Data Science

Level 2 of 3

Intermediate Level

Prerequisites

Data Science Beginner level, or equivalent: pandas basics, descriptive statistics, simple charts and data privacy principles.

Duration

8 weeks · 90 guided hours · 6 modules. Taught live by an instructor — online or in person.

By the end of this level you can

  • Design data collection and handle survey data, including weights
  • Reshape, merge and clean complex data sets efficiently
  • Test hypotheses and estimate effects with appropriate statistical methods
  • Use regression to describe relationships and recognise confounding
  • Produce reproducible reports and dashboards for monitoring

Modules

  1. 1Module 1 · 15 h · 3 lessonsData Collection and Survey Data
  2. 2Module 2 · 16 h · 3 lessonsData Wrangling with pandas and NumPy
  3. 3Module 3 · 16 h · 3 lessonsStatistical Inference
  4. 4Module 4 · 13 h · 3 lessonsRelationships and Regression for Analysis
  5. 5Module 5 · 13 h · 3 lessonsReporting and Dashboards
  6. 6Module 6 · 17 h · 3 lessonsIntermediate Data Science Project

Intermediate level project

Education Programme Monitoring Analysis

Combine a provided school census, attendance records and a household survey (all synthetic) to report on an education programme's indicators, test whether attendance differs between groups and deliver a reproducible report and a simple dashboard.

Deliverables

  • A cleaning and merging notebook with a data dictionary
  • Indicator tables with confidence intervals, using survey weights where needed
  • Two hypothesis tests and one regression analysis with interpretation
  • A reproducible report and a dashboard prototype

Assessed on

  • Data is merged correctly with documented checks of row counts and keys
  • Statistical methods suit the data and results are interpreted with uncertainty
  • Confounding and limits are discussed honestly
  • The report regenerates from raw data with one command

All levels are taught live by an instructor — online or in person — see registration options.