Causality

  • Two things: Structure of the graph, relations
  • Packages: Causaleffect, daggity, dowhy, causalinference, causalnex
  • Moderation
    • Moderator, X affects Y differently depending on what M is
    • When callous traits are low, video games aren’t associated with violence much, but when it’s high, there is a higher association
    • Included as interaction terms in regression
  • Difference in differences
    • Example of food program in schools in city A
    • If there is a comparable city B, (R_t2_A - R_t1_A) - (R_t2_B - R_t1_B)

Links

  • https://emilyriederer.netlify.app/post/resource-roundup-causal/
  • https://github.com/larsroemheld/causalinf_ex_elasticity
  • https://towardsdatascience.com/be-careful-when-interpreting-predictive-models-in-search-of-causal-insights-e68626e664b6
  • https://github.com/larsroemheld/causalinf_ex_elasticity
  • https://emilyriederer.netlify.app/post/causal-design-patterns/
  • https://www.oreilly.com/radar/what-is-causal-inference/

Books reccos:

  • Trustworthy Online Controlled Experiments
  • Mostly Harmless Econometrics
  • Mastering Metrics
  • Causal Inference: The Mixtape
  • Chicago Guide to Writing About Multivariate Analysis
  • Agile Data Science 2.0
  • Measure What Matters

Notes mentioning this note

Data Science
[[Don’t make type 3 errors]]

Here are all the notes in this garden, along with their links, visualized as a graph. If you don't see any nodes try zooming and panning in the grey area.