LAISHA
Open Laisha

CUET-PG Statistical Inference I: Estimation: practice questions

CUET-PG - Statistics · India · National Testing Agency

Original practice questions written to the published syllabus · not past papers
10worked here, free
70written to this exam in this subject
11syllabus units

About CUET-PG

CUET-PG - Statistics is a postgraduate admission exam run by National Testing Agency, for candidates in India. Computer-based MCQ test used by central and participating universities for MSc Statistics admission.

Official site: exams.nta.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 I: Estimation in CUET-PG

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 70 CUET-PG questions in this subject: 36 easy, 29 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 CUET-PG and are not shown on any other exam's page.

Question 1 · easy

An estimator T of θ has bias 0.5 and variance 2. What is its mean squared error?

  1. 2.50
  2. 2.25
  3. 1.50
  4. 2.00
Answer and working

B. 2.25

MSE = Var(T) + bias² = 2 + 0.25 = 2.25. Adding the bias without squaring gives 2.50; ignoring the bias gives 2.00.

Question 2 · easy

What does the Neyman-Fisher factorisation theorem state?

  1. T is sufficient iff its variance attains the Cramér-Rao lower bound
  2. T is sufficient iff f(x; θ) = g(T(x); θ)h(x), with h free of θ
  3. T is sufficient iff E(T) = θ for every θ in the parameter space
  4. T is sufficient iff its distribution does not depend on θ at all
Answer and working

B. T is sufficient iff f(x; θ) = g(T(x); θ)h(x), with h free of θ

Factorisation: the likelihood splits into a factor depending on the data only through T (and on θ) and a factor free of θ. Unbiasedness and attaining the CRLB are different properties; a statistic whose distribution is free of θ is ancillary, the opposite of sufficient.

Question 3 · medium

X₁, ..., Xₙ are iid with density e^(−(x − θ)) for x > θ. Which statistic is sufficient for θ?

  1. X̄, the sample mean
  2. ΣXᵢ together with X₍ₙ₎
  3. X₍₁₎, the smallest observation
  4. X₍ₙ₎, the sample maximum
Answer and working

C. X₍₁₎, the smallest observation

L(θ) = exp(−Σxᵢ + nθ) 1{X₍₁₎ > θ} = e^(−Σxᵢ) × e^(nθ)1{X₍₁₎ > θ}: the θ-part depends on the data only through the minimum. The support depends on θ, so the support indicator must stay inside g.

Question 4 · easy

What does the Rao-Blackwell theorem guarantee for an unbiased estimator U and a sufficient statistic T?

  1. E(U | T) is the unique UMVUE, whatever the family of distributions
  2. E(U | T) is unbiased with variance ≤ Var(U) for every θ
  3. E(U | T) attains the Cramér-Rao lower bound for every θ
  4. E(U | T) is consistent, even if U itself is not consistent
Answer and working

B. E(U | T) is unbiased with variance ≤ Var(U) for every θ

Conditioning on a sufficient statistic keeps unbiasedness and cannot raise variance (law of total variance). Uniqueness and UMVUE status need completeness as well (Lehmann-Scheffé); attaining the CRLB is not guaranteed.

Question 5 · easy

Counts are iid Poisson(λ) with λ = 4. What is the Cramér-Rao lower bound for the variance of an unbiased estimator of λ from 25 observations?

  1. 6.25
  2. 0.04
  3. 0.16
  4. 0.0064
Answer and working

C. 0.16

I(λ) = 1/λ per observation, so the bound is λ/n = 4/25 = 0.16, attained by X̄. 0.0064 = 4/625 divides by n² instead of n; 0.04 = 1/25 forgets λ; 6.25 inverts the bound.

Question 6 · medium

For which of these distributions do the method-of-moments and maximum-likelihood estimators coincide?

  1. Uniform (0, θ), where both equal X₍ₙ₎
  2. Cauchy location, where both equal the median
  3. Poisson(λ), where both equal X̄
  4. Gamma with unknown shape, where both use X̄ and S²
Answer and working

C. Poisson(λ), where both equal X̄

For the Poisson, both give λ̂ = X̄. For the uniform, MoM is 2X̄ but MLE is X₍ₙ₎; the gamma shape MLE involves log X; the Cauchy has no moments, so no MoM estimator exists.

