D'Math University | Statistics & Data Science  ·  Programme #12

MSc Statistics

An intensive one-year postgraduate programme for mathematics and statistics graduates seeking advanced expertise in statistical theory and application. Develop the skills to lead research, consult in industry, or pursue doctoral study with confidence.

Postgraduate 1 Year Online Research-Ready
10
Core Specialist Modules
£58k
Average Graduate Salary
40+
Global Partner Institutions
2,000+
Alumni Worldwide

Programme Overview

The MSc Statistics is designed for graduates with a strong quantitative background who wish to deepen their expertise in statistical science. The curriculum covers advanced theory alongside powerful computational tools — Python, R, and SAS — enabling graduates to conduct original research and lead analytical teams in complex real-world settings.

A dissertation or applied research project in Semester 2 allows students to specialise in biostatistics, econometrics, spatial analysis, or machine learning for statistics, supported by faculty supervisors with active research portfolios.

What You'll Learn

  • Advanced Statistical Theory: Exponential families, sufficiency, completeness, UMVUE
  • Generalised Linear Models: Logistic, Poisson, multinomial, and mixed-effects models
  • Machine Learning for Statisticians: Supervised/unsupervised learning with statistical rigour
  • Time Series Analysis: ARIMA, GARCH, state-space models, spectral analysis
  • Survival Analysis: Kaplan-Meier, Cox regression, competing risks
  • Multivariate Methods: Factor analysis, MANOVA, canonical correlation
  • Spatial Statistics: Geostatistics, kriging, spatial autocorrelation
  • Statistical Programming: Advanced R, Python (statsmodels, scipy), SAS procedures
Core Curriculum
🧮

Advanced Statistical Theory

Decision theory, sufficiency, completeness, and UMVUEs in the context of exponential families and Bayesian paradigms.

📊

Generalised Linear Models

Theory and application of GLMs — logistic, Poisson, gamma, negative binomial, and mixed-effects extensions.

🤖

Machine Learning for Statisticians

Statistical perspective on classification, regression trees, ensemble methods, and model selection criteria.

📉

Time Series Analysis

ARIMA/SARIMA, GARCH volatility modelling, state-space representations, Kalman filtering, and forecasting.

🧪

Experimental & Clinical Trials

Randomised controlled trial design, adaptive trial methods, sample size calculation, and regulatory considerations.

📐

Multivariate Methods

MANOVA, principal components, factor analysis, canonical variates, and multidimensional scaling.

💻

Statistical Programming

Advanced workflows in Python (pandas, scipy, statsmodels), R (tidyverse, caret), and SAS for large-scale data analysis.

🔬

Survival Analysis

Life tables, Kaplan-Meier curves, parametric models, Cox proportional hazards, and frailty models.

Course Catalogue

Click any course to view its objective and learning outcomes.

STA 501 Statistical Inference +

Objective

To establish frequentist inference at advanced level.

Learning Outcomes

  • Apply MLE and likelihood ratio tests.
  • Use UMP and unbiased tests.
  • Apply asymptotic theory.
  • Use sufficient and complete statistics.
  • Apply Bayesian decision theory.
Interactive Activity — Distribution Plotter
Pick a distribution and adjust its parameters. Read off mean and variance directly from the plot.
Distribution: p1 = 0.0 p2 = 1.0
Interactive Activity — Central Limit Theorem Simulator
Sample n values, take their average, repeat. The histogram of averages converges to a normal distribution — CLT in action.
Source: Sample size n = 10
Total sample means: 0
Interactive Activity — Hypothesis Testing Visualizer
Set null hypothesis μ₀, sample mean x̄, sample size n and σ. The activity computes the z-statistic, p-value (shaded tail), and tells you whether to reject H₀ at significance α.
μ₀ = x̄ = σ = n =
α = 0.050 Tail:
STA 502 Linear Models +

Objective

To fit, diagnose and select linear models rigorously.

Learning Outcomes

  • Apply OLS rigorously.
  • Use generalised linear models.
  • Apply mixed-effects models.
  • Use variable selection.
  • Apply regularisation.
STA 503 Bayesian Statistics +

Objective

To apply Bayesian inference to advanced problems.

Learning Outcomes

  • Apply MCMC methods.
  • Use variational inference.
  • Apply hierarchical models.
  • Use Bayesian model comparison.
  • Apply Bayesian decision theory.
Interactive Activity — Distribution Plotter
Pick a distribution and adjust its parameters. Read off mean and variance directly from the plot.
Distribution: p1 = 0.0 p2 = 1.0
Interactive Activity — Central Limit Theorem Simulator
Sample n values, take their average, repeat. The histogram of averages converges to a normal distribution — CLT in action.
Source: Sample size n = 10
Total sample means: 0
STA 504 Multivariate Analysis +

Objective

To analyse multivariate datasets rigorously.

Learning Outcomes

  • Apply PCA and factor analysis.
  • Use canonical correlation analysis.
  • Apply MANOVA.
  • Use clustering methods.
  • Apply discriminant analysis.
STA 505 Time Series Analysis +

Objective

To analyse and forecast time series.

