Philosophical Foundations of Data Analysis

1

What counts as evidence

Introductory lesson of the Philosophical Foundations of Data Analysis module.

2

Aristotle and the Four Causes

How Aristotle's framework of the four causes helps understand why phenomena occur in data.

Prerequisites: 1

3

David Hume: experience, mental habit, and skepticism

Why induction is a mental habit, not a logical law, and what it means for data analysis.

Prerequisites: 1

4

Francis Bacon: induction and idols of the mind

Cognitive biases that distort data interpretation, from 1620 to today.

Prerequisites: 1

5

Immanuel Kant: causality as a category of the intellect

Kant and the idea that causality is not in the data but in the structure of the human mind.

Prerequisites: 1

6

Karl Popper: falsifiability and experimentation

Why a test that confirms your hypothesis is not worth as much as one that could disprove it.

Prerequisites: 1

7

Thomas Kuhn: scientific paradigms and data culture

How collective paradigms determine what an organization considers “true” in data.

Prerequisites: 1

8

Judea Pearl, DAG, and the causal revolution

How Pearl transformed statistics from descriptive to causal and what it means for the analyst.

Prerequisites: 1

9

Frequentism vs Bayesianism: two ways to interpret uncertainty

Two opposing philosophies of probability and their practical consequences in data analysis.

Prerequisites: 1

10

Data epistemology: what you can really know

The limits of knowledge obtainable from data and how to distinguish what you know from what you think you know.

Prerequisites: 1

11

Algorithm ethics and analytical responsibility

What it means to be ethically responsible when working with data and algorithms.

Prerequisites: 1

12

Correlation, causation, and counterfactuals

Because 'correlation does not imply causation' is only the beginning of the story.

Prerequisites: 1

13

Models, assumptions, and misspecification

Hidden assumptions in statistical models and how to recognize them before they cause damage.

Prerequisites: 1

14

Measurement theory: what it means to measure well

How to distinguish between what you measure and what you want to measure, and why the difference matters.

Prerequisites: 1

15

Simpson's paradox and confounding

Why aggregated and disaggregated data tell opposite stories.

Prerequisites: 1

17

Scientific method applied to data work

How to Turn Daily Analytical Work into a Rigorous Scientific Process.

Prerequisites: 1

18

Uncertainty, risk, and ignorance

How to distinguish what you know, what you can estimate, and what you cannot even imagine.

Prerequisites: 1

19

From classical causality to the future of data analysis

How causal thinking is redefining the analyst’s role in the AI era.

Prerequisites: 1

20

Case Study: Philosophical Thinking and Business Decision

Practical Lab: Apply the entire philosophy module to a real case.

Prerequisites: 1

20

Index — Philosophical Foundations of Data Analysis

Map of the module on philosophical foundations for the modern analyst.