LAISHA
Open Laisha

Indian Statistical Institute admission tests Statistical Inference II: Testing of Hypotheses & Sequential Analysis: practice questions

Indian Statistical Institute admission tests (BStat, MStat, JRF in Statistics) · India · Indian Statistical Institute

Original practice questions written to the published syllabus · not past papers
10worked here, free
50written to this exam in this subject
11syllabus units

About Indian Statistical Institute admission tests

Indian Statistical Institute admission tests (BStat, MStat, JRF in Statistics) is a postgraduate admission exam run by Indian Statistical Institute, for candidates in India. Written tests in two parts: an objective mathematics/statistics test and a descriptive subject test, followed by interview for some programmes (reported). JRF selection by written test and interview.

Official site: isical.ac.in.

We have not been able to confirm these details against the exam body's own specification, so fees, dates and pass marks are left out on purpose. Check the current format, eligibility, fees and dates on the official site.

Statistical Inference II: Testing of Hypotheses & Sequential Analysis in Indian Statistical Institute admission tests

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 50 Indian Statistical Institute admission tests questions in this subject: 18 easy, 27 medium, 5 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 Indian Statistical Institute admission tests and are not shown on any other exam's page.

Question 1 · medium

H₀ is composite, θ ∈ Θ₀. How is the size of a test with power function π(θ) defined?

  1. inf over θ ∈ Θ₀ of π(θ)
  2. sup over θ ∈ Θ₀ of π(θ)
  3. π(θ) averaged over θ ∈ Θ₀
  4. inf over θ ∉ Θ₀ of π(θ)
Answer and working

B. sup over θ ∈ Θ₀ of π(θ)

The size is the largest Type I error probability over the null set; a test is of level α when its size is at most α. The infimum over the alternative relates to the worst-case power, not the size.

Question 2 · medium

Ten seeds are tested and H₀: p = 0.5 is rejected in favour of p > 0.5 if 9 or more germinate. What is the size of the test?

  1. 0.0500
  2. 0.0107
  3. 0.0098
  4. 0.0547
Answer and working

B. 0.0107

P(X ≥ 9 | p = 0.5) = (10 + 1)/1024 = 0.0107. 0.0098 counts only X = 9; 0.0547 is the size of the rule X ≥ 8. With discrete data the size cannot be exactly 0.05 without randomisation.

Question 3 · medium

Why is the size of a Karlin-Rubin UMP test of H₀: θ ≤ θ₀ attained at θ = θ₀?

  1. Its power function is non-decreasing in θ, so the largest null rejection probability is at θ₀
  2. Its size is defined only at θ₀, so other null values are ignored
  3. Its power function is decreasing in θ, so the largest value is at the smallest θ
  4. Its power function is constant over the whole null set, so every null value gives the same size
Answer and working

A. Its power function is non-decreasing in θ, so the largest null rejection probability is at θ₀

Under MLR the one-sided test's power function increases with θ; so sup over θ ≤ θ₀ of π(θ) = π(θ₀) = α.

Question 4 · medium

The one-sided test 'reject H₀: μ = μ₀ when Z > z_α' is used against the two-sided alternative μ ≠ μ₀. Why is this test biased?

  1. For μ > μ₀ its power falls below α
  2. Its power is exactly α everywhere
  3. Its size exceeds α at μ = μ₀
  4. For μ < μ₀ its power falls below α
Answer and working

D. For μ < μ₀ its power falls below α

As μ decreases below μ₀, P(Z > z_α) drops below α: the test is less likely to reject when μ < μ₀ than when H₀ is true.

Question 5 · easy

For N(μ, σ²) with both parameters unknown, what are the asymptotic degrees of freedom of −2 log Λ for H₀: μ = μ₀?

  1. 1
  2. n − 1
  3. 0
  4. 2
Answer and working

A. 1

The full model has 2 free parameters and H₀ leaves 1 (σ²), so r = 1 restriction and −2 log Λ ~ χ²₁ approximately. Here the LRT is in fact the exact two-sided t-test.

Question 6 · hard

Which drawback is specific to the Wald test among the three asymptotic likelihood tests?

