Data Analytics in Practice
Work like a mid-level data analyst: define KPIs, forecast, run and analyse A/B tests, model analytics tables and turn stakeholder requests into recommendations.
Leads to: Data Analyst
Before you start
This course builds on Data Visualization & Storytelling and SQL for Analysis. Take them first if you are new to the topic.
About this course
This mid-level course covers the parts of a data analyst's job that come after the basics: deciding what to measure, running experiments, owning reliable tables and working with the people who ask the questions. It builds on Data Visualization & Storytelling and SQL for Analysis. The first module is about metrics: defining a KPI with an exact formula in SQL, redesigning a dashboard around decisions, and making a simple trend-plus-seasonality forecast in Python. The second module covers A/B testing from start to finish: sizing a test with a power calculation, analysing results with lift, a confidence interval and a p-value, and spotting common pitfalls such as peeking, novelty effects and sample ratio mismatch. The third module introduces analytics engineering: modelling fact and dimension tables, the dbt approach of transformations and tests as version-controlled code, and data quality checks that run with every load. The last module is about stakeholders: scoping a vague request into a brief, presenting a recommendation with honest caveats, and publishing an end-to-end portfolio case study. Code exercises run in your browser (SQLite and Python); practical steps use free tools and public data.
Course content
Module 1
Metrics
3 lessons · 1h 45mDefine KPIs with exact formulas, rebuild dashboards around decisions, and make a simple trend-and-seasonality forecast.
- 25mDefining KPIsReading
Turn a vague goal into a key performance indicator with an exact, testable formula.
- 49mDashboards people useReading
Audit an existing dashboard and rebuild it around the decisions its users actually make.
- 31mSimple forecastingReading
Forecast a business metric from its trend and seasonality, and check the forecast against held-out data.
Module 2
Experiments
3 lessons · 1h 44mPlan, size and analyse A/B tests, and avoid the mistakes that make experiment results untrustworthy.
- 44mA/B test designReading
Plan an A/B test with a clear hypothesis, primary metric and sample size before it starts.
- 29mAnalysing a testReading
Compute lift, a confidence interval and a p-value for an A/B test, and report the result honestly.
- 31mExperiment pitfallsReading
Recognise peeking, multiple comparisons, novelty effects and other traps that make A/B results untrustworthy.
Module 3
Analytics Engineering
3 lessons · 1h 52mModel clean fact and dimension tables, treat transformations as tested code, and own the quality of the data you publish.
- 43mModelling analytics tablesReading
Design fact and dimension tables (a star schema) so analysis queries are simple, fast and consistent.
- 22mTransformations as codeReading
Explain how dbt-style projects turn SQL transformations into version-controlled, tested, documented models.
- 47mData quality ownershipReading
Own the quality of the tables you publish with automated checks, thresholds, alerts and clear incident handling.
Module 4
Working With Stakeholders
3 lessons · 2h 21mScope requests into clear briefs, present recommendations with honest caveats, and publish a portfolio case study.
- 40mScoping requestsReading
Turn a vague stakeholder request into a clear analysis brief with a decision, questions, scope and deadline.
- 42mMaking recommendationsReading
Present a clear recommendation backed by evidence, with honest caveats, options and a specific ask.
- 59mPortfolio case studyReading
Plan, complete and publish an end-to-end analytics case study that shows employers how you work.