LAISHA
Open Laisha

GATE ST Multivariate Analysis: practice questions

GATE - Statistics (ST) · India · IITs and IISc on rotation (2027: IIT Madras)

Original practice questions written to the published syllabus · not past papers
10worked here, free
76written to this exam in this subject
12syllabus units

About GATE ST

GATE - Statistics (ST) 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 subject). MCQ, MSQ and NAT; negative marking on MCQ only; on-screen virtual calculator.

Source: gate2026.iitg.ac.in.

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

Multivariate Analysis in GATE ST

Analysing many correlated variables together: the multivariate normal and its estimation, Wishart and Hotelling's T-squared, MANOVA, and the reduction and classification tools agricultural scientists use daily (principal components, factor analysis, discriminant and cluster analysis, Mahalanobis D-squared).

Our 76 GATE ST questions in this subject: 21 easy, 45 medium, 10 hard, across 12 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 ST and are not shown on any other exam's page.

Question 1 · easy

X ~ Nₚ(μ, Σ), and A is a fixed q × p matrix. What is the distribution of AX + b?

  1. N(Aμ, AΣA′ + b)
  2. N(Aμ + b, AΣA′)
  3. N(Aμ + b, AΣ)
  4. N(Aμ + b, A′ΣA)
Answer and working

B. N(Aμ + b, AΣA′)

Linear transformations of a multivariate normal are multivariate normal, with mean Aμ + b and dispersion AΣA′. A′ΣA has the wrong dimensions for a q-vector.

Question 2 · medium

Yield X₁ and plant height X₂ are bivariate normal with means 50 and 100, variances 16 and 25 and covariance 10. What is E(X₁ | X₂ = 110)?

  1. 50
  2. 54
  3. 56.25
  4. 55
Answer and working

B. 54

E(X₁ | x₂) = μ₁ + (σ₁₂/σ₂₂)(x₂ − μ₂) = 50 + (10/25)(10) = 54. Dividing by σ₁₁ instead gives 56.25; using the correlation 0.5 as a slope gives 55.

Question 3 · hard

In the multivariate normal, what is the matrix of regression coefficients of X₁ on X₂?

  1. Σ₂₂⁻¹Σ₁₂
  2. Σ₁₂Σ₂₂⁻¹
  3. Σ₁₁⁻¹Σ₁₂
  4. Σ₁₂Σ₁₁⁻¹
Answer and working

B. Σ₁₂Σ₂₂⁻¹

E(X₁ | x₂) = μ₁ + Σ₁₂Σ₂₂⁻¹(x₂ − μ₂), so the coefficient matrix is Σ₁₂Σ₂₂⁻¹ (q × (p − q)). Σ₁₁⁻¹Σ₁₂ regresses in the other direction.

Question 4 · easy

What is the distribution of the sample mean vector x̄ from n observations of Nₚ(μ, Σ)?

  1. Wₚ(n, Σ)
  2. Nₚ(μ, Σ)
  3. Nₚ(μ, Σ/n)
  4. Nₚ(μ/n, Σ/n²)
Answer and working

C. Nₚ(μ, Σ/n)

x̄ is a linear combination of independent normal vectors with weights 1/n, so its dispersion is Σ/n.

Question 5 · easy

A sample dispersion matrix has variances 4 and 9 and covariance 3. What are its total variance and generalised variance?

  1. 36 and 13
  2. 13 and 27
  3. 19 and 27
  4. 13 and 36
Answer and working

B. 13 and 27

Total variance = tr(S) = 13; generalised variance = |S| = 36 − 9 = 27. Ignoring the covariance gives 36; 19 is the variance of the sum of the two variables.

Question 6 · medium

W₁ ~ Wₚ(m₁, Σ) and W₂ ~ Wₚ(m₂, Σ) are independent. What is the distribution of W₁ + W₂?

  1. W₂ₚ(m₁ + m₂, Σ)
  2. Wₚ(max(m₁, m₂), Σ)
  3. Wₚ(m₁ + m₂, 2Σ)
  4. Wₚ(m₁ + m₂, Σ)
Answer and working

D. Wₚ(m₁ + m₂, Σ)

Additivity: pooling independent Wishart matrices with the same Σ adds degrees of freedom, which is why pooled within-group SSCP matrices are Wishart.

Question 7 · medium

Two standardised traits have correlation 0.6. What are the eigenvalues of their correlation matrix?

  1. 1 and 1
  2. 1.36 and 0.64
  3. 0.6 and 0.4
  4. 1.6 and 0.4
Answer and working

D. 1.6 and 0.4

For [[1, r], [r, 1]] the eigenvalues are 1 + r = 1.6 and 1 − r = 0.4, with eigenvectors (1, 1)/√2 and (1, −1)/√2: the sum and the contrast.

Question 8 · easy

Four soil properties are related to three crop responses by canonical correlation analysis. How many canonical correlations are there?

  1. 3
  2. 7
  3. 4
  4. 12
Answer and working

A. 3

The number of canonical pairs is min(p, q) = min(4, 3) = 3.

Question 9 · medium

Why are correlated traits transformed to uncorrelated variables (pivotal condensation) in D² computation?

  1. To make D² a simple sum of squares
  2. So that the traits become normally distributed
  3. So that each trait has a larger variance
  4. So that the number of traits is reduced to one
Answer and working

A. To make D² a simple sum of squares

After transforming with the pooled error dispersion matrix, D² = Σ(differences)² in the new variables, which simplifies computing D² for many pairs.

Question 10 · medium

A contingency table of 500 farms has Pearson χ² = 60. What is its total inertia in correspondence analysis?

  1. 60
  2. 8.33
  3. 0.12
  4. 0.346
Answer and working

C. 0.12

Total inertia = χ²/n = 60/500 = 0.12. Its square root is the mean-square contingency coefficient φ.

A study plan for Multivariate Analysis in GATE ST

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 (39% of the 76 questions): Cluster analysis: hierarchical and k-means (8, 11%); Discriminant analysis and classification (8, 11%); Estimation of the mean vector and dispersion matrix (7, 9%); Multivariate normal distribution: properties, marginals and conditionals (7, 9%).

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

  2. Then the middle band: Principal component analysis (7, 9%); Canonical correlation analysis (6, 8%); Factor analysis (6, 8%); Hotelling's T-squared and its applications (6, 8%).

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

  3. Then the lighter units: Multidimensional scaling and correspondence analysis (6, 8%); Multivariate analysis of variance (MANOVA) (6, 8%); Wishart distribution (5, 7%); Mahalanobis D-squared and genetic divergence (4, 5%).

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

  4. Leave time for the hard ones: Multivariate analysis of variance (MANOVA) (2 hard of 6), Discriminant analysis and classification (2 hard of 8), Mahalanobis D-squared and genetic divergence (1 hard of 4).

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

  5. Bank the easy marks: Estimation of the mean vector and dispersion matrix (3 easy of 7); Principal component analysis (3 easy of 7).

    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 ST Multivariate 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.