LAISHA
Open Laisha

GATE Probability, Statistics & Data Analysis: practice questions

GATE — Agricultural Engineering (AG) · India · IITs and IISc on rotation (2027: IIT Madras)

Original practice questions written to the published syllabus · not past papers
10worked here, free
62written to this exam in this subject
10syllabus units

About GATE

GATE — Agricultural Engineering (AG) is a postgraduate admission exam run by IITs and IISc on rotation (2027: IIT Madras), for candidates in India. Computer-based, 3 hours, 100 marks (15 General Aptitude + 85 technical: 25 one-mark and 30 two-mark questions). MCQ, MSQ and NAT; negative marking on MCQ only (−1/3 for one-mark, −2/3 for two-mark); no partial credit on MSQ. On-screen virtual calculator.

Source: gate2027.iitm.ac.in.

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

Probability, Statistics & Data Analysis in GATE

Probability and statistics sit inside the Engineering Mathematics section and appeared in every paper Laisha counted from 2019 to 2026, usually as one or two short computational items, often numerical-answer type: a conditional or Bayes probability, a binomial or Poisson probability, a normal-table calculation, the mean or variance of a random variable from its density, a correlation coefficient or regression slope from a small table. Hydrology questions in the soil and water sections reuse return period, risk and Gumbel frequency factors; processing and machinery questions reuse CV and uniformity.

Describing data, probability distributions, regression and designed experiments, with the frequency analysis that hydrology and quality control rely on.

Our 62 GATE questions in this subject: 18 easy, 27 medium, 17 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 GATE and are not shown on any other exam's page.

Question 1 · hard

Eight nozzles on a sprayer boom deliver 0.98, 1.02, 1.05, 0.95, 1.00, 1.04, 0.97 and 0.99 L/min. What is the coefficient of variation of the discharge (using the sample standard deviation)?

  1. 3.24 per cent
  2. 0.120 per cent
  3. 0.0346 per cent
  4. 3.46 per cent
Answer and working

D. 3.46 per cent

Mean = 1.0000 L/min; sample SD = 0.03464 L/min; CV = s/x̄ × 100 = 3.46 per cent. Using the population SD (divide by n) gives 3.24 per cent; using the variance instead of the SD gives 0.120; forgetting to multiply by 100 but still writing 'per cent' gives 0.0346.

Question 2 · medium

Filled bags of wheat have weights that are normally distributed with mean 50.2 kg and standard deviation 0.4 kg. What proportion of bags weigh less than 49.5 kg? (Take Φ(1.75) = 0.9599.)

  1. 0.9599
  2. 0.0401
  3. 0.0802
  4. 0.4599
Answer and working

B. 0.0401

z = (49.5 − 50.2)/0.4 = -1.75. P(Z < −1.75) = 1 − Φ(1.75) = 1 − 0.9599 = 0.0401. 0.9599 is the proportion above 49.5 kg; 0.0802 doubles the tail (a two-tailed slip); 0.4599 is the area between the mean and z.

Question 3 · medium

The regression coefficient of y on x is 0.8 and that of x on y is 0.45. What is the correlation coefficient between x and y?

  1. 0.36
  2. 0.625
  3. 1.25
  4. 0.60
Answer and working

D. 0.60

r² = byx × bxy = 0.8 × 0.45 = 0.36, so r = √0.36 = 0.60, with the common positive sign of the two coefficients. 0.36 is r²; 0.625 is the average of the coefficients; 1.25 = 1/0.8 and is impossible for a correlation.

Question 4 · medium

Two judges rank 8 samples of dried mango slices for colour. The differences between the two ranks for the samples are 1, −1, 2, 0, −2, 1, −1 and 0. What is Spearman's rank correlation coefficient?

  1. 0.8571
  2. 0.8615
  3. 0.9762
  4. 0.1429
Answer and working

A. 0.8571

Σd² = 1 + 1 + 4 + 0 + 4 + 1 + 1 + 0 = 12. rs = 1 − 6Σd²/(n(n² − 1)) = 1 − 6 × 12/(8 × 63) = 1 − 72/504 = 0.8571. Using n² + 1 gives 0.8615; omitting the 6 gives 0.9762; 0.1429 forgets to subtract from 1.

Question 5 · easy

A completely randomised design has 5 treatments, each replicated 4 times. How many degrees of freedom does the error term have?

