directeffects

An R package for estimating controlled direct effects.

https://github.com/mattblackwell/directeffects

Repository

An R package for estimating controlled direct effects.

README.Rmd

---
output: github_document
---


# DirectEffects 

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


## Overview


DirectEffects is an R package to estimate controlled direct effects (CDEs), which are the effect of a treatment fixing a set of downstream mediators to particular values. As of now, the package supports general doubly robust estimation of CDEs under both selection-on-observables and difference-in-differences assumptions. sequential g-estimation and a two-stage matching approach called telescope matching. For more information on how CDEs can be useful for applied research and a brief introduction to sequential g-estimation, see [Acharya, Blackwell, and Sen (2016)][de-paper]. For more on the telescope matching procedure, see  [Blackwell and Strezhnev (2022)][tm-paper]. For more on the difference-in-differences approach, see [Blackwell, Glynn, Hilbig, and Phillips (2024)][did-paper].


## Installation

You can install DirectEffects via CRAN for the current stable version or via GitHub for the development version. 

```{r, eval = FALSE}
# Installing from CRAN
install.packages("DirectEffects")

# Installing development version from Github:
# install.packages("devtools")
devtools::install_github("mattblackwell/DirectEffects", build_vignettes = TRUE)
```

## Usage


DirectEffects uses a modular approach to specifying the models and estimators used to estimate the average controlled direct effect (ACDE). You can specify a propensity score and outcome regression model for each treatment variable (that is, each causal variable of interest), along with a set of parametric and machine learning estimators for these nuisance functions. The package has a workflow for [models that assume the selection-on-observables](https://mattblackwell.github.io/DirectEffects/articles/DirectEffects.html) and for models that utilize a [difference-in-differences approach](https://mattblackwell.github.io/DirectEffects/articles/did_cde.html). 


```{r}
library(DirectEffects)

data(jobcorps)
my_aipw <- cde_aipw() |>
  set_treatment(treat, ~ female + age_cat) |>
  treat_model(engine = "logit") |>
  outreg_model(engine = "lm") |>
  set_treatment(work2year2q, ~ emplq4 + pemplq4) |>
  treat_model(engine = "logit") |>
  outreg_model(engine = "lm") |>
  estimate(exhealth30 ~ treat + work2year2q, data = jobcorps)

broom::tidy(my_aipw)
```




## Specific estimator implementations

DirectEffects also implements a number of specific estimators outside the modular framework. These are often specific estimators proposed in the literature:

- [`sequential_g()`](https://mattblackwell.github.io/DirectEffects/articles/sequential_g.html): estimate controlled direct effects using two-stage linear models. 
- [`telescope_match()`](https://mattblackwell.github.io/DirectEffects/articles/telescope_matching.html): estimated controlled direct effects using a two-stage matching procedure with bias correction. 

DirectEffects also provides diagnostics for these two approaches, including sensitivity analyses and balance checks. 

[de-paper]: http://www.mattblackwell.org/files/papers/direct-effects.pdf
[tm-paper]: https://www.mattblackwell.org/files/papers/telescope_matching.pdf
[did-paper]: https://www.mattblackwell.org/files/papers/did_cde.pdf

Owner

GitHub Events

Packages