LAISHA
Open Laisha

Indian Statistical Institute admission tests Probability Theory: 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
64written 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.

Probability Theory in Indian Statistical Institute admission tests

Probability from its axioms to the limit theorems: random variables, expectation, generating functions, inequalities and modes of convergence, ending with the laws of large numbers and the central limit theorem that justify most of applied statistics.

Our 64 Indian Statistical Institute admission tests questions in this subject: 20 easy, 36 medium, 8 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

Two quality checks on a seed lot are passed with probabilities 0.8 and 0.7. Nothing is known about how the checks are related. What is the smallest possible probability that a lot passes both?

  1. 0
  2. 0.5
  3. 0.7
  4. 0.56
Answer and working

B. 0.5

Bonferroni's inequality gives P(A ∩ B) ≥ P(A) + P(B) − 1 = 0.8 + 0.7 − 1 = 0.5, and this bound is attained when the failures never overlap. 0.56 is the value only under independence; 0.7 is the largest possible value; 0 is impossible because the two failure probabilities add to only 0.5.

Question 2 · medium

Two fair coins are tossed. A = first coin shows a head, B = second coin shows a head, C = the two coins show the same face. Which statement is correct?

  1. A, B and C are mutually independent, since each pair is independent
  2. No two of A, B and C are independent, since all use the same tosses
  3. A, B and C are pairwise independent but not mutually independent
  4. A and C are dependent, because C is defined using the first coin
Answer and working

C. A, B and C are pairwise independent but not mutually independent

Each event has probability 1/2 and each pairwise intersection has probability 1/4 = (1/2)(1/2), so the events are pairwise independent. But A ∩ B ∩ C is 'both heads', with probability 1/4, not 1/8, so they are not mutually independent (Bernstein's example). Pairwise independence does not imply mutual independence.

Question 3 · medium

Daily rainfall X at a station is exactly 0 on 60% of days and has a continuous distribution on positive values otherwise. Which description of its CDF F is correct?

  1. F is a step function with jumps at every observed rainfall value
  2. F is continuous everywhere, with density 0.6 at the point x = 0
  3. F has a jump of 0.6 at x = 0 and is continuous for x > 0
  4. F is zero up to x = 0.6 and increases continuously after that
Answer and working

C. F has a jump of 0.6 at x = 0 and is continuous for x > 0

Rainfall is a mixed variable: P(X = 0) = 0.6 appears as a jump F(0) − F(0−) = 0.6, and the remaining probability 0.4 is spread continuously over x > 0. A continuous CDF cannot put positive probability on a single point; a step function would make all positive amounts discrete.

Question 4 · medium

Which property holds for the Poisson distribution with mean λ?

  1. Every factorial moment E[X(X−1)⋯(X−r+1)] equals λ
  2. Every cumulant κᵣ, r = 1, 2, 3, ..., equals λ
  3. Every central moment μᵣ, r = 2, 3, 4, ..., equals λ
  4. Every raw moment E(Xʳ), r = 1, 2, 3, ..., equals λ
Answer and working

B. Every cumulant κᵣ, r = 1, 2, 3, ..., equals λ

K(t) = log M(t) = λ(eᵗ − 1), whose every derivative at 0 is λ, so all cumulants equal λ. Raw moments grow (E X² = λ + λ²); μ₄ = λ + 3λ²; the r-th factorial moment is λʳ.

Question 5 · medium

X is standard normal and Y = X². Which statement is correct?

  1. Cov(X, Y) = 1, because Y is a function of X
  2. Cov(X, Y) = 2, the variance of a chi-square(1)
  3. Cov(X, Y) = 0, so X and Y are independent
  4. Cov(X, Y) = 0, yet X and Y are dependent
Answer and working

D. Cov(X, Y) = 0, yet X and Y are dependent

Cov(X, X²) = E(X³) − E(X)E(X²) = 0 − 0 = 0 by symmetry, but Y is completely determined by X. Zero correlation measures only linear association; it implies independence only under joint normality, and (X, X²) is not jointly normal. 2 is Var(Y), not the covariance.

Question 6 · hard

(X, Y) is uniformly distributed on the triangle 0 < y < x < 1. What is E(Y | X = x)?

