LAISHA
Open Laisha

ICAR AICE-JRF/SRF Factorial Experiments, Confounding, Split- & Strip-Plot Designs: 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
88written to this exam in this subject
11syllabus 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.

Source: icar.org.in.

Checked against the exam body's published information. Formats and fees change; confirm the current edition there before you book.

Factorial Experiments, Confounding, Split- & Strip-Plot Designs in ICAR AICE-JRF/SRF

2^n and 3^n factorials, asymmetrical factorials, total and partial confounding, split- and strip-plot designs, crossover designs: effects, sums of squares, confounding schemes, degrees of freedom and error terms.

Split-plot, strip-plot, factorial and simple confounding designs as used in agronomic research; which design for which practical constraint; reading the ANOVA.

Studying several factors at once: 2^n, 3^n and asymmetrical factorials, main effects and interactions by Yates' method, total and partial confounding, fractional factorials, and the split-plot, split-split-plot and strip-plot layouts that field operations such as irrigation and tillage force on agronomists.

Our 88 ICAR AICE-JRF/SRF questions in this subject: 21 easy, 50 medium, 17 hard, across 11 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 · hard

A single replicate of a 2^5 factorial is run without blocks. How can the effects be tested?

  1. No test is possible, so the experiment must be repeated first
  2. Pool high-order interactions as error, or plot effects on a normal plot
  3. Use the block mean square as error, since each replicate is a block
  4. Test each effect against the total mean square of the experiment
Answer and working

B. Pool high-order interactions as error, or plot effects on a normal plot

With no replication there is no pure error; assuming three- and higher-order interactions negligible gives an error estimate, and a normal probability plot shows effects that stand out from noise.

Question 2 · medium

Why are response surface designs often preferred to full 3^n factorials when fitting quadratic responses with several factors?

  1. They need only two levels of each factor to show curvature
  2. They avoid the need for any replication of the centre point
  3. They fit a quadratic surface with far fewer runs
  4. They estimate all high-order interactions that a 3^n cannot
Answer and working

C. They fit a quadratic surface with far fewer runs

A 3^3 needs 27 combinations before replication, whereas a central composite or Box-Behnken design fits the full second-order model with fewer runs. These designs usually replicate the centre point to estimate pure error.

Question 3 · medium

In a 2^3 with four replicates, AB, AC, BC and ABC are each confounded in one replicate. What is the relative information on AB compared with a main effect?

  1. 1/2
  2. 1/4
  3. 3/4
  4. 1
Answer and working

C. 3/4

AB is unconfounded in three of the four replicates, so it is estimated from 3/4 of the data; main effects use all four replicates.

Question 4 · medium

What distinguishes partial from total confounding?

  1. Different effects are confounded in different replicates
  2. The same effect is confounded in every replicate
  3. Only main effects are confounded, never interactions
  4. Confounding is applied to some blocks within a replicate
Answer and working

A. Different effects are confounded in different replicates

Partial confounding spreads the loss over several effects, each estimated from the replicates where it is unconfounded; total confounding loses one effect completely.

Question 5 · medium

What is the resolution of a 2^(4-1) design with defining relation I = ABCD?

  1. V
  2. III
  3. IV
  4. II
Answer and working

C. IV

Resolution is the length of the shortest word in the defining relation; ABCD has four letters, so resolution IV: main effects are clear of two-factor interactions, but two-factor interactions are aliased with each other.

Question 6 · medium

What is the main justification for running a fractional factorial?

  1. High-order interactions are negligible in most cases, so fewer runs suffice
  2. Fractions always give more error degrees of freedom than full designs
  3. Fractions give unbiased estimates of every interaction in the model
  4. Fractions need no randomisation because aliases cancel out
Answer and working

A. High-order interactions are negligible in most cases, so fewer runs suffice

The sparsity-of-effects idea: with many factors, few effects matter and high-order interactions are small, so a fraction estimates main effects and low-order interactions at a fraction of the cost.

Question 7 · medium

A split-plot design has 4 main-plot treatments and 3 sub-plot treatments in 3 replications. How many degrees of freedom do error (a) and error (b) have?

  1. 6 and 16
  2. 16 and 6
  3. 6 and 24
  4. 12 and 16
Answer and working

A. 6 and 16

Error (a) = (r - 1)(a - 1) = 2 x 3 = 6; error (b) = a(r - 1)(b - 1) = 4 x 2 x 2 = 16. 24 would be the error of an RCBD with 12 treatments ignoring the split.

Question 8 · medium

A strip-plot design has 3 horizontal-factor levels and 5 vertical-factor levels in 4 replications. What are the degrees of freedom for errors (a), (b) and (c)?

  1. 12, 6 and 42
  2. 6, 12 and 42
  3. 6, 36 and 24
  4. 6, 12 and 24
Answer and working

D. 6, 12 and 24

Error (a) = (r - 1)(a - 1) = 6; error (b) = (r - 1)(b - 1) = 12; error (c) = (r - 1)(a - 1)(b - 1) = 24. a(r - 1)(b - 1) = 36 is the split-plot error (b).

Question 9 · medium

In a strip plot with 3 horizontal levels and 5 vertical levels in 4 replications, with error (a) mean square Ea, what is the standard error of the difference between two horizontal-factor means?

  1. The square root of (2 Ea / 12)
  2. The square root of (2 Ea / 15)
  3. The square root of (2 Ea / 4)
  4. The square root of (2 Ea / 20)
Answer and working

D. The square root of (2 Ea / 20)

Each horizontal-factor mean is over r x b = 20 plots, so SEd = sqrt(2Ea/(rb)).

Question 10 · hard

A 3 x 3 factorial plus a control is laid out in an RCBD with 3 replications. The control total is 30 and the total of all factorial plots is 360. What is the sum of squares for control versus the factorial treatments?

  1. 5100.0
  2. -4770.0
  3. 30.0
  4. 33.3
Answer and working

C. 30.0

SS = Tc^2/r + Tf^2/(rk) - (Tc + Tf)^2/[r(k + 1)] = 300 + 4800 - 5070 = 30.0. Omitting the factorial term gives a negative figure; omitting the correction gives 5100.0.

A study plan for Factorial Experiments, Confounding, Split- & Strip-Plot Designs 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.

  1. First, the heavy units (47% of the 88 questions): Factorial experiments: main effects and interactions (11, 13%); 2^n factorials and Yates' algorithm (10, 11%); Split-plot designs and their error terms (10, 11%); Total and partial confounding (10, 11%).

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

  2. Then the middle band: Fractional factorials and aliasing (9, 10%); Crossover (changeover) designs (8, 9%); 3^n factorials (7, 8%); Asymmetrical factorials (6, 7%).

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

  3. Then the lighter units: Factorials with extra (control) treatments (6, 7%); Strip-plot (split-block) designs (6, 7%); Split-split-plot designs (5, 6%).

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

  4. Leave time for the hard ones: Factorials with extra (control) treatments (2 hard of 6), Total and partial confounding (3 hard of 10), 3^n factorials (2 hard of 7).

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

  5. Bank the easy marks: Crossover (changeover) designs (3 easy of 8); Factorial experiments: main effects and interactions (4 easy of 11).

    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 — ICAR AICE-JRF/SRF Factorial Experiments, Confounding, Split- & Strip-Plot Designs

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.