22 R Packages Used in This Book

This book relies on the broader R causal-inference ecosystem rather than a single bespoke stack. The goal of this appendix is to map each chapter’s methods onto the actual R packages that implement them, so a reader can move from “what is this method?” to “which R function should I call?” without searching the book code by hand.

Most packages live on CRAN. A few (pcalg’s graph, RBGL, Rgraphviz dependencies) come from Bioconductor and require a one-line install via BiocManager. None of the packages were written for this book — they are the same tools researchers use in published papers.

22.1 Working With The Environment

A minimal reproducible workflow is:

cd ~/projects/books/causal_econometrics_guide
# Install Bioconductor dependencies once (needed by pcalg)
Rscript -e 'install.packages("BiocManager"); BiocManager::install(c("graph","RBGL","Rgraphviz"))'
quarto render

The book uses Quarto’s execute: freeze: auto setting (configured in _quarto.yml), so each chapter’s computed output is cached under _freeze/. Re-rendering only re-executes chunks whose source has changed. When upgrading a package whose API may have moved, delete the relevant _freeze/<chapter>/ directory to force a re-run.

22.2 Package Map

Package	Used For	Main Book Chapters
`dagitty`	DAG and ADMG construction, adjustment-set search, d-separation	Identification, DAG workflow, Smoking cessation
`ggdag`	Visual rendering of DAGs/ADMGs built with `dagitty`	Identification, DAG workflow, IV/RDD
`causaleffect`	Pearl–Shpitser ID algorithm for general ADMGs	DAG workflow
`tidyverse` (`dplyr`, `tidyr`, `purrr`, `ggplot2`)	Data wrangling and plotting throughout	Every chapter
`haven`	Reading Stata `.dta` files used as examples	Estimation, DiD, IV/RDD
`causaldata`	Built-in NHEFS, mortgages, and other causal-inference example datasets	Estimation, DiD, IV/RDD, Smoking cessation
`hdm`	Pension (`p401k`) dataset and high-dimensional inference	Estimation
`SuperLearner`	Stacked machine-learning nuisance estimation	Nonparametric
`npcausal`	Influence-function-based ATE/ATT estimators (Edward Kennedy)	Nonparametric
`tmle`	Targeted maximum likelihood estimation	Nonparametric
`DoubleML`, `mlr3`, `mlr3learners`	Double/debiased ML for partially linear and interactive models	Nonparametric
`did`	Callaway & Sant’Anna estimators; `mpdta` example dataset	DiD
`etwfe`	Wooldridge’s extended TWFE for staggered DiD	DiD
`fixest`	High-dimensional fixed-effects OLS, Poisson, IV; clustered SEs	DiD, IV/RDD, Poisson-IV
`synthdid`	Standard DiD, synthetic control, synthetic DiD; Prop 99 example	DiD
`sem`	Classical two-stage least squares via `tsls()`	IV/RDD
`MASS`	Multivariate normal sampling for IV simulations	IV/RDD
`rdrobust`	Local-polynomial RDD, sharp and fuzzy designs	IV/RDD
`gmm`	Generalized method of moments for nonlinear IV	Poisson-IV
`lavaan`	SEM and CFA syntax for classical mediation	Mediation
`medoutcon`	Causal mediation: controlled, natural, interventional effects	Mediation
`pcalg`	PC, GES, FCI, RFCI causal-discovery algorithms	Causal Discovery (both chapters)
`Rgraphviz`, `graph`	Rendering CPDAG/PAG output from `pcalg`	Causal Discovery

22.3 `dagitty` and `ggdag`

The dagitty package provides a small DSL for graphs and the standard graph-theoretic identification queries:

library(dagitty)

g <- dagitty("dag {
  X -> A
  X -> Y
  A -> Y
}")

adjustmentSets(g, exposure = "A", outcome = "Y")

adjustmentSets returns all minimal sufficient sets for the backdoor criterion. Bidirected edges encoded as A <-> Y represent unobserved common causes (an ADMG), and dagitty correctly returns no adjustment set in that case.

ggdag consumes dagitty objects and renders them through ggplot2:

library(ggdag)
ggdag(g) + theme_dag_blank()

22.4 `causaleffect`

When dagitty::adjustmentSets returns an empty list, the effect may still be identified through a non-backdoor route (front-door, more general ID-algorithm patterns). causaleffect implements Tikka & Karvanen’s R port of the Pearl–Shpitser ID algorithm:

library(igraph)
library(causaleffect)

g <- graph_from_literal(A -+ M, M -+ Y, A -+ Y, Y -+ A)
g <- set_edge_attr(g, "description", index = c(2, 4), value = "U")
causal.effect(y = "Y", x = "A", G = g, simp = TRUE)
# → \sum_{M} P(M|A)\left(\sum_{A} P(Y|A,M) P(A)\right)

The bidirected edge convention is two reciprocal directed edges with description = "U". The function either returns a symbolic identification expression or raises an error indicating the effect is not identifiable.

