https://github.com/google/CausalImpact

An R package for causal inference in time series
https://github.com/google/CausalImpact

Last synced: about 1 month ago
JSON representation

An R package for causal inference in time series

• Host: GitHub
• URL: https://github.com/google/CausalImpact
• Owner: google
• License: apache-2.0
• Created: 2014-08-08T17:16:13.000Z (over 10 years ago)
• Default Branch: master
• Last Pushed: 2023-07-17T18:19:58.000Z (over 1 year ago)
• Last Synced: 2025-01-07T16:07:29.434Z (3 months ago)
• Language: R
• Homepage:
• Size: 3.15 MB
• Stars: 1,720
• Watchers: 104
• Forks: 255
• Open Issues: 34
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• awesome-AIOps - google/CausalImpact, An R package for causal inference in time series
• awesome-marketing-machine-learning - CausalImpact
• StarryDivineSky - google/CausalImpact

README

        
# CausalImpact

[![R-CMD-check](https://github.com/google/CausalImpact/workflows/R-CMD-check/badge.svg)](https://github.com/google/CausalImpact/actions)

[![Codecov test coverage](https://codecov.io/gh/google/CausalImpact/branch/master/graph/badge.svg)](https://app.codecov.io/gh/google/CausalImpact?branch=master)

## An R package for causal inference using Bayesian structural time-series models

This R package implements an approach to estimating the causal effect of a

designed intervention on a time series. For example, how many additional daily

clicks were generated by an advertising campaign? Answering a question like this

can be difficult when a randomized experiment is not available. The package aims

to address this difficulty using a structural Bayesian time-series model to

estimate how the response metric might have evolved after the intervention if

the intervention had not occurred.

As with all approaches to causal inference on non-experimental data, valid

conclusions require strong assumptions. The CausalImpact package, in particular,

assumes that the outcome time series can be explained in terms of a set of

control time series that were themselves not affected by the intervention.

Furthermore, the relation between treated series and control series is assumed

to be stable during the post-intervention period. Understanding and checking

these assumptions for any given application is critical for obtaining valid

conclusions.

## Installation

```r

install.packages("CausalImpact")

library(CausalImpact)

```

## Getting started

[Video tutorial](https://www.youtube.com/watch?v=GTgZfCltMm8)

[Documentation and examples](https://google.github.io/CausalImpact/CausalImpact.html)

## Further resources

*   Manuscript:

    [Brodersen et al., Annals of Applied Statistics (2015)](https://research.google/pubs/pub41854/)

*   For questions on the statistics behind CausalImpact:

    [Cross Validated](https://stats.stackexchange.com/questions/tagged/causalimpact)

*   For questions on how to use the CausalImpact R package:

    [Stack Overflow](https://stackoverflow.com/questions/tagged/causalimpact)

*   [Bug reports](https://github.com/google/CausalImpact/issues)