LAISHA
Open Laisha

ASRB NET Nonparametric & Rank-Based Methods: 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
43written to this exam in this subject
11syllabus 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.

Nonparametric & Rank-Based Methods in ASRB NET

Applied choice of rank methods for disease scores, damage grades and sensory or farmer-ranking data, with interpretation.

Methods that hold without a normal model: the empirical distribution, goodness-of-fit, sign and rank tests for one, two and many samples, rank correlation, and tests used for scored or ranked agricultural data such as disease ratings and sensory panels.

Our 43 ASRB NET questions in this subject: 18 easy, 24 medium, 1 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 ASRB NET and are not shown on any other exam's page.

Question 1 · easy

What is the one-sample Kolmogorov-Smirnov statistic for testing H₀: F = F₀?

  1. The largest absolute gap between the sample and population means
  2. The largest absolute vertical gap between Fₙ(x) and F₀(x)
  3. The sum of squared gaps between Fₙ(x) and F₀(x) over the observations
  4. The area between Fₙ(x) and F₀(x) over the whole real line
Answer and working

B. The largest absolute vertical gap between Fₙ(x) and F₀(x)

Dₙ = sup|Fₙ(x) − F₀(x)|. The integrated squared gap is the Cramér-von Mises statistic; the area between curves is a Wasserstein-type distance.

Question 2 · medium

Residuals from a field trial are listed in plot order along the field. Which test checks them for a trend or cycle without any distributional assumption?

  1. The two-sample KS test
  2. Cochran's Q test
  3. Runs above and below the median
  4. The Wilcoxon signed-rank test on residuals
Answer and working

C. Runs above and below the median

Coding each residual + or − relative to the median and counting runs tests randomness of the ordering; long runs indicate spatial trend or autocorrelation.

Question 3 · easy

How are zero differences handled in the sign test?

  1. They count as half a success each
  2. They count as positive
  3. They are dropped and n is reduced
  4. They are given the median rank
Answer and working

C. They are dropped and n is reduced

Standard practice drops ties with the hypothesised median and reduces n; alternatives exist, but counting them as positive biases the test.

Question 4 · easy

What does the Wilcoxon signed-rank test assume about the distribution of the paired differences that the sign test does not?

  1. Symmetry of the differences
  2. Normality
  3. A known median
  4. Equal variances in the two members of each pair
Answer and working

A. Symmetry of the differences

Both need independence and continuity; the signed-rank test also assumes symmetry, which is what lets each rank carry either sign with probability 1/2. Neither assumes normality.

Question 5 · medium

With 20 non-zero paired differences and no ties, T⁺ = 160. What is the normal-approximation Z?

  1. 0.077
  2. 1.03
  3. 2.05
  4. −1.87
Answer and working

C. 2.05

Z = (160 − 105)/√717.5 = 55/26.79 = 2.05: significant at 5% two-sided. Dividing by the variance gives 0.077.

Question 6 · medium

Treatments are increasing doses of a nutrient, and the alternative of interest is a monotone increase in response. Which rank test is more powerful than Kruskal-Wallis here?

  1. The runs test on the doses
  2. The two-sample KS test on each adjacent pair
  3. The Jonckheere-Terpstra test
  4. Cochran's Q test
Answer and working

C. The Jonckheere-Terpstra test

Jonckheere-Terpstra targets ordered alternatives across independent groups (Page's test does the same for blocked designs). Kruskal-Wallis spends power on all possible patterns.

Question 7 · easy

What kind of data does Cochran's Q test analyse?

  1. Continuous responses in a completely randomised design
  2. Ranks of treatments within blocks
  3. Counts in an r × c contingency table of independent units, one per farm
  4. Binary responses with every treatment applied in every block
Answer and working

D. Binary responses with every treatment applied in every block

Cochran's Q is the binary counterpart of Friedman's test for blocked designs. An r × c table of independent units uses Pearson's χ².

Question 8 · easy

Two judges rank 6 varieties for taste, and the squared rank differences sum to 8. What is Spearman's rank correlation?

  1. 0.771
  2. 0.778
  3. 0.962
  4. 0.229
Answer and working

A. 0.771

ρ_s = 1 − 6Σd²/[n(n² − 1)] = 1 − 48/210 = 0.771. Omitting the 6 gives 0.962; using n³ instead of n(n² − 1) gives 0.778.

Question 9 · medium

A breeder wants to know whether variety rankings for yield are consistent between two environments. Which summary is most appropriate?

  1. The one-sample KS test on each environment
  2. Spearman's or Kendall's rank correlation
  3. Cochran's Q on the yields above the median
  4. The paired t-test on the two environment yield means
Answer and working

B. Spearman's or Kendall's rank correlation

Consistency of ranking (a rank-based view of crossover genotype-by-environment interaction) is measured by rank correlation. A paired t-test compares mean levels, not rankings.

Question 10 · medium

Why is reporting a mean disease score of 3.4 ± 0.2 on a 0-5 Horsfall-Barratt-type scale misleading?

  1. The standard error of scores is always larger than the mean, so the reported 0.2 must be wrong
  2. Grades are ordinal with unequal intervals, so means and SEs imply false precision
  3. The mean of a 0-5 scale must be an integer, so 3.4 is impossible
  4. Scores cannot be summarised at all, even by medians or proportions
Answer and working

B. Grades are ordinal with unequal intervals, so means and SEs imply false precision

Horsfall-Barratt grades correspond to logarithmic intervals of percentage severity; averaging codes treats unequal steps as equal. Medians, proportions per grade or class-midpoint percentages are better summaries.

A study plan for Nonparametric & Rank-Based Methods 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 (53% of the 43 questions): Analysing ordinal scores: disease ratings and sensory panels (7, 16%); Friedman's test for randomised blocks (6, 14%); Kruskal-Wallis test (5, 12%); Sign test and Wilcoxon signed-rank test (5, 12%).

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

  2. Then the middle band: Cochran's Q test (4, 9%); Run test for randomness (4, 9%); Goodness of fit: chi-square and Kolmogorov-Smirnov tests (3, 7%); Mann-Whitney U test and two-sample Kolmogorov-Smirnov test (3, 7%).

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

  3. Then the lighter units: Asymptotic relative efficiency (2, 5%); Empirical distribution function and its properties (2, 5%); Spearman's and Kendall's rank correlations (2, 5%).

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

  4. Leave time for the hard ones: Analysing ordinal scores: disease ratings and sensory panels (1 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: Empirical distribution function and its properties (2 easy of 2); Goodness of fit: chi-square and Kolmogorov-Smirnov tests (2 easy of 3).

    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 Nonparametric & Rank-Based Methods

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.