LAISHA
Open Laisha

CSIR-UGC NET Optimization Techniques for Statisticians: 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
29written to this exam in this subject
10syllabus 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.

Optimization Techniques for Statisticians in CSIR-UGC NET

The optimisation theory statisticians use: linear programming with simplex and duality, transportation and assignment, integer and goal programming for farm and crop planning, non-linear optimisation with Kuhn-Tucker conditions, and the numerical optimisers inside likelihood estimation. The Agribusiness track teaches operations research for managers; this goes to the theory.

Our 29 CSIR-UGC NET questions in this subject: 0 easy, 11 medium, 18 hard, across 10 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 · medium

Least absolute deviations regression minimises Σ|yᵢ − xᵢ′β|. How can it be solved?

  1. Only by Newton's method
  2. As a linear programme
  3. By ordinary least squares
  4. By dynamic programming only
Answer and working

B. As a linear programme

Writing each residual as uᵢ − vᵢ with uᵢ, vᵢ ≥ 0 and minimising Σ(uᵢ + vᵢ) gives an LP; quantile regression uses asymmetric weights.

Question 2 · hard

Minimising the variance of a stratified mean for fixed total sample size is solved by which method, and what does it give?

  1. Branch and bound, giving proportional allocation
  2. Lagrange multipliers; nₕ ∝ WₕSₕ
  3. Simplex, giving equal allocation
  4. Dynamic programming, giving nₕ ∝ Nₕ²
Answer and working

B. Lagrange multipliers; nₕ ∝ WₕSₕ

Minimising ΣWₕ²Sₕ²/nₕ subject to Σnₕ = n gives nₕ ∝ WₕSₕ, the Neyman allocation of sampling theory.

Question 3 · hard

In the MODI method, how are the dual values uᵢ and vⱼ found?

  1. From uᵢ + vⱼ = cᵢⱼ on basic cells
  2. From the north-west corner cost
  3. From supplies and demands directly
  4. From the row and column minima
Answer and working

A. From uᵢ + vⱼ = cᵢⱼ on basic cells

Basic cells have zero reduced cost; a non-basic cell with cᵢⱼ − uᵢ − vⱼ < 0 improves the solution.

Question 4 · hard

With 12 ha and a 20-day labour limit, wheat (40/ha, 2 days) and mustard (30/ha, 1 day), can an income goal of 450 be met?

  1. No; the maximum is 440
  2. No; the maximum is 400
  3. Yes, with 4 ha wheat and 8 ha mustard
  4. Yes, with 12 ha wheat
Answer and working

A. No; the maximum is 440

Maximising 40x + 30y with x + y ≤ 12 and 2x + y ≤ 20 gives (8, 4) and 440 < 450, so the goals conflict and weights decide the compromise.

Question 5 · medium

Yield is y = 50N − 0.25N² kg/ha. With grain price p and nitrogen price w, what is the profit-maximising N?

  1. N = 100 − 2w/p
  2. N = 100 + 2w/p
  3. N = 100
  4. N = 50w/p
Answer and working

A. N = 100 − 2w/p

dProfit/dN = p(50 − 0.5N) − w = 0 gives N = 100 − 2w/p, below the yield-maximising 100 kg/ha whenever w > 0.

Question 6 · medium

Maximise 10x − x² subject to x ≤ 3. What are x* and the KKT multiplier?

  1. x* = 5, μ = 0
  2. x* = 3, μ = 0
  3. x* = 5, μ = 4
  4. x* = 3, μ = 4
Answer and working

D. x* = 3, μ = 4

The unconstrained maximum x = 5 is infeasible, so the constraint binds: x = 3 and 10 − 2x = μ gives μ = 4 ≥ 0.

Question 7 · medium

Which is NOT one of the KKT conditions for a maximum with constraints gᵢ(x) ≤ bᵢ?

  1. ∇f = Σμᵢ∇gᵢ
  2. μᵢ ≥ 0
  3. μᵢ[gᵢ(x) − bᵢ] = 0
  4. μᵢ < 0 for binding constraints
Answer and working

D. μᵢ < 0 for binding constraints

Dual feasibility requires μᵢ ≥ 0; the others are stationarity and complementary slackness (plus primal feasibility).

Question 8 · hard

A chance constraint requires P(income ≥ 200) ≥ 0.95, with income normal, mean μ(x) and SD σ(x). What deterministic constraint results?

  1. μ(x) ≥ 200
  2. σ(x) ≤ 0.05
  3. μ(x) + 1.645σ(x) ≥ 200
  4. μ(x) − 1.645σ(x) ≥ 200
Answer and working

D. μ(x) − 1.645σ(x) ≥ 200

P(income ≥ 200) ≥ 0.95 means the 5% quantile μ − 1.645σ must be at least 200.

Question 9 · medium

For the Poisson log-likelihood 30 log λ − 10λ, what is one Newton step from λ₀ = 2?

  1. 2.667
  2. 2.500
  3. 3.000
  4. 1.333
Answer and working

A. 2.667

λ₁ = λ₀ − ℓ′/ℓ″ = 2 − 5/(−7.5) = 2.667; the MLE is 3. Adding instead of subtracting gives 1.333.

Question 10 · medium

Which method for non-linear least squares approximates the Hessian by J′J?

  1. Simplex method for LP
  2. Nelder-Mead
  3. Gauss-Newton
  4. Branch and bound
Answer and working

C. Gauss-Newton

Gauss-Newton uses the Jacobian of the residuals; Levenberg-Marquardt adds damping.

A study plan for Optimization Techniques for Statisticians 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 (59% of the 29 questions): Numerical optimisation: gradient, Newton and quasi-Newton methods (6, 21%); Non-linear programming: Lagrange multipliers and Kuhn-Tucker conditions (5, 17%); Dynamic programming (3, 10%); Quadratic programming and risk programming (MOTAD) (3, 10%).

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

  2. Then the middle band: Duality and sensitivity analysis (2, 7%); Goal programming for multi-objective farm planning (2, 7%); Integer programming: branch and bound (2, 7%); Linear programming: formulation and graphical solution (2, 7%).

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

  3. Then the lighter units: Simplex method, Big-M and two-phase methods (2, 7%); Transportation and assignment problems (2, 7%).

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

  4. Leave time for the hard ones: Dynamic programming (3 hard of 3), Quadratic programming and risk programming (MOTAD) (3 hard of 3), Duality and sensitivity analysis (2 hard of 2).

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

  5. 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 Optimization Techniques for Statisticians

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.