Principles for building Analytic Graphics - General Rules

Principle # 1 - Show Comparisons

  • Evidence is always relative to another competing hypothesis

  • Always ask “Compared to what?”

Principle # 2 - Show Causality, mechanism, explanation, systematic structure

  • What is your causual framework for thinking about a question?

  • Causal : defined as how “you” believe the world is working - so to speak. What is the explanation for the phenomenon.

  • Ask why? Then show plot to corroborate that perspective.

  • Then SHOW it via plots from the data.

  • To really confirm this is the case, a more righorous statistical process must be undertaken, but this is a good start.

Principle # 3 - Show multivariate data - show as much data on a single plot as you can.

  • Multivariate = more than 2 variables

  • The real world is inherently Multivariate

  • Need to escape the flatland.

Principle # 4 - Integration of evidence - use as many modes as evidence as you can. Combine as many modes of evidence into a single graphic (presentation) to make it as information rich as possible.

  • Completely integrate words, numbers, images, diagrams.

  • Data graphics should make use of many modes of data presentation

  • Don’t let the tools drive the analysis - you make the plot you want to make, don’t let the tools do the thinking.

Principle # 5 - Describe and document the evidence with appropriate lables, scales, sources, etc.

  • data graphic should a complete story that is credible

  • preserve the code that made the plot.

Principle # 5 - Content is king!

  • analytical presenations ultimately stand or fall depending on the quality, relevance, and inegrity of their content.

Notes:

Notes: