LAISHA
Open Laisha

GATE ST Nonparametric & Rank-Based Methods: practice questions

GATE - Statistics (ST) · India · IITs and IISc on rotation (2027: IIT Madras)

Original practice questions written to the published syllabus · not past papers
10worked here, free
65written to this exam in this subject
11syllabus units

About GATE ST

GATE - Statistics (ST) is a postgraduate admission exam run by IITs and IISc on rotation (2027: IIT Madras), for candidates in India. Computer-based, 3 hours, 100 marks (15 General Aptitude + 85 subject). MCQ, MSQ and NAT; negative marking on MCQ only; on-screen virtual calculator.

Source: gate2026.iitg.ac.in.

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

Nonparametric & Rank-Based Methods in GATE ST

Methods that hold without a normal model: the empirical distribution, goodness-of-fit, sign and rank tests for one, two and many samples, rank correlation, and tests used for scored or ranked agricultural data such as disease ratings and sensory panels.

Our 65 GATE ST questions in this subject: 20 easy, 29 medium, 16 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 GATE ST and are not shown on any other exam's page.

Question 1 · medium

Along a row there are 10 diseased and 10 healthy plants. What is the variance of the number of runs under randomness?

  1. 4.737
  2. 4.500
  3. 5.500
  4. 10.000
Answer and working

A. 4.737

Var(R) = 2n₁n₂(2n₁n₂ − N)/[N²(N − 1)] = 2 × 100 × 180/(400 × 19) = 4.737. Dividing by N³ instead of N²(N − 1) gives 4.500.

Question 2 · medium

With n = 5 non-zero differences and no ties, what is P(T⁺ ≤ 1) under H₀ for the Wilcoxon signed-rank statistic?

  1. 0.0312
  2. 0.0625
  3. 0.2000
  4. 0.40
Answer and working

B. 0.0625

All 2⁵ = 32 sign patterns are equally likely. T⁺ = 0 (all negative) and T⁺ = 1 (only rank 1 positive) each occur once, so P = 2/32 = 0.0625.

Question 3 · easy

For samples of sizes n₁ and n₂ from the same continuous distribution, what are the null mean and variance of U?

  1. n₁n₂/2 and n₁n₂/4
  2. n₁(n₁ + 1)/2 and n₁n₂/12
  3. n₁n₂/2 and n₁n₂(n₁ + n₂ + 1)/12
  4. (n₁ + n₂)/2 and n₁n₂(n₁ + n₂)/12
Answer and working

C. n₁n₂/2 and n₁n₂(n₁ + n₂ + 1)/12

E(U) = n₁n₂/2 and Var(U) = n₁n₂(N + 1)/12 with N = n₁ + n₂, before any tie correction.

Question 4 · medium

Two varieties have similar median yields across farms, but one is far more variable. Which two-sample test is suited to detecting this difference?

  1. The paired sign test
  2. The pooled two-sample t-test
  3. The Mann-Whitney test
  4. The two-sample Kolmogorov-Smirnov test
Answer and working

D. The two-sample Kolmogorov-Smirnov test

Mann-Whitney and t-tests focus on location; KS compares whole distributions and can detect a difference in spread with equal medians.

Question 5 · medium

In a panel, 6 judges rank 4 samples and Friedman's statistic is 9.0. What is Kendall's coefficient of concordance W?

  1. 1.5
  2. 0.75
  3. 0.375
  4. 0.50
Answer and working

D. 0.50

W = χ²_F/[b(k − 1)] = 9/(6 × 3) = 0.50: moderate agreement. 0.375 divides by bk; 0.75 divides by k(k − 1).

Question 6 · medium

Under independence, what is the variance of Kendall's tau for n = 10?

  1. 0.1000
  2. 0.0617
  3. 0.5556
  4. 0.1111
Answer and working

B. 0.0617

Var(τ) = 2(2n + 5)/[9n(n − 1)] = 50/810 = 0.0617. 1/(n − 1) = 0.1111 is the null variance of Spearman's ρ_s.

Question 7 · medium

A statistician uses the Mann-Whitney test instead of the t-test for small yield samples that may contain outliers. What is the cost if the data turn out to be normal?

  1. Severe: the test becomes invalid when the data are normal
  2. Small: about 5% efficiency, in exchange for protection against heavy tails
  3. None: rank tests are always at least as efficient as t-tests
  4. Large: about 36% efficiency, the same as for the sign test
Answer and working

B. Small: about 5% efficiency, in exchange for protection against heavy tails

ARE = 3/π ≈ 0.955 under normality, so the loss is about 5%, while with outliers the rank test can be far more powerful. It never becomes invalid.

Question 8 · medium

Two samples of 3 observations each come from the same continuous distribution. What is the exact probability that U₁ = 0 (all of sample 1 below all of sample 2)?

  1. 0.05
  2. 0.1667
  3. 0.1111
  4. 0.0156
Answer and working

A. 0.05

All C(6, 3) = 20 assignments of ranks to sample 1 are equally likely, and only {1, 2, 3} gives U₁ = 0: probability 0.05. 1/9 wrongly treats the nine pairs as one event.

Question 9 · easy

A blocked trial has many treatments but only three blocks. Which rank test weights blocks by their range of responses and is often more powerful than Friedman's test here?

  1. Page's test
  2. Cochran's Q test
  3. McNemar's test
  4. Quade's test
Answer and working

D. Quade's test

Quade's test ranks the blocks by their ranges and weights within-block ranks accordingly; with few blocks and many treatments it tends to beat Friedman. Page's test targets ordered alternatives.

Question 10 · medium

For uniform data the sign test has ARE 1/3 relative to the t-test. Roughly how many observations does the sign test need to match a t-test using 30?

  1. 30
  2. 47
  3. 10
  4. 90
Answer and working

D. 90

n_sign = n_t/ARE = 30/(1/3) = 90. 47 would apply under normality (30/0.637); 10 inverts the ratio.

A study plan for Nonparametric & Rank-Based Methods in GATE ST

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 (51% of the 65 questions): Mann-Whitney U test and two-sample Kolmogorov-Smirnov test (11, 17%); Sign test and Wilcoxon signed-rank test (8, 12%); Asymptotic relative efficiency (7, 11%); Empirical distribution function and its properties (7, 11%).

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

  2. Then the middle band: Goodness of fit: chi-square and Kolmogorov-Smirnov tests (7, 11%); Friedman's test for randomised blocks (6, 9%); Spearman's and Kendall's rank correlations (6, 9%); Kruskal-Wallis test (4, 6%).

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

  3. Then the lighter units: Run test for randomness (4, 6%); Analysing ordinal scores: disease ratings and sensory panels (3, 5%); Cochran's Q test (2, 3%).

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

  4. Leave time for the hard ones: Cochran's Q test (1 hard of 2), Empirical distribution function and its properties (3 hard of 7), Analysing ordinal scores: disease ratings and sensory panels (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: Empirical distribution function and its properties (4 easy of 7); Cochran's Q test (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 — GATE ST Nonparametric & Rank-Based Methods

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.