GATE - Statistics (ST) · India · IITs and IISc on rotation (2027: IIT Madras)
Original practice questions written to the published syllabus · not past papersGATE - 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.
How to estimate well and know it: sufficiency and completeness, unbiasedness and minimum variance, the Cramer-Rao bound, the Rao-Blackwell and Lehmann-Scheffe theorems, the methods of moments, maximum likelihood and minimum chi-square, and confidence intervals.
Our 84 GATE ST questions in this subject: 32 easy, 38 medium, 14 hard, across 11 units.
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.
For a sample of 10 from uniform (0, θ), both 2X̄ and (n + 1)X₍ₙ₎/n are unbiased for θ. What is the efficiency of 2X̄ relative to (n + 1)X₍ₙ₎/n?
A. 0.25
Var(2X̄) = 4 × θ²/12/n = θ²/30; Var((n + 1)X₍ₙ₎/n) = θ²/[n(n + 2)] = θ²/120. Efficiency of 2X̄ relative to the other = Var(other)/Var(2X̄) = 30/120 = 0.25. The inverse ratio 4.00 is the efficiency of the max-based estimator relative to 2X̄.
Eight pump lifetimes are exponential with rate λ and total 40 months. What is the UMVUE estimate of λ?
A. 0.175 per month
ΣX ~ gamma(n, λ) with E(1/ΣX) = λ/(n − 1), so (n − 1)/ΣX = 7/40 = 0.175 is unbiased and a function of the complete sufficient statistic. The MLE 1/X̄ = 0.200 is biased upward; 5 months is the mean life, not the rate.
In 10 Bernoulli trials there are 4 successes. What is the UMVUE estimate of p²?
B. 0.1333
E[T(T − 1)] = n(n − 1)p² for T binomial(n, p), so T(T − 1)/[n(n − 1)] = 12/90 = 0.1333. The MLE p̂² = 0.16 is biased upward.
For Poisson counts, the Fisher information about λ per observation is 1/λ. What is the information per observation about η = log λ?
A. λ
I(η) = I(λ)(dλ/dη)² = (1/λ)(λ)² = λ. Information is not invariant to reparameterisation; on the log scale it grows with λ.
Which statement about method-of-moments estimators is generally true?
B. They are consistent when the moments exist, but less efficient than the MLE in many models
By the law of large numbers and continuity, moment estimators are consistent; but they can be inefficient (2X̄ for the uniform), biased, not based on sufficient statistics, and outside the parameter space.
Observations are iid uniform on (−θ, θ). The sample mean of the squared observations is 12. What is the method-of-moments estimate of θ?
D. 6.0
E(X) = 0 carries no information, so use E(X²) = θ²/3: θ̂ = √(3 × 12) = 6.0. √12 forgets the factor 3.
Nine plot yields from N(μ, σ²) have Σ(xᵢ − x̄)² = 36. What are the MLE of σ² and the unbiased estimate s²?
A. MLE 4.0; s² = 4.5
MLE σ̂² = 36/9 = 4.0 (divisor n); s² = 36/8 = 4.5 (divisor n − 1). 2.0 is σ̂, the MLE of σ.
Why is the Wilson score interval preferred to the Wald interval for a binomial proportion?
D. It inverts the score test, keeps coverage near nominal for small n and stays inside [0, 1]
The Wilson interval uses the null standard error √(p(1 − p)/n) and solves for p, which corrects the Wald interval's undercoverage near 0 and 1. It is still an approximation and is not always narrower; exact (Clopper-Pearson) intervals guarantee coverage.
How does Fisher's method of scoring differ from Newton-Raphson?
A. It replaces the observed information −ℓ″(θ) by the expected information nI(θ) at each step
Scoring uses θ + ℓ′(θ)/[nI(θ)]. Expected information is positive, which stabilises the iteration. Using E(score) = 0 would never move; derivative-free methods are a different class.
Which property does the EM algorithm have?
D. The likelihood never decreases from one iteration to the next, though convergence is linear and slow
EM guarantees monotone increase of the likelihood but converges linearly and can stop at a local maximum; standard errors need extra computation (for example Louis's method).
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.
Read the manual chapters for these first and do every worked question you can find on them.
Aim for one sitting per unit, then mixed questions across them.
Learn the definitions, classifications and standard numbers; these units are more often recalled than worked.
Come back to these after a first pass, untimed, and read every explanation, including for the options you rejected.
Do these early in revision so they are fast on the day.
Last updated · How Laisha writes and checks its pages · Report a mistake
US$10 a month · one price worldwide · cancel any time
| Free | Smarter | |
|---|---|---|
| Grow guides, pest pages, articles | Read all | Read all |
| Ask Laisha | 5 a day | Up to 1,000 a month |
| Exam practice | The sample on each page | Every question, timed papers |
| Crop calendar and pest alerts | — | For your own fields |
| Calculators and tools | — | All |
| Uploads and reports | — | 100 a month, real files |
An AI operating system for agriculture: free guides, manuals and tools written for every country.