LAISHA
Open Laisha

CSIR-UGC NET Probability Distributions & Sampling Distributions: practice questions

CSIR-UGC NET - Mathematical Sciences (statistics option) · India · National Testing Agency for CSIR

Original practice questions written to the published syllabus · not past papers
10worked here, free
30written to this exam in this subject
9syllabus units

About CSIR-UGC NET

CSIR-UGC NET - Mathematical Sciences (statistics option) is a PhD, fellowship and lectureship exam run by National Testing Agency for CSIR, for candidates in India. Computer-based, 3 hours, Parts A (general aptitude), B and C (subject); statisticians answer from the statistics unit.

Official site: csirnet.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.

Probability Distributions & Sampling Distributions in CSIR-UGC NET

Every standard distribution a statistician must recognise and derive from: discrete and continuous families, their relations and limiting forms, compound and truncated distributions, order statistics, the bivariate normal and the sampling distributions chi-square, t and F.

Our 30 CSIR-UGC NET questions in this subject: 3 easy, 10 medium, 17 hard, across 9 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 CSIR-UGC NET and are not shown on any other exam's page.

Question 1 · hard

X and Y are independent Poisson variables with means 2 and 3. What is P(X = 2 | X + Y = 4)?

  1. 0.3750
  2. 0.4000
  3. 0.3456
  4. 0.2707
Answer and working

C. 0.3456

Given X + Y = 4, X ~ binomial(4, 2/5): P(X = 2) = C(4, 2)(0.4)²(0.6)² = 0.3456. 0.2707 is the unconditional P(X = 2); 0.3750 uses p = 1/2, ignoring the unequal means.

Question 2 · hard

For large n, Fisher's approximation to the chi-square distribution with n degrees of freedom states that √(2χ²ₙ) is approximately:

  1. N(√n, 1)
  2. N(√(2n), 2)
  3. N(√(2n − 1), 1)
  4. N(n, 2n)
Answer and working

C. N(√(2n − 1), 1)

Fisher: √(2χ²) is approximately normal with mean √(2n − 1) and unit variance. N(n, 2n) is the direct normal approximation to χ²ₙ itself, not to its square root.

Question 3 · medium

X and Y each have a standard normal marginal distribution. What can be concluded about (X, Y)?

  1. X and Y are independent, because both marginals are standard normal
  2. X + Y is normal with variance 2, whatever the dependence between them
  3. (X, Y) is bivariate normal, with correlation to be estimated from the data
  4. Nothing more without further information; normal marginals do not make the pair bivariate normal
Answer and working

D. Nothing more without further information; normal marginals do not make the pair bivariate normal

Counterexample: Y = SX with S an independent random sign. Y is standard normal, but X + Y = 0 with probability 1/2, so (X, Y) is not bivariate normal and X + Y is not normal. Joint normality must be assumed or checked separately.

Question 4 · hard

(X, Y) is standard bivariate normal with correlation 0.5. What is P(X > 0, Y > 0)?

  1. 0.3750
  2. 0.2500
  3. 0.5000
  4. 0.3333
Answer and working

D. 0.3333

Sheppard's formula: 1/4 + arcsin(ρ)/(2π) = 0.25 + (π/6)/(2π) = 0.25 + 1/12 = 0.3333. 0.25 holds only when ρ = 0; 0.375 adds ρ/4 linearly, which is not the formula.

Question 5 · hard

(X, Y) is standard bivariate normal with correlation ρ, and W = (X² − 2ρXY + Y²)/(1 − ρ²). What is P(W ≤ 4.605)?

  1. 0.97
  2. 0.99
  3. 0.90
  4. 0.95
Answer and working

C. 0.90

W ~ χ²₂, an exponential with mean 2, so P(W ≤ c) = 1 − e^(−c/2) = 1 − e^(−2.3025) = 0.90: the 90% probability ellipse. 0.97 wrongly uses χ²₁; 0.95 would need c = 5.99.

Question 6 · hard

V is non-central chi-square with 4 degrees of freedom and non-centrality λ = Σμᵢ² = 3. What are E(V) and Var(V)?

  1. Mean 5.5, variance 11
  2. Mean 7, variance 20
  3. Mean 4, variance 8
  4. Mean 7, variance 14
Answer and working

B. Mean 7, variance 20

With λ = Σμᵢ², E(V) = n + λ = 7 and Var(V) = 2(n + 2λ) = 2 × 10 = 20. 2(n + λ) = 14 forgets that the non-centrality enters the variance doubled; mean 5.5 uses the λ/2 convention inconsistently.

