ICAR AICE-JRF/SRF Advanced Design of Experiments (PhD): practice questions
ICAR AICE-JRF/SRF - Agricultural Statistics, Computer Application, Bioinformatics (PhD admission and fellowship) · India · National Testing Agency for ICAR
Original practice questions written to the published syllabus · not past papers
10worked here, free
86written to this exam in this subject
10syllabus units
About ICAR AICE-JRF/SRF
ICAR AICE-JRF/SRF - Agricultural Statistics, Computer Application, Bioinformatics (PhD admission and fellowship) is a PhD, fellowship and lectureship exam run by National Testing Agency for ICAR, for candidates in India. Computer-based test, 2 hours, 120 MCQs, +4 / -1 (Part A general, Part B core group, Part C subject). 2026 exam held with AIEEA-PG in July 2026.
Checked against the exam body's published information. Formats and fees change; confirm the current edition there before you book.
Advanced Design of Experiments (PhD) in ICAR AICE-JRF/SRF
General block design analysis and design construction, which this subject extends to optimality, row-column designs and orthogonal arrays.
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 86 ICAR AICE-JRF/SRF questions in this subject: 19 easy, 42 medium, 25 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 ICAR AICE-JRF/SRF and are not shown on any other exam's page.
Question 1 · easy
Whenever a BIBD exists for given v, b and k, it is:
Universally optimal
Optimal only for E
Never A-optimal
Disconnected
Answer and working
A. Universally optimal
Its C-matrix is completely symmetric with maximum trace.
Question 2 · medium
Which criterion minimises the average variance of elementary contrasts?
D-optimality
G-optimality
A-optimality
E-optimality
Answer and working
C. A-optimality
A minimises the sum of reciprocal eigenvalues of C (average variance); D maximises their product; E the smallest.
Question 3 · medium
In a latinized design, what extra condition holds?
Each entry once in each long field column
Each entry appears twice in every block
Entries are never randomised within blocks
Each replicate is a complete Latin square
Answer and working
A. Each entry once in each long field column
Latinization protects against trends along the full length of the field.
Question 4 · medium
What are border plots used for in circular neighbour-balanced designs?
Measuring the error variance directly
Testing a new treatment outside the design
Holding extra replicates of the control
Giving end plots their designed neighbours
Answer and working
D. Giving end plots their designed neighbours
Border plots repeat end treatments so every plot has the intended neighbours.
Question 5 · medium
For 8 parents (28 crosses), how many SCA effects remain after 7 GCA contrasts and the mean?
7
20
28
21
Answer and working
B. 20
28 crosses give 27 df after the mean; 7 go to GCA, leaving 28 - 7 - 1 = 20 for SCA.
Question 6 · medium
How many treatment df does a symmetric (3, 3) assay have, and how are they split?
3: one each for preparations, regression and curvature
6: one per dose for each preparation separately
5: preparations, regression, parallelism, two curvature
4: preparations, regression and two parallelism terms
Answer and working
C. 5: preparations, regression, parallelism, two curvature
Six dose groups give 5 df: preparations, regression, parallelism, curvature, difference of curvature.
Question 7 · medium
For quantal-response assays, where should doses be placed?
Only at doses giving 100% response
Around 20% to 80% expected response
Only at doses giving 0% response
At a single dose repeated many times
Answer and working
B. Around 20% to 80% expected response
Information about the LD50 is greatest in the middle response range.
Question 8 · medium
How many times does each level pair occur in two columns of OA(8, 7, 2, 2)?
2
8
4
1
Answer and working
A. 2
Each pair of columns has 2^2 = 4 level combinations, each occurring lambda = 8/4 = 2 times.
Question 9 · medium
Which constraint is often added in searches for variety-trial designs?
No pair sharing a block twice
All controls in one block
Every entry in every block
Entries sorted by name
Answer and working
A. No pair sharing a block twice
Spreading concurrences improves balance and robustness.
Question 10 · medium
Why are computer experiments not replicated?
Replication is too expensive
Blocks are not available
The simulator is deterministic
Randomisation is impossible
Answer and working
C. The simulator is deterministic
Repeating a run gives the same output, so replication adds nothing.
A study plan for Advanced Design of Experiments (PhD) in ICAR AICE-JRF/SRF
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 (47% of the 86 questions): Designs for bioassays and parallel-line assays (10, 12%); Optimality theory of block designs: universal optimality (10, 12%); Row-column designs and their analysis (10, 12%); Supersaturated and screening designs (10, 12%).
Read the manual chapters for these first and do every worked question you can find on them.
Then the middle band: Designs for computer experiments: Latin hypercube sampling (9, 10%); Orthogonal arrays and their construction (9, 10%); Computer-aided search for efficient designs (7, 8%); Designs for diallel crosses and for factorial treatments in blocks (7, 8%).
Aim for one sitting per unit, then mixed questions across them.
Then the lighter units: Designs with neighbour effects and correlated errors (7, 8%); Robustness of designs to missing observations (7, 8%).
Learn the definitions, classifications and standard numbers; these units are more often recalled than worked.
Leave time for the hard ones: Designs with neighbour effects and correlated errors (3 hard of 7), Designs for computer experiments: Latin hypercube sampling (3 hard of 9), Orthogonal arrays and their construction (3 hard of 9).
Come back to these after a first pass, untimed, and read every explanation, including for the options you rejected.
Bank the easy marks: Row-column designs and their analysis (3 easy of 10); Supersaturated and screening designs (3 easy of 10).
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.