  1. 15
  2. 16
  3. 19
  4. 12
Answer and working

A. 15

Total df = 20 − 1 = 19; treatment df = 5 − 1 = 4; error df = 19 − 4 = 15 = t(r − 1) = 5 × 3. 16 is t × (r − 1) + 1; 19 is the total; 12 is the RBD error df (t − 1)(r − 1).

Question 6 · easy

In a field experiment, grouping plots of similar fertility into blocks and randomising treatments within each block puts into practice which of Fisher's principles?

  1. Local control
  2. Replication
  3. Randomisation only
  4. Confounding
Answer and working

A. Local control

Blocking to remove a known source of variation from the error is local control. Replication means repeating each treatment; randomisation ensures unbiased allocation; confounding is a deliberate technique in factorial designs and not one of the three basic principles.

Question 7 · easy

Which experiment is best suited to a completely randomised design?

  1. A tillage trial on a sloping field with a clear fertility gradient
  2. A comparison of five harvesters, each operated on a different day by a different crew in a different field
  3. A trial of irrigation schedules spread across three soil types
  4. A laboratory comparison of four drying temperatures on sub-samples from one well-mixed grain lot
Answer and working

D. A laboratory comparison of four drying temperatures on sub-samples from one well-mixed grain lot

CRD is efficient only when experimental units are homogeneous, as with sub-samples of one mixed lot in the laboratory. The other three all have a known source of variation (slope, day and crew, soil type) that should be controlled by blocking in an RBD.

Question 8 · hard

In an RBD with 5 treatments and 4 blocks, one plot is missing. Excluding it, the total of its block is 58.0, the total of its treatment is 44.0 and the grand total is 290.0. Using the standard missing-plot formula, what is the estimated value?

  1. 14.667
  2. 13.500
  3. 8.100
  4. 36.500
Answer and working

B. 13.500

y = (rB + tT − G)/((r − 1)(t − 1)) = (4 × 58 + 5 × 44 − 290)/(3 × 4) = (232 + 220 − 290)/12 = 162/12 = 13.500. Swapping r and t in the numerator gives 14.667; dividing by rt gives 8.100; 36.500 is the average of the block and treatment totals minus the grand mean, which has no basis. After inserting the estimate, the error df is reduced by one.

Question 9 · medium

In the log-Pearson type III method of flood-frequency analysis, if the skew coefficient of the logarithms of the annual peaks is zero, the method reduces to

  1. the Gumbel method
  2. the log-normal method
  3. the normal method applied to the untransformed flows
  4. the exponential distribution
Answer and working

B. the log-normal method

Log-Pearson III applies the frequency factor to the logarithms; its K depends on the skew of the logs and equals the standard normal deviate when that skew is zero, which is exactly the log-normal method. Gumbel has a fixed skew of about 1.14 in the original data.

Question 10 · medium

What does bootstrap resampling do?

  1. It removes outliers from the data before analysis
  2. It repeatedly draws samples of the same size, with replacement, from the observed data to estimate the sampling variability of a statistic without assuming its distribution
  3. It fits a normal distribution to the data by least squares
  4. It draws new data from the field until the sample is large enough for the central limit theorem
Answer and working

B. It repeatedly draws samples of the same size, with replacement, from the observed data to estimate the sampling variability of a statistic without assuming its distribution

Bootstrap resamples the data already collected, with replacement, many times; the spread of the statistic across resamples estimates its standard error and gives confidence intervals. It does not clean data, fit a normal curve or require new fieldwork.

A study plan for Probability, Statistics & Data Analysis in GATE

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 (55% of the 62 questions): Design of experiments: CRD and RBD (10, 16%); Frequency analysis of rainfall and floods (9, 15%); Tests of hypothesis (z, t, chi-square, F) (8, 13%); Binomial, Poisson and normal distributions (7, 11%).

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

  2. Then the middle band: Correlation and linear regression (7, 11%); Probability and random variables (6, 10%); Sampling and sampling distributions (6, 10%); Measures of central tendency and dispersion (4, 6%).

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

  3. Then the lighter units: Statistical quality control charts (4, 6%); Data analysis with spreadsheets and scripts (1, 2%).

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

  4. Leave time for the hard ones: Measures of central tendency and dispersion (2 hard of 4), Design of experiments: CRD and RBD (4 hard of 10), Probability and random variables (2 hard of 6).

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

  5. Bank the easy marks: Sampling and sampling distributions (3 easy of 6); Statistical quality control charts (2 easy of 4).

    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 — GATE Probability, Statistics & Data Analysis

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.