LAISHA
Open Laisha

ASRB NET Advanced Design of Experiments (PhD): practice questions

ASRB NET - Agricultural Statistics (and Computer Application / Bioinformatics) · India · Agricultural Scientists Recruitment Board (ICAR)

Original practice questions written to the published syllabus · not past papers
10worked here, free
84written to this exam in this subject
10syllabus units

About ASRB NET

ASRB NET - Agricultural Statistics (and Computer Application / Bioinformatics) is a professional certification run by Agricultural Scientists Recruitment Board (ICAR), for candidates in India. NET: one objective paper of about 150 questions, 2 hours, negative marking, online, Master's level (pattern as reported for other disciplines).

Official site: asrb.org.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.

Advanced Design of Experiments (PhD) in ASRB NET

Research-level design questions: optimality, neighbour-balanced and row-column designs, bioassay designs, orthogonal arrays and computer-generated designs.

Research-level design theory as practised at IASRI and Rothamsted: optimality of block and row-column designs, designs for correlated errors and neighbour effects, designs for bioassays and diallel crosses, supersaturated and computer-search designs, and designs for computer experiments.

Our 84 ASRB NET questions in this subject: 13 easy, 47 medium, 24 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 ASRB NET and are not shown on any other exam's page.

Question 1 · medium

What is the trace of C for a binary block design with b blocks of size k?

  1. b(k - 1)
  2. b(k + 1)
  3. bk
  4. v(k - 1)
Answer and working

A. b(k - 1)

tr C = n - n/k = bk - b = b(k - 1), the maximum for given b and k.

Question 2 · medium

How many error df does a connected row-column design with p = 4 rows, q = 6 columns and v = 12 treatments have?

  1. 13
  2. 8
  3. 6
  4. 4
Answer and working

D. 4

pq - p - q - v + 2 = 24 - 4 - 6 - 12 + 2 = 4.

Question 3 · medium

Tall and dwarf wheat lines are tested in narrow plots. What is a practical first remedy for shading?

  1. Increase replicates only
  2. Analyse plot totals as ranks
  3. Harvest outer rows only
  4. Group lines of similar height
Answer and working

D. Group lines of similar height

Grouping by height or using guard rows reduces competition between neighbours.

Question 4 · medium

In a slope-ratio assay, how is relative potency estimated?

  1. Ratio of mean responses
  2. Ratio of slopes on dose
  3. Horizontal distance on log dose
  4. Difference of intercepts
Answer and working

B. Ratio of slopes on dose

Lines in dose share an intercept; potency is the slope ratio.

Question 5 · medium

Which criterion is commonly minimised in choosing supersaturated designs?

  1. Error df (N - 1)
  2. E(s^2)
  3. Trace of C
  4. Number of levels
Answer and working

B. E(s^2)

E(s^2), the average squared inner product of column pairs (Booth and Cox), measures non-orthogonality.

Question 6 · medium

Which analysis suits a supersaturated design?

  1. Latin square ANOVA with rows and columns
  2. Variable selection such as the lasso
  3. Ordinary least squares on all factors
  4. Chi-square tests on run totals
Answer and working

B. Variable selection such as the lasso

OLS cannot fit more effects than runs; selection methods exploit sparsity.

Question 7 · medium

Why is simulated annealing used in design search?

  1. To escape local optima
  2. To avoid any criterion
  3. To reduce the number of treatments
  4. To guarantee balanced designs
Answer and working

A. To escape local optima

Occasionally accepting worse moves lets the search leave local optima.

Question 8 · medium

A crop model has ten uncertain parameters. Why use a Latin hypercube instead of a 3^10 grid?

  1. The grid needs 59,049 runs
  2. The grid has only ten runs
  3. The grid cannot vary parameters
  4. The grid gives random outputs
Answer and working

A. The grid needs 59,049 runs

3^10 = 59,049 runs; a few hundred LHS runs plus an emulator suffice.

Question 9 · hard

What are the parameters of a BIBD with v = 6, k = 3, lambda = 2?

  1. r = 4, b = 8
  2. r = 5, b = 6
  3. r = 6, b = 12
  4. r = 5, b = 10
Answer and working

D. r = 5, b = 10

r = 2 x 5/2 = 5; b = 6 x 5/3 = 10.

Question 10 · hard

For 5 runs on [0, 1] with interval midpoints, which values does each input take in an LHS?

  1. 0.2, 0.4, 0.6, 0.8 and 1.0
  2. Five random values anywhere
  3. 0.1, 0.3, 0.5, 0.7 and 0.9
  4. 0, 0.25, 0.5, 0.75 and 1
Answer and working

C. 0.1, 0.3, 0.5, 0.7 and 0.9

Five intervals of width 0.2 with midpoints 0.1 to 0.9, each used once.

A study plan for Advanced Design of Experiments (PhD) in ASRB 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 (44% of the 84 questions): Optimality theory of block designs: universal optimality (10, 12%); Designs for bioassays and parallel-line assays (9, 11%); Designs for computer experiments: Latin hypercube sampling (9, 11%); Supersaturated and screening designs (9, 11%).

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

  2. Then the middle band: Computer-aided search for efficient designs (8, 10%); Designs for diallel crosses and for factorial treatments in blocks (8, 10%); Designs with neighbour effects and correlated errors (8, 10%); Orthogonal arrays and their construction (8, 10%).

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

  3. Then the lighter units: Row-column designs and their analysis (8, 10%); Robustness of designs to missing observations (7, 8%).

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

  4. Leave time for the hard ones: Designs with neighbour effects and correlated errors (3 hard of 8), Designs for bioassays and parallel-line assays (3 hard of 9), Designs for computer experiments: Latin hypercube sampling (3 hard of 9).

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

  5. Bank the easy marks: Designs for diallel crosses and for factorial treatments in blocks (2 easy of 8); Row-column designs and their analysis (2 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 — ASRB NET Advanced Design of Experiments (PhD)

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.