Causal Inference and Confounding Questions
Foundational concepts and methods for reasoning about cause and effect and for estimating causal effects from experimental and observational data. Topics include the distinction between correlation and causation, causal graphs and directed acyclic graphs, sources of confounding bias, randomized experiments, instrumental variable approaches, difference in differences, regression discontinuity designs, propensity score methods, sensitivity analysis, diagnostics for assumptions, and considerations for external validity and transportability.
HardTechnical
30 practiced
Leadership wants to know whether a price change last year caused the drop in retention, but there was no A/B test, the price change rolled out to everyone at once. Walk me through how you'd approach estimating a causal effect here, and what would make you trust or distrust the result.
EasyTechnical
37 practiced
Before you run a regression to estimate a causal effect, why would you first want to sketch out a causal diagram (a DAG) of the variables involved?
EasyTechnical
41 practiced
Why are randomized experiments considered the gold standard for establishing causality, compared to analyzing data you already have sitting in a warehouse?
MediumTechnical
52 practiced
Customers who spend over $500 in a year automatically get moved into your loyalty program's gold tier. Marketing wants to know if gold status itself increases future spend. How could a regression discontinuity design answer this, and where does its causal claim actually apply?
MediumTechnical
39 practiced
Users who enable your product's advanced analytics dashboard retain at a much higher rate than those who don't. Is this confounding, selection bias, or could it be both? How would you tell the difference in your analysis?
Unlock Full Question Bank
Get access to hundreds of Causal Inference and Confounding interview questions and detailed answers.
Sign in to ContinueJoin thousands of developers preparing for their dream job.