  1. 1/3
  2. 1/2
  3. x/2
  4. x
Answer and working

C. x/2

Joint density 2 on the triangle; f_X(x) = 2x; f(y | x) = 2/(2x) = 1/x on (0, x), a uniform, so E(Y | X = x) = x/2. 1/3 is the unconditional E(Y) = E(X/2) = (2/3)/2.

Question 7 · medium

X is a positive random variable with finite E(X) and E(1/X). What does Jensen's inequality imply?

  1. E(1/X) ≤ 1/E(X)
  2. E(1/X) ≥ 1/E(X)
  3. E(1/X) = 1/E(X)
  4. E(1/X) ≥ E(X)
Answer and working

B. E(1/X) ≥ 1/E(X)

g(x) = 1/x is convex for x > 0, so E g(X) ≥ g(E X): E(1/X) ≥ 1/E(X), with equality only if X is constant. Equality is the common mistake of treating expectation as if it commuted with non-linear functions.

Question 8 · easy

Which inequality gives directly that every correlation coefficient lies between −1 and 1?

  1. Chebyshev: P(|X − μ| ≥ kσ) ≤ 1/k²
  2. Cauchy-Schwarz: [E(UV)]² ≤ E(U²)E(V²)
  3. Jensen: E g(X) ≥ g(E X) for convex g
  4. Markov: P(X ≥ a) ≤ E(X)/a
Answer and working

B. Cauchy-Schwarz: [E(UV)]² ≤ E(U²)E(V²)

Apply Cauchy-Schwarz to U = X − μ_X and V = Y − μ_Y: Cov² ≤ Var(X)Var(Y), so ρ² ≤ 1, with equality only for exact linear relations.

Question 9 · medium

Events Aₙ have P(Aₙ) = 1/n², with no assumption about dependence. What is P(Aₙ occurs infinitely often)?

  1. It cannot be determined without independence
  2. 1, by the second Borel-Cantelli lemma
  3. π²/6, the sum of the probabilities
  4. 0, by the first Borel-Cantelli lemma
Answer and working

D. 0, by the first Borel-Cantelli lemma

Σ1/n² = π²/6 < ∞, so by the first Borel-Cantelli lemma P(lim sup Aₙ) = 0. That lemma needs no independence. The second lemma needs both a divergent sum and independence. A sum of probabilities is not itself a probability.

Question 10 · easy

Khintchine's weak law of large numbers requires which condition on iid X₁, X₂, ...?

  1. A finite moment-generating function near zero
  2. A finite mean; a finite variance is not needed
  3. A normal distribution for each observation
  4. A finite variance; the mean may be infinite
Answer and working

B. A finite mean; a finite variance is not needed

Khintchine's WLLN: iid with E|X| < ∞ gives X̄ₙ → μ in probability. Chebyshev's proof needs a finite variance, but Khintchine's (via characteristic functions or truncation) does not. A finite mean cannot be dropped: Cauchy averages do not converge.

A study plan for Probability Theory 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 (45% of the 64 questions): Functions of random variables and transformations (Jacobian method) (8, 13%); Expectation, moments and moment-generating, probability-generating and characteristic functions (7, 11%); Inequalities: Markov, Chebyshev, Jensen and Cauchy-Schwarz (7, 11%); Joint, marginal and conditional distributions; conditional expectation (7, 11%).

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

  2. Then the middle band: Modes of convergence and their relations; Slutsky's lemma; Borel-Cantelli lemma (7, 11%); Random variables, distribution functions, mass and density functions (6, 9%); Sample spaces, sigma-fields and the axioms of probability (6, 9%); Weak and strong laws of large numbers (6, 9%).

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

  3. Then the lighter units: Central limit theorems (Lindeberg-Levy, Liapounov) and the delta method (4, 6%); Elements of measure theory: measurable functions and Lebesgue integral (4, 6%); Conditional probability, independence and Bayes' theorem (2, 3%).

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

  4. Leave time for the hard ones: Sample spaces, sigma-fields and the axioms of probability (2 hard of 6), Modes of convergence and their relations; Slutsky's lemma; Borel-Cantelli lemma (2 hard of 7), Elements of measure theory: measurable functions and Lebesgue integral (1 hard of 4).

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

  5. Bank the easy marks: Central limit theorems (Lindeberg-Levy, Liapounov) and the delta method (3 easy of 4); Random variables, distribution functions, mass and density functions (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 Probability Theory

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.