Causal Impact of Traffic Throttling on Flagged Sellers

Context

A traffic throttling policy was launched for sellers flagged as risky. Because the rollout lacked a clean A/B test, you must estimate the causal impact of throttling on abuse and business KPIs using observational data. Primary outcomes include:

• complaint_per_1k_orders (abuse proxy)
• GMV (gross merchandise volume)

Tasks

(a) Specify the causal estimands (e.g., average treatment effect on treated sellers) for both outcomes.

(b) Propose two credible quasi-experimental designs and when each is valid:

• Regression Discontinuity (RD) around the risk-score threshold that triggers throttling. Detail bandwidth selection, manipulation checks, and local polynomial specification.
• Difference-in-Differences (DiD) / Event Study with staggered adoption. Describe constructing a matched control group, testing pre-trends, choosing an estimator robust to staggered timing (e.g., Sun–Abraham), clustering of standard errors, and handling dynamic effects.

(c) Define the analysis window, unit of observation, and how to handle treatment intensity (dose = percent rank penalty or impression share reduced).

(d) List at least three robustness/validity checks (e.g., placebo thresholds, negative-control outcomes, falsification on pre-policy periods, sensitivity to trimming top-GMV sellers, bounding bias from misclassification).

(e) Explain how you would detect and adjust for spillovers (e.g., seller migration to new accounts) and survivorship bias.