CUET-PG Optimization Techniques for Statisticians: practice questions
CUET-PG - Statistics · India · National Testing Agency
Original practice questions written to the published syllabus · not past papers
10worked here, free
35written to this exam in this subject
10syllabus 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.
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 CUET-PG
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 35 CUET-PG questions in this subject: 5 easy, 23 medium, 7 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 CUET-PG and are not shown on any other exam's page.
Question 1 · medium
What shape is the feasible region of a linear programme?
A non-convex polygon
Any closed curve
A convex polyhedron
A circle or ellipse
Answer and working
C. A convex polyhedron
Intersections of half-spaces are convex polyhedra.
Question 2 · medium
At the optimum, a non-basic variable has zero objective-row coefficient. What does this indicate?
Alternative optima exist
The problem is infeasible
The problem is unbounded
The basis is degenerate
Answer and working
A. Alternative optima exist
Bringing that variable in changes the solution without changing z.
Question 3 · hard
In branch and bound, the LP solution has x = 3.4. How is the problem branched?
x ≤ 3.4 and x ≥ 3.4
x = 3 and x = 4
x ≤ 3 and x ≥ 4
x ≤ 0 and x ≥ 7
Answer and working
C. x ≤ 3 and x ≥ 4
The two branches exclude the fractional region 3 < x < 4 while keeping all integer points.
Question 4 · medium
Why is rounding the LP solution not a reliable way to solve an integer programme?
LP solutions are always integers
It ignores feasibility and optimality
Rounding changes the objective function
Rounding always gives the optimum
Answer and working
B. It ignores feasibility and optimality
Rounding ignores the constraints and the objective; the example (3, 1.5) → (3, 1) loses 1 unit relative to (4, 0).
Question 5 · medium
When are the KKT conditions sufficient for a global maximum?
Never; they are only necessary
Only for linear constraints with a convex objective
Any smooth objective
Concave objective and convex feasible region
Answer and working
D. Concave objective and convex feasible region
In convex programming (maximising a concave function over a convex set) KKT points are global optima.
Question 6 · medium
A KKT multiplier is zero at the optimum. What does it indicate?
The constraint must be removed
The objective is linear
The constraint is not binding
The problem is infeasible
Answer and working
C. The constraint is not binding
By complementary slackness, μ > 0 only for binding constraints; μ = 0 typically means the constraint does not bind.
Question 7 · medium
What is the 'curse of dimensionality' in dynamic programming?
Exponential growth of states
Stages grow with time
Returns become non-linear
Recursions diverge
Answer and working
A. Exponential growth of states
Several continuous states make the state space enormous, requiring approximation.
Question 8 · medium
Deciding each year whether to replace a tractor, by its age, is modelled how?
An assignment problem
A DP with age as the state
A transportation problem
A linear regression
Answer and working
B. A DP with age as the state
Each stage (year) has a state (age) and decision (keep/replace); costs depend on age.
Question 9 · medium
Which method is derivative-free?
Nelder-Mead
BFGS
Gauss-Newton
Newton-Raphson
Answer and working
A. Nelder-Mead
Nelder-Mead moves a simplex by reflection, expansion and contraction using function values only.
Question 10 · easy
What does each Newton step need that a gradient step does not?
A feasible starting basis
The Hessian matrix
Integer variables
Only function values
Answer and working
B. The Hessian matrix
Newton uses curvature through H; gradient steps use first derivatives only.
A study plan for Optimization Techniques for Statisticians 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.
First, the heavy units (57% of the 35 questions): Numerical optimisation: gradient, Newton and quasi-Newton methods (6, 17%); Dynamic programming (5, 14%); Integer programming: branch and bound (5, 14%); Non-linear programming: Lagrange multipliers and Kuhn-Tucker conditions (4, 11%).
Read the manual chapters for these first and do every worked question you can find on them.
Then the middle band: Duality and sensitivity analysis (3, 9%); Goal programming for multi-objective farm planning (3, 9%); Linear programming: formulation and graphical solution (3, 9%); Quadratic programming and risk programming (MOTAD) (2, 6%).
Aim for one sitting per unit, then mixed questions across them.
Then the lighter units: Simplex method, Big-M and two-phase methods (2, 6%); Transportation and assignment problems (2, 6%).
Learn the definitions, classifications and standard numbers; these units are more often recalled than worked.
Leave time for the hard ones: Numerical optimisation: gradient, Newton and quasi-Newton methods (3 hard of 6), Duality and sensitivity analysis (1 hard of 3), Non-linear programming: Lagrange multipliers and Kuhn-Tucker conditions (1 hard of 4).
Come back to these after a first pass, untimed, and read every explanation, including for the options you rejected.
Bank the easy marks: Transportation and assignment problems (1 easy of 2); Duality and sensitivity analysis (1 easy of 3).
Do these early in revision so they are fast on the day.
Finish timed. Sit the subject as a timed set without notes, mark it, and send each wrong answer back to its unit above.