| Next revision | Previous revision |
| data_analysis:ab_test [2021/02/07 05:56] – created prgram | data_analysis:ab_test [2025/07/07 14:12] (current) – external edit 127.0.0.1 |
|---|
| ====== ab test ====== | ====== A/B test ====== |
| | |
| | AB 테스트 추천 도서 : [[https://www.amazon.com/Trustworthy-Online-Controlled-Experiments-Practical/dp/1108724264|Trustworthy Online Controlled Experiments: A Practical Guide to A/B Testing]] [[https://coupa.ng/b7Omnt|쿠팡]] |
| | 통계적 지식 뿐 아니라 실제 적용에서 고민해야할 문제들에 대한 상세한 설명이 있다. |
| | |
| | |
| | [[data_analysis:convergence_testing]] |
| |
| https://reflectivedata.com/comprehensive-guide-to-statistics-in-a-b-testing/ | https://reflectivedata.com/comprehensive-guide-to-statistics-in-a-b-testing/ |
| https://cdn2.hubspot.net/hubfs/310840/VWO_SmartStats_technical_whitepaper.pdf | |
| https://www.slideshare.net/cojette/ab-150118831 | https://www.slideshare.net/cojette/ab-150118831 |
| https://onlinemix.tistory.com/entry/significant-result-from-ab-testing | https://onlinemix.tistory.com/entry/significant-result-from-ab-testing |
| https://is.muni.cz/th/wt0tu/Humaj-thesis.pdf | |
| https://cxl.com/blog/ab-testing-guide/ | https://cxl.com/blog/ab-testing-guide/ |
| https://hbr.org/2017/06/a-refresher-on-ab-testing | https://hbr.org/2017/06/a-refresher-on-ab-testing |
| |
| | Bayesian |
| | https://is.muni.cz/th/wt0tu/Humaj-thesis.pdf |
| | https://brunch.co.kr/@gimmesilver/15 |
| | [[https://cdn2.hubspot.net/hubfs/310840/VWO_SmartStats_technical_whitepaper.pdf|VWO_SmartStats_technical_whitepaper]] |
| | |
| | |
| | [[https://www.researchgate.net/publication/287927836_Sample_Size_Calculation_for_Two_Independent_Groups_A_Useful_Rule_of_Thumb|Sample size calculation for two independent Groups]] |
| | |
| | |
| | https://www.evanmiller.org/ab-testing/ |
| | |
| | |
| | MAB |
| | http://sanghyukchun.github.io/96/ |
| | https://kw94.tistory.com/49 |
| | https://sumniya.tistory.com/9 |
| | |
| | |
| | ===== 실행순서 ==== |
| | * 가설 : 인터뷰, idea, 기존자료 분석 |
| | * 실험설계 : control/treatment, 지표, bayesian/frequentist |
| | * Random unit : user/session/page |
| | * Target unit : 전체 / segment |
| | * Size : sample, traffic 분배 |
| | * How long : 학습효과 |
| | * 실행 : 모니터링. 오류, 다른 feature들이 떨어지는지, 예상치 못하게 효율이 떨어지는지 (cf. 가드레일 metric) |
| | * 분석 : traffic 분배 정합성, 샘플수, 다른 segments의 특성, 다른 지표, Bot은 없는지 |
| | * 결정 : 통계적vs실질적 유의도, A/A test->검증 |
| |
| {{tag>data_analysis 실험 experiment ABtest}} | {{tag>data_analysis 실험 experiment ABtest}} |