Question 7 · medium

For multinomial data, minimising the likelihood-ratio statistic G² = 2ΣOⱼ log(Oⱼ/Eⱼ(θ)) over θ is equivalent to which estimation method?

  1. Least squares on the frequencies
  2. The method of moments
  3. Maximum likelihood
  4. Minimum Pearson chi-square
Answer and working

C. Maximum likelihood

G² = 2[ΣOⱼ log Oⱼ − ΣOⱼ log Eⱼ(θ)], and the first term does not involve θ, so minimising G² maximises ΣOⱼ log pⱼ(θ), the multinomial log-likelihood.

Question 8 · easy

Ten plots of a new wheat variety give mean 4.2 t/ha and s = 0.5 t/ha. With t₀.₀₂₅,₉ = 2.262, what is the 95% confidence interval for the mean yield?

  1. 4.09 to 4.31 t/ha
  2. 3.07 to 5.33 t/ha
  3. 3.89 to 4.51 t/ha
  4. 3.84 to 4.56 t/ha
Answer and working

D. 3.84 to 4.56 t/ha

x̄ ± t s/√n = 4.2 ± 2.262 × 0.5/√10 = 4.2 ± 0.358. Using z = 1.96 ignores that σ is estimated; omitting √n gives the range for single plots, not for the mean.

Question 9 · medium

For which pivot do equal tail areas give the shortest confidence interval?

  1. The uniform pivot X₍ₙ₎/θ, whose density increases towards 1
  2. The F pivot for a variance ratio, whose density is skewed
  3. The t pivot for a normal mean, whose density is symmetric and unimodal
  4. The chi-square pivot for a normal variance, whose density is skewed to the right
Answer and working

C. The t pivot for a normal mean, whose density is symmetric and unimodal

For a symmetric unimodal pivot the shortest interval puts equal densities, hence equal tails, at the two ends. For skewed pivots (χ², F) equal tails are conventional but not shortest; for X₍ₙ₎/θ the shortest interval is one-sided.

Question 10 · medium

Plot yields have a coefficient of variation of 20%. How many plots are needed to estimate the mean yield within ±5% of its value with 95% confidence?

  1. 16
  2. 8
  3. 1
  4. 62
Answer and working

D. 62

n = (1.96 × CV/r)² = (1.96 × 20/5)² = 61.47, so 62 plots. Omitting 1.96 gives 16; forgetting to square gives 8.

A study plan for Statistical Inference I: Estimation in CUET-PG

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 (43% of the 70 questions): Interval estimation: pivotal quantities and coverage (8, 11%); Minimum chi-square and other methods (8, 11%); Iterative maximum likelihood: Newton-Raphson and Fisher scoring (7, 10%); Large-sample confidence intervals (7, 10%).

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

  2. Then the middle band: Maximum likelihood: properties, invariance and asymptotic normality (7, 10%); Point estimation: unbiasedness, consistency and efficiency (7, 10%); Sufficiency, the factorisation theorem and minimal sufficiency (7, 10%); Method of moments (6, 9%).

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

  3. Then the lighter units: Cramer-Rao inequality and Fisher information (5, 7%); Completeness, ancillarity and Basu's theorem (4, 6%); Minimum variance unbiased estimation; Rao-Blackwell and Lehmann-Scheffe theorems (4, 6%).

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

  4. Leave time for the hard ones: Completeness, ancillarity and Basu's theorem (1 hard of 4), Cramer-Rao inequality and Fisher information (1 hard of 5), Iterative maximum likelihood: Newton-Raphson and Fisher scoring (1 hard of 7).

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

  5. Bank the easy marks: Point estimation: unbiasedness, consistency and efficiency (5 easy of 7); Minimum chi-square and other methods (5 easy of 8).

    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 — CUET-PG Statistical Inference I: Estimation

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.