Search Results for "inference"

The CausalImpact repository houses an R package that implements causal inference in time series using Bayesian structural time series models. Its goal is to estimate the effect of an intervention (e.g. a marketing campaign, policy change) on a time series outcome by predicting what would have happened in a counterfactual “no intervention” world. The package requires as input a response time series plus one or more control (covariate) time series that are assumed unaffected by the intervention, and it divides the time horizon into “pre-intervention” and “post-intervention” periods. ...

easystats is a meta‑package that installs and unifies a suite of R packages for post‑processing statistical models. It delivers a consistent API to assess model performance, effect sizes, parameters, and to generate reports and visualizations, all with minimal dependencies and maximum clarity.

...It is part of a larger ecosystem: the compiled HTML / book version of the labs is published via a companion “book” repository, which presents a polished, browsable version of the materials. The content covers topics such as data wrangling in R, statistical inference, genomics workflows, Bioconductor packages, and project-based analyses. Because it’s open and modular, contributors can suggest improvements, update modules, or add new exercises.

This repository hosts the 2022 version of the Statistical Rethinking course. It contains course materials such as R scripts, notebooks, and worked examples aligned with McElreath’s textbook. The code emphasizes Bayesian data analysis using R, the rethinking package, and Stan models. It includes lecture code files, example datasets, and structured exercises that parallel the topics covered in the lectures (probability, regression, model comparison, Bayesian updating). The repo functions as a...

This R package accompanies Richard McElreath’s Statistical Rethinking (2nd edition), offering utilities to fit and compare Bayesian models using both MAP estimation (quap) and Hamiltonian Monte Carlo via RStan (ulam). It supports specifying models via explicit distributional assumptions, providing flexibility for advanced statistical workflows.

The “statistics-for-data-scientists” repository is a pedagogical resource designed to bridge rigorous statistics theory and practical data science workflows. The code and materials are intended to help data scientists and analysts grasp statistical principles (e.g. inference, regressions, hypothesis testing, probability, confidence intervals) in contexts relevant to real data analysis tasks. The repository includes Jupyter notebooks, R scripts, worked examples, and possibly problem sets that illustrate how statistical methods are applied to real datasets. It aims to demystify the bridge between textbook statistics and empirical modeling by walking through assumption checking, visualization, interpreting outputs, and pitfalls of misuse. ...

...The repository is designed as a shared space for code examples, datasets, and instructional materials, helping learners follow along with lectures and assignments. It spans essential topics such as R programming, data cleaning, exploratory data analysis, statistical inference, regression models, machine learning, and practical data science projects. By providing centralized resources, the repo makes it easier for students to practice concepts and replicate examples from the curriculum. It also offers a structured view of how multiple disciplines—programming, statistics, and applied data analysis—come together in a professional workflow.

RStan is the R interface to Stan, a C++ library for statistical modeling and high-performance statistical computation. It lets users specify models in the Stan modeling language (for Bayesian inference), compile them, and perform inference from R. Key inference approaches include full Bayesian inference via Hamiltonian Monte Carlo (specifically the No-U-Turn Sampler, NUTS), approximate Bayesian inference via variational methods, and optimization (penalized likelihood). RStan integrates with Stan’s automatic differentiation library, provides diagnostics, model comparison, posterior predictive checks, etc. ...