Question 7 · easy

Why are non-central t and F distributions needed in planning field experiments?

  1. They give the distribution of the test statistic under the alternative, from which power and replication follow
  2. They describe test statistics when the error variance is unknown and estimated from data
  3. They replace the central distributions for computing critical values when data are not normal
  4. They correct the F-test for missing plots and unequal replication of treatments
Answer and working

A. They give the distribution of the test statistic under the alternative, from which power and replication follow

Under H₀ the statistic is central; under an alternative it is non-central with non-centrality set by the true effects, σ² and replication. Power = P(non-central variable > central critical value). Estimated error variance is already built into the central t and F.

Question 8 · hard

X₁, ..., X₁₀ are iid N(1, 4). With λ = Σμᵢ²/σ², what are the distributions of ΣXᵢ²/4 and Σ(Xᵢ − X̄)²/4?

  1. Non-central χ²₁₀ with λ = 2.5; non-central χ²₉ with λ = 2.5
  2. Non-central χ²₁₀ with λ = 10; central χ²₉
  3. Non-central χ²₁₀ with λ = 2.5; central χ²₉
  4. Central χ²₁₀; central χ²₉
Answer and working

C. Non-central χ²₁₀ with λ = 2.5; central χ²₉

Xᵢ/2 ~ N(0.5, 1), so ΣXᵢ²/4 is non-central χ²₁₀ with λ = 10 × 0.25 = 2.5. Centring removes the common mean: Σ(Xᵢ − X̄)²/σ² is central χ²₉ (the non-centrality μ′Aμ = 0 because the centring matrix annihilates a constant vector). λ = 10 forgets to divide by σ².

Question 9 · hard

X ~ Nₙ(0, I) and X′X = Q₁ + Q₂ + ... + Q_k with Qᵢ = X′AᵢX of rank rᵢ. What does Cochran's theorem say?

  1. The Qᵢ are chi-squares with rᵢ df, but are never mutually independent
  2. The Qᵢ are independent chi-squares with rᵢ df if and only if Σrᵢ = n
  3. The Qᵢ are independent chi-squares with rᵢ df whenever each Aᵢ is symmetric
  4. The Qᵢ are independent if and only if the trace of every Aᵢ equals 1
Answer and working

B. The Qᵢ are independent chi-squares with rᵢ df if and only if Σrᵢ = n

Cochran's theorem: the ranks adding to n is necessary and sufficient for the Qᵢ to be independent χ²_(rᵢ); equivalently each Aᵢ is idempotent, or AᵢAⱼ = 0 for i ≠ j. Symmetry alone guarantees nothing.

Question 10 · hard

X ~ Nₙ(μ, I) and A is symmetric idempotent of rank r. What is the distribution of X′AX?

  1. Normal with mean μ′Aμ and variance 2r
  2. Central chi-square with r df, whatever μ
  3. Non-central chi-square with n df and non-centrality μ′μ
  4. Non-central chi-square with r df and non-centrality μ′Aμ
Answer and working

D. Non-central chi-square with r df and non-centrality μ′Aμ

Write A = PP′ with P′P = I_r; then P′X ~ N_r(P′μ, I) and X′AX = ‖P′X‖² is non-central χ²_r with λ = μ′PP′μ = μ′Aμ. It is central only when Aμ = 0.

A study plan for Probability Distributions & Sampling Distributions in CSIR-UGC NET

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 (70% of the 30 questions): Non-central chi-square, t and F (8, 27%); Distributions of quadratic forms in normal variables (Cochran's theorem) (7, 23%); Exponential family of distributions (6, 20%).

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

  2. Then the middle band: Bivariate normal: marginal and conditional distributions (3, 10%); Relations and limiting forms among distributions (2, 7%); Discrete distributions: Bernoulli, binomial, Poisson, geometric, negative binomial, hypergeometric and multinomial (1, 3%).

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

  3. Then the lighter units: Order statistics: distributions of single, joint and range (1, 3%); Pearsonian system and fitting of distributions to agricultural data (1, 3%); Sampling distributions: chi-square, t and F and their properties (1, 3%).

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

  4. Leave time for the hard ones: Relations and limiting forms among distributions (2 hard of 2), Discrete distributions: Bernoulli, binomial, Poisson, geometric, negative binomial, hypergeometric and multinomial (1 hard of 1), Order statistics: distributions of single, joint and range (1 hard of 1).

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

  5. Bank the easy marks: Non-central chi-square, t and F (2 easy of 8); Exponential family of distributions (1 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 — CSIR-UGC NET Probability Distributions & Sampling Distributions

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.