Research map / Probabilistic and scientific modeling / Molecules and proteins
Anytime-Valid Inference For Multinomial Count Data
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use sequential multinomial test instead of chi-squared test under continuous peeking | sample ratio mismatch testing · Type I error simulation, 10000 runs | false rejections: 654 -> 37 | Helped |
| use anytime-valid test instead of fixed-n experiment | signup funnel A/B test · streaming company case study | time to declare a winner: 9 -> 1 week | Helped |
| relax constant success probability to constant ratio p1(t)/p0(t) | confidence sequences · signup funnel case study | validity of the stationarity assumption | Helped |
| monitor Poisson intensity ratio with continuous-time confidence sequence | canary test · streaming company SPS events | time to detect bug | Helped |
| test contrasts delta_2-delta_0 versus delta_2-delta_1 | confidence sequences · Bernoulli arms simulation | samples needed: 573 vs 1882 | Mixed |
Closest papers by meaning
- Architectural and Inferential Inductive Biases for Exchangeable Sequence Modeling (NeurIPS 2025 · similarity 0.83)
- Asymptotically Log-Optimal Bayes-Assisted Confidence Sequences for Bounded Means (NeurIPS 2026 · similarity 0.83)
- Hypothesis Testing for Generalized Thurstone Models (ICML 2025 · similarity 0.83)
- Causal Discovery from Poisson Branching Structural Causal Model Using High-Order Cumulant with Path Analysis (AAAI 2024 · similarity 0.83)
- On the Identifiability of Poisson Branching Structural Causal Model Using Probability Generating Function (NeurIPS 2024 · similarity 0.82)
- Asymptotic Anytime-Valid Inference for U-statistics (NeurIPS 2026 · similarity 0.82)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.