≤ B, reject H₀ if Λₙ ≥ A, otherwise take another observation
  4. Reject H₀ if B < Λₙ < A, otherwise stop sampling and accept H₀
Answer and working

C. Accept H₀ if Λₙ ≤ B, reject H₀ if Λₙ ≥ A, otherwise take another observation

Λₙ large favours H₁ (reject H₀); small favours H₀. Sampling continues while the ratio stays between the boundaries.

Question 8 · medium

Where is the average sample number (ASN) of an SPRT largest?

  1. It is the same at every θ, because the boundaries are fixed
  2. At θ₀, because the test is designed to accept H₀ quickly there
  3. Far beyond θ₁, because large effects need more data to confirm
  4. At parameter values between θ₀ and θ₁, where evidence accumulates slowly
Answer and working

D. At parameter values between θ₀ and θ₁, where evidence accumulates slowly

Between the two hypotheses E_θ(Z) is near zero, so the random walk drifts slowly and takes longest to hit a boundary. Far from both values decisions are quick.

Question 9 · hard

A sequential plan tests p₀ = 0.10 against p₁ = 0.30 infested plants with α = 0.05 and β = 0.10. The spray (reject H₀) line is d = h₁ + sn with s = 0.186. What is h₁?

  1. 2.141
  2. 1.668
  3. 2.631
  4. 2.890
Answer and working

A. 2.141

h₁ = log A/[log(p₁/p₀) + log((1 − p₀)/(1 − p₁))] = 2.8904/1.3499 = 2.141. 1.668 is the magnitude of the acceptance intercept h₀ = log B/(...); 2.890 forgets to divide.

Question 10 · hard

For the SPRT of μ₀ = 0 against μ₁ = 1 with N(μ, 1) data, α = 0.05 and β = 0.10, E₀(Z) = −1/2. Using Wald's approximation, what is the average sample number under H₀?

  1. 3.99
  2. 9
  3. 1.99
  4. 4.50
Answer and working

A. 3.99

E₀(N) ≈ [(1 − α)log B + α log A]/E₀(Z) = [0.95(−2.251) + 0.05(2.890)]/(−0.5) = 3.99. The fixed-sample one-sided test with the same α and β needs (1.645 + 1.282)² = 8.56, i.e. 9 observations; 4.50 ignores the chance of rejecting.

A study plan for Statistical Inference II: Testing of Hypotheses & Sequential Analysis 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 (64% of the 44 questions): Sequential probability ratio test: OC and ASN functions (10, 23%); Unbiased tests and UMPU tests for exponential families (7, 16%); Monotone likelihood ratio and uniformly most powerful tests (6, 14%); Relation between tests and confidence intervals (5, 11%).

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

  2. Then the middle band: Wald and score (Rao) tests (5, 11%); Likelihood ratio tests and Wilks' theorem (3, 7%); Hypotheses, the two types of error, size and power (2, 5%); Multiple testing: family-wise error rate and false discovery rate (2, 5%).

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

  3. Then the lighter units: Neyman-Pearson lemma and most powerful tests (2, 5%); Power and sample-size calculation for common tests (1, 2%); Tests based on Z, t, chi-square and F distributions (1, 2%).

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

  4. Leave time for the hard ones: Likelihood ratio tests and Wilks' theorem (2 hard of 3), Wald and score (Rao) tests (3 hard of 5), Unbiased tests and UMPU tests for exponential families (4 hard of 7).

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

  5. Bank the easy marks: Tests based on Z, t, chi-square and F distributions (1 easy of 1); Neyman-Pearson lemma and most powerful tests (1 easy of 2).

    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 Statistical Inference II: Testing of Hypotheses & Sequential Analysis

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.