LAISHA
Open Laisha

IIT JAM Categorical Data Analysis & Generalized Linear Models: practice questions

IIT JAM - Mathematical Statistics (MS) · India · IITs (JAM 2026 organised by IIT Bombay)

Original practice questions written to the published syllabus · not past papers
10worked here, free
73written to this exam in this subject
11syllabus units

About IIT JAM

IIT JAM - Mathematical Statistics (MS) is a postgraduate admission exam run by IITs (JAM 2026 organised by IIT Bombay), for candidates in India. Computer-based, 3 hours, 60 questions, 100 marks, English. Section A 30 MCQs (10 x 1 mark, 20 x 2 marks); Section B 10 MSQs (2 marks, no negative or partial marking); Section C 20 NAT (10 x 1, 10 x 2, no negative). MCQ wrong answers lose 1/3 or 2/3 mark.

Source: jam2026.iitb.ac.in.

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

Categorical Data Analysis & Generalized Linear Models in IIT JAM

Models for counts, proportions and categories: contingency tables, the exponential-family GLM with its link functions, logistic and Poisson regression, log-linear models, overdispersion, ordinal outcomes and generalised linear mixed models, applied to germination, mortality, pest counts and adoption data.

Our 73 IIT JAM questions in this subject: 15 easy, 45 medium, 13 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 IIT JAM and are not shown on any other exam's page.

Question 1 · medium

Mortality is recorded at five increasing doses. Which test of association uses the order of the doses?

  1. The Breslow-Day test
  2. The Cochran-Armitage trend test with 1 df
  3. McNemar's test
  4. Pearson's X² with 4 df
Answer and working

B. The Cochran-Armitage trend test with 1 df

A trend test concentrates power on a monotone dose effect with 1 df, while the general X² spreads it over 4 df. McNemar is for paired binary data; Breslow-Day tests homogeneity of odds ratios across strata.

Question 2 · medium

When is the residual deviance of a single GLM approximately χ²ₙ₋ₚ and usable as a goodness-of-fit test?

  1. For grouped data with large counts per observation
  2. Only for the normal linear model
  3. Whenever n exceeds 30
  4. For binary (0/1) data of any size
Answer and working

A. For grouped data with large counts per observation

The χ² approximation needs large binomial denominators or Poisson means; for ungrouped binary data the deviance depends on the fitted values alone and says nothing about fit.

Question 3 · medium

Which checks of fit suit a logistic model for individual (ungrouped) binary outcomes?

  1. Comparing the residual deviance with χ²ₙ₋ₚ
  2. The ratio of deviance to df as an overdispersion test
  3. Shapiro-Wilk on the raw 0/1 responses
  4. Hosmer-Lemeshow test and the area under the ROC curve
Answer and working

D. Hosmer-Lemeshow test and the area under the ROC curve

For binary data the deviance is not a goodness-of-fit statistic and overdispersion is not identifiable; Hosmer-Lemeshow assesses calibration and the AUC discrimination.

Question 4 · easy

What is the main consequence of ignoring overdispersion in a Poisson or binomial GLM?

  1. The deviance becomes negative
  2. Coefficient estimates become strongly biased
  3. Fitted values fall outside their allowed range
  4. Standard errors are too small and tests too liberal
Answer and working

D. Standard errors are too small and tests too liberal

The mean model and β̂ are usually fine, but the assumed variance is too small, so SEs are understated and spurious significance results.

Question 5 · medium

For a 2 × 2 × 2 table, how many residual degrees of freedom does the mutual-independence model (X, Y, Z) have?

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

A. 4

8 cells minus 4 parameters (constant plus one for each variable) = 4. (XZ, YZ) has 2, homogeneous association 1, saturated 0.

Question 6 · medium

Before fitting a zero-inflated model to aphid counts, what should be checked?

  1. Whether the proportional-odds assumption holds
  2. Whether a NB model explains the zeros
  3. Whether the zeros can be deleted
  4. Whether the counts are normally distributed
Answer and working

B. Whether a NB model explains the zeros

Apparent excess zeros are often just overdispersion; a negative binomial with small k produces many zeros. Comparing observed and predicted zero frequencies settles it.

Question 7 · hard

A logistic GLMM has a random-intercept variance of 2 and a conditional treatment coefficient β. About what is the corresponding marginal (population-averaged) coefficient?

  1. 1.30β
  2. 0.77β
  3. 0.50β
  4. β
Answer and working

B. 0.77β

β_marginal ≈ β/√(1 + 0.346σ²) = β/√1.692 = 0.77β: marginal effects are attenuated towards zero.

Question 8 · easy

What is the Pearson residual for a Poisson observation y = 7 with fitted mean 4?

  1. 0.75
  2. 3.0
  3. 1.35
  4. 1.5
Answer and working

D. 1.5

(y − μ̂)/√V(μ̂) = 3/√4 = 1.5. 3 is the raw residual; 1.35 is the deviance residual.

Question 9 · medium

How many degrees of freedom does the Hosmer-Lemeshow statistic have with the usual 10 groups?

  1. 9
  2. n − p
  3. 10
  4. 8
Answer and working

D. 8

g − 2 = 8 with g = 10 groups of fitted probability. n − p would apply to the deviance of grouped data.

Question 10 · easy

What is the deviance of the saturated model?

  1. n
  2. 0
  3. n − p
  4. The null deviance
Answer and working

B. 0

The saturated model fits every observation exactly, so its log-likelihood is the maximum possible and D = 0; other models are measured against it.

A study plan for Categorical Data Analysis & Generalized Linear Models in IIT JAM

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 (42% of the 73 questions): Link functions, deviance and iteratively reweighted least squares (8, 11%); Ordinal and multinomial logistic models (8, 11%); Poisson regression for counts (8, 11%); Contingency tables: association, odds ratios and tests (7, 10%).

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

  2. Then the middle band: Model checking: residuals and goodness of fit (7, 10%); Zero-inflated and hurdle models (7, 10%); Exponential family and the generalized linear model (6, 8%); Generalized linear mixed models (6, 8%).

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

  3. Then the lighter units: Overdispersion: quasi-likelihood and negative binomial models (6, 8%); Log-linear models for multi-way tables (5, 7%); Logistic regression for binary and binomial data (5, 7%).

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

  4. Leave time for the hard ones: Exponential family and the generalized linear model (2 hard of 6), Generalized linear mixed models (2 hard of 6), Model checking: residuals and goodness of fit (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: Exponential family and the generalized linear model (2 easy of 6); Overdispersion: quasi-likelihood and negative binomial models (2 easy of 6).

    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 — IIT JAM Categorical Data Analysis & Generalized Linear Models

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.