Learning path

How the course is organised, and what to study before what

The four levels of the course, the dependencies between modules and the full list of lessons with estimated study times.

The course grows in four levels. Each level uses the tools of the previous ones, and each lesson lists its own prerequisites at the top. The total self-study time is roughly 85 hours (excluding the capstone), which matches a university module of up to 9 ECTS.

The map

flowchart LR
  subgraph L1["Level 1 · R foundations"]
    M1["1 · Getting started"] --> M2["2 · Working with data"]
    M1 --> M3["3 · Programming"]
    M2 --> M4["4 · Data in and out"]
  end
  subgraph L2["Level 2 · Describe & explore"]
    M5["5 · Descriptive statistics"] --> M6["6 · Visualisation"]
  end
  subgraph L3["Level 3 · Uncertainty & inference"]
    M7["7 · Probability & simulation"] --> M8["8 · Statistical inference"]
  end
  subgraph L4["Level 4 · Models & learning"]
    M9["9 · Regression models"] --> M10["10 · Supervised learning"]
    M11["11 · Dimensionality reduction"] --> M12["12 · Clustering"]
    M10 -.-> M13["13 · Deep learning (optional)"]
  end
  M4 --> M5
  M6 --> M7
  M8 --> M9
  M6 --> M11
  M3 -.-> M7
  M10 --> CAP(["Capstone project"])
  M12 --> CAP

Modules and their main dependencies. Solid arrows: required; dashed arrows: helpful.

What each level gives you

Level You will be able to… Key statistical ideas
1 · R foundations write R code, organise a project, import, clean, reshape and summarise data types of variables, units and observations, tidy data, missing-data mechanisms
2 · Describe & explore describe a dataset with tables, numbers and graphics, and spot patterns distributions, location and spread, robustness, association vs causation
3 · Uncertainty & inference quantify uncertainty and test hypotheses, and explain results correctly probability, sampling variability, standard error, CLT, bootstrap, CIs, p-values, power, effect sizes
4 · Models & learning fit, check, compare and interpret statistical and machine-learning models conditional means, GLMs, overfitting, cross-validation, regularisation, latent structure, clustering

All lessons

1. Getting started (Level 1)

# Lesson Time
01 What is R? ~40 min
02 First steps in R ~50 min
03 Data types and operators ~60 min
04 Vectors ~60 min
05 Matrices ~50 min
06 Factors and types of variables ~60 min
07 Lists ~50 min

2. Working with data (Level 1)

# Lesson Time
08 Data frames and tibbles ~60 min
09 Data manipulation with dplyr ~75 min
10 Grouped summaries ~60 min
11 Joining tables ~60 min
12 Tidy data and reshaping ~60 min
13 Strings, factors and dates ~75 min

3. Programming (Level 1)

# Lesson Time
14 Writing functions ~60 min
15 Conditionals: if, else and friends ~45 min
16 Loops: for, while and repeat ~60 min
17 Iteration with apply and purrr ~60 min

4. Data in and out (Level 1)

# Lesson Time
18 Importing data ~60 min
19 Exporting data and results ~40 min
20 Missing data ~75 min

5. Descriptive statistics (Level 2)

# Lesson Time
21 Frequency tables ~60 min
22 Summary statistics ~75 min
23 Describing two variables ~75 min

6. Visualisation (Level 2)

# Lesson Time
24 The grammar of graphics ~75 min
25 Plotting distributions ~75 min
26 Plotting categorical data ~60 min
27 Correlation ~75 min

7. Probability & simulation (Level 3)

# Lesson Time
28 Randomness and simulation ~75 min
29 Probability distributions ~80 min
30 Sampling distributions ~80 min
31 The bootstrap ~75 min

8. Statistical inference (Level 3)

# Lesson Time
32 Confidence intervals ~70 min
33 The logic of hypothesis testing ~90 min
34 t-tests: comparing means ~75 min
35 Proportions and chi-square tests ~80 min
36 Non-parametric tests ~70 min
37 Analysis of variance (ANOVA) ~90 min

9. Regression models (Level 4)

# Lesson Time
38 Simple linear regression ~90 min
39 Multiple regression ~100 min
40 Model selection and validation ~90 min
41 Logistic regression ~120 min
42 Poisson regression ~100 min
43 Penalized regression: ridge, lasso and elastic net ~120 min

10. Supervised learning (Level 4)

# Lesson Time
44 The machine-learning workflow ~120 min
45 Decision trees ~90 min
46 Random forests ~90 min
47 Gradient boosting ~100 min
48 Support vector machines ~100 min
49 Comparing and choosing models ~90 min

11. Dimensionality reduction (Level 4)

# Lesson Time
50 Principal component analysis ~90 min
51 Factor analysis ~100 min
52 Correspondence analysis ~80 min
53 Multidimensional scaling ~75 min
54 t-SNE and UMAP ~90 min

12. Clustering (Level 4)

# Lesson Time
55 Clustering: the big picture ~70 min
56 k-means clustering ~90 min
57 Hierarchical clustering ~80 min
58 DBSCAN: density-based clustering ~80 min
59 Model-based clustering: Gaussian mixtures ~90 min
60 Spectral clustering ~90 min

13. Deep learning (Optional)

# Lesson Time
61 Deep learning: ideas and set-up ~60 min
62 Deep neural networks for tabular data ~90 min
63 Autoencoders ~75 min
64 Recurrent networks and LSTM for time series ~90 min
65 GRU networks for text classification ~90 min
66 Convolutional neural networks for images ~90 min

Capstone

# Lesson Time
67 Capstone project project
Back to top