CRITICAL THINKING FOR ANALYTICS AND DATA SCIENCE

Working with data effectively requires more than just a good data analytics toolset. The necessity of well applied critical thinking skills when working with data cannot be overstated.

Crucial skills include tracking assumptions – their origins, their implications, and most importantly, the validity of inferences drawn from them – as well as conscious and unconscious biases, and statistical reasoning. These necessary skills can be easily overlooked in the context of creating and applying particular analytics dataset lifecycles and models, regardless of the technology ecosystem. This is unfortunate, as these skills are essential to preventing insidious foundational errors from creeping into data projects.

The two day Critical Thinking for Analytics and Data Science course aims at developing these critical thinking skills. The course spans a broad range of topics, including some technical content, but focuses on cultivating a high level understanding of what applying critical thinking skills requires. The course is delivered not only in the form of presentations, but also through practical exercises, as well as reference material and notes.

Topics covered include the following:

  • Identifying and distinguishing between the rhetorical aspect of claims and their substantive content.

  • Resolving ambiguity and vagueness in language.

  • Understanding what specific arguments really mean, what justification is provided for them, and whether they succeed or fail on those terms.

  • Distinguishing between the validity and soundness of arguments.

  • How to raise useful and pertinent questions that develop understanding.

  • Metacognition and actively applying scepticism and critical thinking to one’s own positions.

  • Recognising the difference between belief and truth, and attributing fallibility and knowledge.

  • Accurately ascribing reliability and the limits of authority.

  • The mitigation of unintentional bias, and deliberate deception.

  • The basic conceptual tools of formal logic (propositional logic, set theoretic reasoning), and statistical reasoning.