negative-binomial

Code for fitting a negative binomial distribution in Python

Geographically Weighted Negative Binomial Regression in Python - local spatial modeling for over dispersed count data.

Football prop forecasting engine. Post-competition review found the calibration layer was making forecasts worse, removing it is documented, measured, and enforced by tests.

纯 Python 标准库从零实现 RNA-seq 差异表达分析（归一化/离散度收缩/负二项 GLM/Wald/BH），与官方 DESeq2 对拍：log2FC r=0.9997、显著集 Jaccard=0.90。

RNS-Seq Count Model Explorer

The DEGage2 package works to identify differentially expressed genes (DEGs) on bulk RNA-seq data through utilization of DOTNB

Studying the relationship between likes sent and matches on the famous dating app Tinder.

Poisson vs Negative Binomial on 17,379 hourly bike rentals: overdispersion diagnosis, NB2 modeling, and peak-hour anomaly detection

End-to-end Bayesian ML platform for county overdose modeling with PostgreSQL, PyMC, MLflow, FastAPI, Streamlit, and grounded AI.

Code and simulation results for "Generalized Fiducial Inference for Hybrid Discrete–Continuous Count Data" (Thomas and Hannig): samplers for the discrete generalized fiducial distribution, the simulation study, and the scripts behind every table and figure.

Experimentation framework for synthetic accounting data with seven statistical designs, reproducible assignments, causal analysis, guardrails, power checks, and decision reporting.

Predictive model (R, Negative Binomial regression) forecasting monthly eviction filings at census tract level for Philadelphia. Python pipeline handles fairness auditing, PDF reporting, dashboard, and resident notification. Built for resource allocation, not automated enforcement.

Forecasting the full distribution of yellow cards in English league football: a negative binomial model, tested on matches before they were played, with the daily pipeline that collects, checks and scores it

Why RNA-seq counts are negative-binomial not Poisson: overdispersion, the mean-variance trend, and the zero-inflation myth.