  1. It needs the model to be refitted under H₀ every time
  2. It has a different asymptotic null distribution from the others
  3. It cannot be used for more than one parameter at a time
  4. It is not invariant to reparameterisation of θ
Answer and working

D. It is not invariant to reparameterisation of θ

Testing θ = 1 and log θ = 0 by Wald can give different statistics, because the standard error is computed on the chosen scale. The LRT is invariant; all three are asymptotically χ² under H₀ and all extend to several parameters.

Question 7 · medium

In 100 trials there are 60 successes. For H₀: p = 0.5, what are the score and Wald z-statistics?

  1. Score 4.00, Wald 4.17
  2. Score 2.00, Wald 2.00
  3. Score 2.04, Wald 2.00
  4. Score 2.00, Wald 2.04
Answer and working

D. Score 2.00, Wald 2.04

Score uses the null SE √(0.5 × 0.5/100) = 0.05: z = 0.1/0.05 = 2.00. Wald uses √(0.6 × 0.4/100) = 0.0490: z = 2.04. Squared values 4.00 and 4.17 are the χ²₁ forms, not z.

Question 8 · easy

For a one-sided z-test of H₀: μ = μ₀ at level α with known σ and n observations, what is the power at μ₀ + δ (δ > 0)?

  1. Φ(δ/σ − z_α)
  2. Φ(δ√n/σ + z_α)
  3. Φ(δ√n/σ − z_α)
  4. 1 − Φ(δ√n/σ − z_α)
Answer and working

C. Φ(δ√n/σ − z_α)

Power = P(X̄ > μ₀ + z_ασ/√n | μ₀ + δ) = P(Z > z_α − δ√n/σ) = Φ(δ√n/σ − z_α). 1 − Φ(...) is β; omitting √n ignores the sample size.

Question 9 · easy

In sample-size formulas, which z value corresponds to a power of 0.80?

  1. 0.8416
  2. 1.2816
  3. 1.6449
  4. 0.2533
Answer and working

A. 0.8416

z_β with β = 0.20 is Φ⁻¹(0.80) = 0.8416. 1.2816 corresponds to 90% power; 1.6449 is z₀.₀₅.

Question 10 · medium

A two-sided z-test at α = 0.05 uses n = 16 with σ = 2. What is its power to detect a true difference δ = 1?

  1. 0.072
  2. 0.516
  3. 0.639
  4. 0.484
Answer and working

B. 0.516

Power = Φ(δ√n/σ − 1.96) + Φ(−δ√n/σ − 1.96) = Φ(0.04) + Φ(−3.96) = 0.516. Using 1.645 treats the test as one-sided; omitting √n gives 0.072.

A study plan for Statistical Inference II: Testing of Hypotheses & Sequential Analysis in Indian Statistical Institute admission tests

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 (46% of the 50 questions): Neyman-Pearson lemma and most powerful tests (6, 12%); Power and sample-size calculation for common tests (6, 12%); Wald and score (Rao) tests (6, 12%); Hypotheses, the two types of error, size and power (5, 10%).

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

  2. Then the middle band: Monotone likelihood ratio and uniformly most powerful tests (5, 10%); Relation between tests and confidence intervals (5, 10%); Unbiased tests and UMPU tests for exponential families (5, 10%); Likelihood ratio tests and Wilks' theorem (4, 8%).

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

  3. Then the lighter units: Multiple testing: family-wise error rate and false discovery rate (4, 8%); Sequential probability ratio test: OC and ASN functions (2, 4%); Tests based on Z, t, chi-square and F distributions (2, 4%).

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

  4. Leave time for the hard ones: Unbiased tests and UMPU tests for exponential families (2 hard of 5), Multiple testing: family-wise error rate and false discovery rate (1 hard of 4), Hypotheses, the two types of error, size and power (1 hard of 5).

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

  5. Bank the easy marks: Likelihood ratio tests and Wilks' theorem (3 easy of 4); Power and sample-size calculation for common tests (3 easy of 6).

    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 — Indian Statistical Institute admission tests Statistical Inference II: Testing of Hypothes

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.