Learning Outcomes

  • Fit ARIMA and GARCH models.
  • Apply state-space models.
  • Use spectral analysis.
  • Apply VAR models.
  • Forecast with uncertainty.
Interactive Activity — Sequence Convergence
Pick a sequence and an ε. The graph shows when a_n enters the ε-band around limit L. The smallest such N is the "epsilon-N" for convergence.
a_n = ε = 0.10
Interactive Activity — Epsilon-Delta for Continuity
For f(x) = x², set the point a and tolerance ε. The activity finds the largest δ such that |x − a| < δ ⟹ |f(x) − f(a)| < ε.
a = 1.0 ε = 0.50
STA 506 Survival Analysis +

Objective

To analyse time-to-event data including censoring.

Learning Outcomes

  • Estimate Kaplan-Meier curves.
  • Apply Cox regression.
  • Use parametric models.
  • Apply competing risks.
  • Address censoring.
Interactive Activity — Distribution Plotter
Pick a distribution and adjust its parameters. Read off mean and variance directly from the plot.
Distribution: p1 = 0.0 p2 = 1.0
Interactive Activity — Central Limit Theorem Simulator
Sample n values, take their average, repeat. The histogram of averages converges to a normal distribution — CLT in action.
Source: Sample size n = 10
Total sample means: 0
Interactive Activity — Gompertz Survival Curve
Pick mortality preset or adjust the Gompertz scale c. The activity plots S(x) and h(x), then reads off the probability of surviving from age x.
c (slope) = 1.100 age x = 30
STA 507 Categorical Data Analysis +

Objective

To model count and categorical outcomes.

Learning Outcomes

  • Apply chi-squared tests.
  • Fit logistic regression.
  • Apply multinomial regression.
  • Use log-linear models.
  • Apply GEEs.
STA 508 Nonparametric Statistics +

Objective

To apply distribution-free statistical methods.

Learning Outcomes

  • Apply kernel density estimation.
  • Use rank-based tests.
  • Apply spline regression.
  • Use bootstrap.
  • Apply permutation tests.
STA 509 Causal Inference +

Objective

To estimate causal effects from observational data.

Learning Outcomes

  • Apply potential-outcomes framework.
  • Use propensity scores.
  • Apply instrumental variables.
  • Use difference-in-differences.
  • Apply DAGs.
Interactive Activity — Distribution Plotter
Pick a distribution and adjust its parameters. Read off mean and variance directly from the plot.
Distribution: p1 = 0.0 p2 = 1.0
Interactive Activity — Central Limit Theorem Simulator
Sample n values, take their average, repeat. The histogram of averages converges to a normal distribution — CLT in action.
Source: Sample size n = 10
Total sample means: 0
Interactive Activity — Correlation Explorer
Generate 100 sample points with a chosen correlation ρ. Compare Pearson r, Spearman ρ_s, and Kendall τ. See how the scatter pattern changes.
ρ = 0.70
STA 510 Statistical Computing +

Objective

To use computational methods for advanced inference.

Learning Outcomes

  • Apply MCMC samplers.
  • Use EM algorithm.
  • Apply variational methods.
  • Use bootstrap.
  • Implement reproducible analysis.
STA 511 Sampling Theory +

Objective

To design surveys and sampling schemes.

Learning Outcomes

  • Apply simple random sampling.
  • Use stratified and cluster sampling.
  • Apply weighting and post-stratification.
  • Address non-response.
  • Use complex survey designs.
Interactive Activity — Distribution Plotter
Pick a distribution and adjust its parameters. Read off mean and variance directly from the plot.
Distribution: p1 = 0.0 p2 = 1.0
Interactive Activity — Central Limit Theorem Simulator
Sample n values, take their average, repeat. The histogram of averages converges to a normal distribution — CLT in action.
Source: Sample size n = 10
Total sample means: 0
STA 512 Master's Project +

Objective

To complete an original statistics research project.

Learning Outcomes

  • Identify a research-quality problem.
  • Apply rigorous methodology.
  • Use real datasets.
  • Write a 15,000-word dissertation.
  • Defend orally.
Career Pathways
📊

Senior Statistician

Lead statistical analysis programmes in government agencies, think tanks, or large research institutions.

💼

Statistical Consultant

Advise businesses and research teams on study design, data collection strategies, and analytical methods.

🏥

Biostatistician

Design and analyse clinical studies for pharmaceutical companies, CROs, and academic medical centres.

🤖

Data Scientist

Apply advanced statistical models and machine learning to product, risk, and research problems in tech firms.

🎓

Research Director

Oversee statistical methodology for research programmes at universities or national research councils.

💹

Financial Risk Analyst

Model credit risk, market risk, and portfolio performance using advanced statistical and econometric tools.

Top Universities Offering This Programme
Stanford University Harvard University University of Oxford Columbia University University of Chicago University of Cambridge University of Toronto University of Melbourne National University of Singapore Lund University

Why D'Math University

01

Research-Led Teaching

All modules are taught by active researchers with publications in top statistical journals including JRSS, Biometrika, and JASA.

02

Multi-Software Proficiency

Graduate fluent in Python, R, and SAS — the three most demanded statistical computing environments in industry and academia.

03

Dissertation Flexibility

Choose your dissertation track: applied industry project, theoretical research paper, or a collaborative study with a partner institution.

04

PhD Pathway

High-performing MSc graduates are fast-tracked into our PhD Statistics programme with scholarship opportunities.

Enrol in MSc Statistics →

Cohorts begin each January and September — limited places available