MAT202-S28 · Mathematics · Semester 4
Probability Theory and Statistics
The mathematics of uncertainty and of learning from data: probability theory, statistical inference and computational methods.
- Format
- Self-paced
- Status
- Status: planned, not offered yet
- Programme
- Foundation programme · Semester 4
- Term
- Spring 2028
- Credits
- 8 ECTS
- Study hours
- 240
- Prerequisites
- MAT231-F27 Calculus II, MAT102-S27 Linear Algebra
- Module leader
- Dr. Ali Khudiyev
- ali.khudiyev@wosm.academy
- Office hours
- Monday–Friday, 10:00–17:00 (Baku time, UTC+4)
- Language
- English
- Cost
- Free
Module Overview
Probability Theory and Statistics introduces the mathematics of uncertainty and of learning from data. The first part builds probability theory from axioms; the second part uses it to draw conclusions from data with estimation, confidence intervals, hypothesis tests and regression.
The module covers:
- Probability spaces, conditional probability, random variables and their distributions (first 5–6 weeks)
- Expectation, variance, joint distributions, tail bounds and the limit theorems
- Statistical inference: estimation, confidence intervals, hypothesis testing and linear regression
- Computational methods: simulation, Monte Carlo and the bootstrap
Examples come from computer science throughout: randomised algorithms and hashing, the analysis of average-case running time, A/B testing, and the probabilistic foundations of machine learning. Students run simulations and analyse data in short programming assignments.
Aims
- Give a rigorous introduction to probability theory, using the calculus and linear algebra of earlier modules.
- Develop the probabilistic reasoning needed to design and analyse randomised algorithms and systems.
- Introduce the main methods of statistical inference and the assumptions behind them.
- Prepare students for machine learning, data science, information theory and networking.
Learning Outcomes
On successful completion of this module, students will be able to:
- LO1.Model random experiments with probability spaces and compute probabilities using counting, conditional probability, independence and Bayes’ theorem.
- LO2.Work with standard discrete and continuous distributions and compute expectations, variances and distributions of functions of random variables.
- LO3.Handle joint distributions, covariance and conditional expectation, including the multivariate normal distribution.
- LO4.Apply linearity of expectation, indicator variables and the Markov, Chebyshev and Chernoff bounds to analyse randomised algorithms.
- LO5.State and apply the law of large numbers and the central limit theorem.
- LO6.Construct estimators by the method of moments and maximum likelihood, assess their bias and variance, and build confidence intervals.
- LO7.Carry out and interpret hypothesis tests and simple and multiple linear regression, and recognise common misuses of p-values.
- LO8.Use simulation, Monte Carlo methods and the bootstrap to approximate probabilities and quantify uncertainty in code.
Syllabus
| Unit | Topic |
|---|---|
| 1 | Sample spaces, events, the axioms of probability |
| 2 | Counting and equally likely outcomes; birthday problem |
| 3 | Conditional probability; law of total probability; Bayes’ theorem |
| 4 | Independence; randomised algorithms: verifying matrix products, min-cut |
| 5 | Discrete random variables; Bernoulli, binomial, geometric, Poisson |
| 6 | Expectation; linearity of expectation; indicator variables |
| 7 | Variance and moments; coupon collector; balls into bins and hashing |
| 8 | Continuous random variables; uniform, exponential, normal |
| 9 | Functions of random variables; transformations of densities |
| 10 | Joint distributions; marginal and conditional distributions |
| 11 | Covariance and correlation; the multivariate normal distribution |
| 12 | Conditional expectation; law of total expectation; quicksort analysis |
| 13 | Moment generating functions |
| 14 | Tail bounds: Markov, Chebyshev, Chernoff |
| 15 | Laws of large numbers |
| 16 | The central limit theorem |
| 17 | Simulation and Monte Carlo methods |
| 18 | Introduction to Markov chains |
| 19 | Descriptive statistics and exploratory data analysis |
| 20 | Point estimation: method of moments, maximum likelihood |
| 21 | Bias, variance, mean squared error, consistency |
| 22 | Confidence intervals; the t-distribution |
| 23 | Hypothesis testing: z- and t-tests, p-values, errors of type I and II |
| 24 | Chi-squared tests; A/B testing; multiple testing |
| 25 | Linear regression: least squares, inference on coefficients |
| 26 | The bootstrap; introduction to Bayesian inference |
Teaching and Learning Methods
The module is self-paced. All materials are provided on Moodle: lecture notes and recorded lectures for each unit, tutorial problem sheets with worked solutions, short quizzes, and the briefs for the two projects. Problem sheets are for practice and are not marked. Questions are discussed in the module channel on Discord and in office hours. Independent study includes reading, problem sheets and project work.
| Activity | Hours |
|---|---|
| Lectures | 52 |
| Labs / Tutorials | 38 |
| Independent study | 150 |
| Total | 240 |
Assessment
Knowledge is assessed with weekly unit quizzes, two projects and a final exam. Working with simulation and real data is central to the module, so the projects carry slightly more weight.
- Project 1 – Simulation study: simulate a randomised algorithm or hashing scheme, compare the observed behaviour with the expectation and tail bounds derived in the module, and illustrate the law of large numbers and the central limit theorem.
- Project 2 – Data analysis: pose a question about a public data set, estimate parameters, build confidence intervals, carry out a hypothesis test or regression, and use the bootstrap; written up as a short report.
The final exam tests whether students can build a probabilistic model for a problem, carry out the calculations, and choose and interpret an appropriate statistical method.
| Component | Weight | Due | LOs |
|---|---|---|---|
| Unit quizzes (best 10 of 12) | 15% | Weekly | LO1–LO7 |
| Project 1: Simulation study | 20% | Week 7 | LO4, LO5, LO8 |
| Project 2: Data analysis | 25% | Week 12 | LO6–LO8 |
| Final exam (3 hours, written) | 40% | End of term | LO1–LO7 |
| Total | 100% |
Reading List
Essential
- J. K. Blitzstein, J. Hwang: Introduction to Probability, 2nd ed., CRC Press, 2019. Free online at https://probabilitybook.net.
- L. Wasserman: All of Statistics: A Concise Course in Statistical Inference, Springer, 2004.
Recommended
- S. M. Ross: A First Course in Probability, 10th ed., Pearson, 2019.
- C. M. Grinstead, J. L. Snell: Introduction to Probability, 2nd ed., American Mathematical Society, 1997. Free online.
- M. Mitzenmacher, E. Upfal: Probability and Computing, 2nd ed., Cambridge University Press, 2017.
- M. H. DeGroot, M. J. Schervish: Probability and Statistics, 4th ed., Pearson, 2012.
Materials and Licence
Course materials are published under the Creative Commons Attribution-ShareAlike 4.0 licence unless stated otherwise. See wosm.academy/licence for details.
Policies
- Attendance: Attendance is not mandatory. The module is self-paced, so you can study the materials when it suits you.
- Late submissions: Work submitted after the deadline is penalised.
- Academic integrity: All submitted work must be your own. See the Code of Conduct.
Free. No application needed. New to Moodle? See How to join.