01
Data questions
Start with a clear question, outcome, audience and decision context before choosing tools or models.
Data Science pathway
Learn data science with interpretation and responsibility.
This pathway connects data preparation, exploratory analysis, modelling, validation and reporting so learners understand not only what to run, but what the results mean.
Suggested route
02
Data preparation
Understand cleaning, missingness, coding, variable types, outliers and documentation.
03
Exploratory analysis
Use summaries and visualisations to understand distributions, patterns, relationships and anomalies.
04
Modelling and validation
Learn how models are trained, checked, validated and interpreted without overclaiming.
05
Reporting
Communicate results clearly with uncertainty, limitations, practical meaning and reproducible reasoning.
Recommended resources
Read these guides alongside the pathway.
Data analysis · Foundation
How to prepare your data before analysis
5 min read · Updated 5 June 2026
A detailed guide for students learning how to clean, check, structure and document data before running statistical analysis.
Regression · Intermediate
Linear regression assumptions and diagnostics
5 min read · Updated 5 June 2026
A detailed guide to the assumptions behind linear regression, why they matter, how students should think about diagnostics and how to report limitations clearly.
Biostatistics · Intermediate
Logistic regression explained for health and social science students
6 min read · Updated 5 June 2026
A detailed guide to logistic regression for binary outcomes, including odds, odds ratios, interpretation, adjustment, limitations and common reporting mistakes.
Data analysis · Intermediate
Missing data: deletion, imputation and reporting
6 min read · Updated 5 June 2026
An advanced guide to understanding missing data mechanisms, complete-case analysis, imputation, bias, sensitivity and transparent reporting.
Biostatistics · Advanced
ROC curves, sensitivity, specificity and AUC
5 min read · Updated 5 June 2026
An advanced guide to diagnostic test evaluation and prediction model performance, covering sensitivity, specificity, thresholds, ROC curves, AUC and limitations.
Statistics · Advanced
Multiple testing and false discovery rate
5 min read · Updated 5 June 2026
An advanced guide explaining why repeated hypothesis testing increases false positives, how family-wise error and false discovery rate differ, and how to report multiple-testing corrections.
Need guidance?
Submit enquiry → review → match.
If you are unsure how to prepare, analyse or interpret your data, submit an enquiry with your subject, level and topic.
Submit enquiry