{"blocks": [{"key": "72f993f3", "text": "Scenario", "type": "header-two", "depth": 0, "inlineStyleRanges": [], "entityRanges": [], "data": {}}, {"key": "f8a04990", "text": "A mobile-app redesign is shipped as a new version; users opt-in by upgrading, so a standard A/B test is not possible.", "type": "unstyled", "depth": 0, "inlineStyleRanges": [], "entityRanges": [], "data": {}}, {"key": "87705bcf", "text": "Question", "type": "header-two", "depth": 0, "inlineStyleRanges": [], "entityRanges": [], "data": {}}, {"key": "3a510bb5", "text": "How would you measure the causal impact of the redesign when users self-select into the new version? Describe the causal-inference framework you would use, how you would construct comparable treatment/control groups, which features you would match or weight on besides past engagement, and how you would validate your assumptions.", "type": "unstyled", "depth": 0, "inlineStyleRanges": [], "entityRanges": [], "data": {}}, {"key": "00e76ca6", "text": "Hints", "type": "header-two", "depth": 0, "inlineStyleRanges": [], "entityRanges": [], "data": {}}, {"key": "294ec41a", "text": "Explain propensity-score matching/weighting, covariate selection, balance checks, difference-in-differences or other robustness tests.", "type": "unstyled", "depth": 0, "inlineStyleRanges": [], "entityRanges": [], "data": {}}], "entityMap": {}}