Control confounding in observational ad lift
TikTokData Scientist · Onsite
Last updated
This question evaluates mastery of observational causal inference for ATE estimation, covering causal DAGs and identification, pre-treatment adjustment, propensity-score and inverse-probability/doubly-robust estimation, diagnostic checks, sensitivity analysis for unobserved confounding, and variance/uncertainty quantification in the context of ad exposure data. It is commonly asked because real-world advertising analyses cannot rely on randomization and interviewers need assurance of both conceptual understanding of identification assumptions and practical application of estimation and diagnostic techniques; the category is Statistics & Math and the level of abstraction spans conceptual reasoning and applied implementation.
You cannot randomize ad exposure. Users differ in age, education, and income.
Propose a causal inference plan to estimate the ATE of ad exposure on conversions. Include:
(1) a DAG to justify a valid adjustment set; (2) a propensity score model and either matching or inverse-probability weighting with stabilized weights; (3) formulas for ATE via IPW and doubly robust (AIPW) estimators; (4) diagnostics (overlap checks, standardized mean differences before/after, effective sample size, weight trimming); (5) sensitivity analysis to unobserved confounding (e.g., Rosenbaum bounds); (6) avoiding post-treatment bias (exclude engagement mediators); (7) variance estimation and uncertainty reporting.
Discuss when you’d prefer diff-in-diff or CUPED and required assumptions.
Solution walkthrough is for members
Get the full walkthrough with reference code and complexity analysis, plus Kitty Coach at 300 messages a day. Hints, the code runner and community answers stay free.