Statistical Inference and Model Validation

Programme outline

Learning objectives
  • Apply hypothesis testing principles, including the interpretation of p-values (probability values) and test statistics.
  • Implement parametric testing methods such as the Z-test, T-test (Student’s t-test) and ANOVA(Analysis of Variance) using Python.
  • Implement non-parametric tests such as the Wilcoxon Signed Rank and Chi-Square using Python.
  • Assess data normality using graphical and numerical approaches.
  • Validate the appropriateness of a selected statistical model.
Day 1
  • Hypothesis Testing – Intuition of hypothesis testing, P-value & significance level, test statistics & critical value, confidence intervals, type I and II errors
  • Parametric testing – Z-test, T-test, Pearson-correlation, ANOVA, ANCOVA
  • Normality testing – Graphical and numerical approaches
Day 2
  • Data transformation – Log-transformation, Normalisation, Standardisation
  • Non-parametric testing – Wilcoxon signed rank, Mann-Whitney U, Chi-Square, Kruskal-Wallis, Friedman, Spearman-Correlations.
  • Tests for Independence – Chi-Square, Fisher’s exact test
Day 3
  • Project consultation
  • Project presentation
Mode of assessment
  • Assignment
  • Project
What’s next

Find out more

Mailing list

Subscribe to our mailing list and learn about the latest developments in SUTD Academy.

Get in touch

Submit an enquiry or schedule a call with our friendly team at +65 6499 7171.