M.Stat
M.Stat Syllabus 2026
The M.Stat (M.Stat) syllabus covers a structured programme spanning 2 Years designed to build both foundational knowledge and specialised expertise. Below is the detailed semester-wise subject breakdown and programme structure.
M.Stat Semester-wise Subjects
M.Stat Syllabus & Subjects
M.Stat comprises 20 courses for the B-stream (ISI B.Stat holders) and 21 courses for the NB-stream (external candidates). The academic year runs from July-August to May.
Year 1 - Core Courses
| Subject | Key Topics |
|---|---|
| Probability Theory | Measure-theoretic probability, convergence theorems, characteristic functions, central limit theorems |
| Statistical Inference | Sufficiency, completeness, UMVUE, Neyman-Pearson theory, likelihood methods, Bayesian inference |
| Linear Models & Regression | Generalised linear models, ANOVA, regression diagnostics, model selection |
| Multivariate Analysis | Multivariate normal distribution, PCA, factor analysis, discriminant analysis, clustering |
| Large Sample Theory | Asymptotic theory, consistency, efficiency, delta method, U-statistics |
| Statistical Computing | Programming in R and Python, simulation methods, computational statistics |
| Sample Survey Design | Sampling theory, stratified/cluster/systematic sampling, estimation techniques |
| Design of Experiments | Factorial designs, block designs, response surface methodology, optimal designs |
| Stochastic Processes | Markov chains, Poisson processes, renewal theory, Brownian motion |
Year 2 - Specialisations
| Stream | Key Courses |
|---|---|
| Applied Statistics | Actuarial Statistics, Biostatistics, Computational Statistics, Finance |
| Theoretical Statistics | Advanced Inference, Decision Theory, Nonparametric Methods |
| Probability | Advanced Probability Theory, Stochastic Calculus, Random Processes |
| Quantitative Economics | Microeconomics, Macroeconomics, Econometrics (for economics-background students) |
CSO Training
All M.Stat students undergo mandatory training at the Central Statistics Office (CSO), New Delhi after Year 1 - providing hands-on exposure to national-level statistical data collection, processing, and analysis.
M.Stat Programme Structure & Credit Distribution
M.Stat Year-Wise Programme Structure
| Year / Semester | Focus | Key Activities |
|---|---|---|
| Year 1 - Sem I | Core Statistical Theory | Probability Theory (measure-theoretic), Statistical Inference, Linear Models, Multivariate Analysis, Computing with R/Python |
| Year 1 - Sem II | Advanced Core + Applied | Large Sample Theory, Stochastic Processes, Sample Surveys, Design of Experiments, additional core courses |
| Summer (May-Jun) | CSO Training | Mandatory training at Central Statistics Office, New Delhi |
| Year 2 - Sem III | Specialisation | Stream-specific courses: Applied Statistics, Theoretical Statistics, Probability, or Quantitative Economics |
| Year 2 - Sem IV | Advanced Specialisation + Placement | Advanced electives in chosen specialisation. Campus placements (typically Dec-Mar). |
Course Load
- B-stream (ISI B.Stat graduates): 20 courses across 4 semesters
- NB-stream (External candidates): 21 courses across 4 semesters (1 additional bridging course)
Skills Developed in M.Stat
Skills Required & Acquired in M.Stat
Skills Required for Admission
Undergraduate-level knowledge of probability, statistical methods, inference, and mathematical statistics. The entrance exam tests these rigorously.
Comfort with real analysis, linear algebra, and calculus. Ability to work with proofs and abstract mathematical concepts.
Ability to formulate problems mathematically, identify appropriate statistical methods, and interpret results rigorously.
Basic programming experience (R/Python) and comfort with computational problem-solving are beneficial.
Skills Acquired During M.Stat
Measure-theoretic probability, Bayesian inference, large sample theory, nonparametric methods - at a depth that places ISI graduates among the world's best-trained statisticians.
Multivariate analysis, time-series modelling, regression techniques, and experimental design - practical tools for data science and research roles.
Proficiency in R, Python, SAS for statistical analysis, simulation, and machine learning. Computational statistics and Monte Carlo methods.
Deep knowledge in chosen specialisation - actuarial methods, biostatistics, stochastic calculus, or econometrics - making graduates specialists in their domain.
Statistical learning theory, classification, clustering, dimension reduction - the mathematical underpinnings of ML that ISI teaches at a deeper level than computer science programmes.
Ability to design studies, collect data, apply appropriate methods, and communicate findings - essential for both academic research and industry analytics.