LAISHA
Open Laisha

Indian Statistical Service Examination Probability Theory: practice questions

Indian Statistical Service Examination (with Indian Economic Service) · India · Union Public Service Commission

Original practice questions written to the published syllabus · not past papers
6worked here, free
27written to this exam in this subject
10syllabus units

About Indian Statistical Service Examination

Indian Statistical Service Examination (with Indian Economic Service) is a government recruitment exam run by Union Public Service Commission, for candidates in India. Written examination of six papers and a viva voce. Reported scheme: General English 100, General Studies 100, Statistics I and II (objective, 200 each), Statistics III and IV (descriptive, 200 each); viva 200.

Official site: upsc.gov.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 Service Examination

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 27 Indian Statistical Service Examination questions in this subject: 7 easy, 14 medium, 6 hard, across 10 units.

6 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 6 were written to Indian Statistical Service Examination and are not shown on any other exam's page.

Question 1 · medium

A yield distribution has central moments μ₂ = 4, μ₃ = -6 and μ₄ = 40. Which description is correct?

  1. β₂ = 2.50, so the distribution is platykurtic
  2. β₂ = 0.56, so the distribution is platykurtic
  3. β₂ = 2.50, so the distribution is leptokurtic
  4. β₂ = 10.00, so the distribution is leptokurtic
Answer and working

A. β₂ = 2.50, so the distribution is platykurtic

β₂ = μ₄/μ₂² = 40/16 = 2.50 < 3, so it is platykurtic (flatter-topped than the normal). β₁ = μ₃²/μ₂³ = 36/64 = 0.5625 measures skewness, not kurtosis. Dividing μ₄ by μ₂ instead of μ₂² gives 10.

Question 2 · easy

Why is convergence in distribution defined as Fₙ(x) → F(x) only at continuity points of F?

  1. Because only continuous random variables can converge in law
  2. Because at a jump the limit always exists and so needs no checking
  3. Because Xₙ = 1/n should converge to 0, yet Fₙ(0) = 0 while F(0) = 1
  4. Because a CDF F(x) is defined only at points where it is continuous
Answer and working

C. Because Xₙ = 1/n should converge to 0, yet Fₙ(0) = 0 while F(0) = 1

The constants 1/n obviously approach 0, but Fₙ(0) = P(1/n ≤ 0) = 0 for all n, whereas the limit CDF has F(0) = 1. Excluding the jump at 0 lets the definition agree with intuition. Discrete variables can converge in law (binomial to Poisson).

Question 3 · medium

100 seeds are sown, each germinating independently with probability 0.8. Using the normal approximation with continuity correction, what is P(at most 75 germinate)?

  1. 0.8697
  2. 0.1303
  3. 0.1056
  4. 0.0846
Answer and working

B. 0.1303

Mean np = 80, SD √(100 × 0.8 × 0.2) = 4. With correction, P(X ≤ 75) ≈ Φ((75.5 − 80)/4) = Φ(−1.125) = 0.1303. Without it, Φ(−1.25) = 0.1056; correcting in the wrong direction (74.5) gives 0.0846. The exact binomial value is 0.1314.

Question 4 · medium

Xₙ → X almost surely, and |Xₙ| ≤ Y for all n, where E(Y) < ∞. Which theorem concludes that E(Xₙ) → E(X)?

  1. The dominated convergence theorem
  2. The monotone convergence theorem
  3. The first Borel-Cantelli lemma
  4. Kolmogorov's zero-one law
Answer and working

A. The dominated convergence theorem

Domination by an integrable Y plus almost-sure convergence is exactly the DCT. MCT would need Xₙ non-negative and increasing; Borel-Cantelli and the zero-one law concern events, not limits of expectations.

Question 5 · hard

Given X = x, Y is Poisson with mean x, and X is exponential with mean 2. What is Var(Y)?

  1. 8
  2. 2
  3. 4
  4. 6
Answer and working

D. 6

E(Y | X) = X and Var(Y | X) = X. Var(Y) = E[Var(Y | X)] + Var[E(Y | X)] = E(X) + Var(X) = 2 + 4 = 6 (an exponential with mean 2 has variance 4). 2 is only the within part E(X); 4 is only Var(X); 8 is E(X²), not E(X) + Var(X).

Question 6 · hard

A national trial averages yield gains over 400 plots, all at a single site in a single season. The site-season effect is common to every plot. As the number of plots grows, the variance of the average gain:

  1. Falls to zero, by the central limit theorem
  2. Falls to zero, by the weak law of large numbers
  3. Falls towards the site-season variance, not towards zero
  4. Stays fixed at the plot-level variance, whatever the plot count
Answer and working

C. Falls towards the site-season variance, not towards zero

With Xᵢ = S + eᵢ, Var(X̄) = Var(S) + Var(e)/n → Var(S). The laws of large numbers need independent or weakly dependent terms; a shared effect is not averaged away. Only more sites and seasons reduce that component.

A study plan for Probability Theory in Indian Statistical Service Examination

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 (52% of the 27 questions): Central limit theorems (Lindeberg-Levy, Liapounov) and the delta method (4, 15%); Inequalities: Markov, Chebyshev, Jensen and Cauchy-Schwarz (4, 15%); Conditional probability, independence and Bayes' theorem (3, 11%); Joint, marginal and conditional distributions; conditional expectation (3, 11%).

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

  2. Then the middle band: Sample spaces, sigma-fields and the axioms of probability (3, 11%); Weak and strong laws of large numbers (3, 11%); Expectation, moments and moment-generating, probability-generating and characteristic functions (2, 7%); Functions of random variables and transformations (Jacobian method) (2, 7%).

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

  3. Then the lighter units: Modes of convergence and their relations; Slutsky's lemma; Borel-Cantelli lemma (2, 7%); Elements of measure theory: measurable functions and Lebesgue integral (1, 4%).

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

  4. Leave time for the hard ones: Weak and strong laws of large numbers (2 hard of 3), Conditional probability, independence and Bayes' theorem (1 hard of 3), Joint, marginal and conditional distributions; conditional expectation (1 hard of 3).

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

  5. Bank the easy marks: Expectation, moments and moment-generating, probability-generating and characteristic functions (1 easy of 2); Functions of random variables and transformations (Jacobian method) (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 — Indian Statistical Service Examination 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.