DATA2902: Data Analytics — Learning from Data (Advanced)

Learning Outcomes

• Problem formulation: Frame domain-specific questions and select appropriate statistical analyses.
• Data acquisition & integration: Extract, join, and harmonise data from multiple sources.
• Summarisation & EDA: Build numerical and graphical summaries for varied—and large/complex—datasets.
• Version control: Use a software version-control system (e.g., Git) effectively in analytics workflows.
• Statistical inference: Choose, justify, and implement suitable parametric or non-parametric tests.
• Linear modelling: Formulate, fit, and interpret linear models for multi-factor relationships.
• Statistical ML: Apply a given classifier, design cross-validation, and report predictive accuracy.
• Reproducible reporting: Produce reproducible reports (R Markdown/Quarto) that communicate results clearly to stakeholders.

Takeaways

Coming soon.