22.5 `etwfe` and `fixest`

fixest is the workhorse for regression models with high-dimensional fixed effects. Its feols, fepois, and feglm use a formula DSL that keeps DiD and IV specifications readable:

library(fixest)

feols(y ~ x | id + year, data = df, vcov = ~id)        # TWFE, clustered SE
fepois(y ~ x + offset(log(pop)) | id + year, data = df)  # Poisson with FE
feols(y ~ x | id + year | x_endo ~ z, data = df)         # IV/2SLS

etwfe wraps fixest for Wooldridge’s extended two-way fixed-effects DiD:

library(etwfe)

mod <- etwfe(fml = lemp ~ lpop, tvar = year, gvar = first.treat,
             data = mpdta, vcov = ~countyreal)
emfx(mod, type = "event")

emfx() aggregates the cohort × time interaction coefficients into an overall ATT, event-time effects, or calendar-time effects.

22.6 `pcalg`

pcalg provides PC, GES, FCI, RFCI, GIES, and LINGAM under one consistent S4 interface. It uses the graph package for graph objects and Rgraphviz for plotting. The Bioconductor dependencies must be installed via BiocManager before pcalg can be installed from CRAN.

library(pcalg)

# Constraint-based: PC algorithm
pc_fit <- pc(suffStat = list(C = cor(data), n = nrow(data)),
             indepTest = gaussCItest, labels = colnames(data),
             alpha = 0.01)

# Score-based: Greedy Equivalence Search
ges_fit <- ges(new("GaussL0penObsScore", data))

# Latent-variable case: FCI / RFCI
fci_fit  <- fci(suffStat = list(C = cor(data), n = nrow(data)),
                indepTest = gaussCItest, labels = colnames(data), alpha = 0.01)
rfci_fit <- rfci(suffStat = list(C = cor(data), n = nrow(data)),
                 indepTest = gaussCItest, labels = colnames(data), alpha = 0.01)

Both observed (PC, GES) and latent (FCI, RFCI) chapters use these as the primary algorithms.

22.7 `lavaan` and `medoutcon`

lavaan ports the SEM model-string syntax familiar from EQS, Mplus, and LISREL into R. It is used in the mediation chapter for classical SEM mediation:

library(lavaan)

model <- "
  m ~ a * x
  y ~ b * m + c * x
  indirect := a * b
  total    := c + indirect
"
fit <- sem(model, data = df)
parameterEstimates(fit)

For causal mediation under the potential-outcomes framework, the book uses medoutcon (Hejazi & van der Laan), which estimates controlled, natural, and interventional direct/indirect effects with cross-fitted nuisance estimators.

22.8 Practical Advice

The packages above form the practical toolkit for the methods in this book, but the broader R causal ecosystem is much larger. A few good entry points outside what’s used directly here:

MatchIt and WeightIt for matching and weighting estimators of the ATE/ATT
grf (Generalized Random Forests) for heterogeneous treatment effects and instrumental-forest IV
bnlearn for an alternative causal-discovery toolkit focused on Bayesian networks
lavaan.survey and blavaan for survey-weighted and Bayesian SEM
mediation for the classical Imai/Keele/Tingley mediation framework

When upgrading any of these packages, re-render affected chapters after deleting the relevant _freeze/<chapter>/ directory so that Quarto does not reuse stale cached results.

# R Packages Used in This Book This book relies on the broader R causal-inference ecosystem rather than a single bespoke stack. The goal of this appendix is to map each chapter's methods onto the actual R packages that implement them, so a reader can move from "what is this method?" to "which R function should I call?" without searching the book code by hand. Most packages live on CRAN. A few (`pcalg`'s `graph`, `RBGL`, `Rgraphviz` dependencies) come from Bioconductor and require a one-line install via `BiocManager`. None of the packages were written for this book — they are the same tools researchers use in published papers. ## Working With The Environment A minimal reproducible workflow is: ```bash cd ~/projects/books/causal_econometrics_guide # Install Bioconductor dependencies once (needed by pcalg) Rscript -e 'install.packages("BiocManager"); BiocManager::install(c("graph","RBGL","Rgraphviz"))' quarto render ``` The book uses Quarto's `execute: freeze: auto` setting (configured in `_quarto.yml`), so each chapter's computed output is cached under `_freeze/`. Re-rendering only re-executes chunks whose source has changed. When upgrading a package whose API may have moved, delete the relevant `_freeze/<chapter>/` directory to force a re-run. ## Package Map | Package | Used For | Main Book Chapters | |---|---|---| | `dagitty` | DAG and ADMG construction, adjustment-set search, d-separation | Identification, DAG workflow, Smoking cessation | | `ggdag` | Visual rendering of DAGs/ADMGs built with `dagitty` | Identification, DAG workflow, IV/RDD | | `causaleffect` | Pearl–Shpitser ID algorithm for general ADMGs | DAG workflow | | `tidyverse` (`dplyr`, `tidyr`, `purrr`, `ggplot2`) | Data wrangling and plotting throughout | Every chapter | | `haven` | Reading Stata `.dta` files used as examples | Estimation, DiD, IV/RDD | | `causaldata` | Built-in NHEFS, mortgages, and other causal-inference example datasets | Estimation, DiD, IV/RDD, Smoking cessation | | `hdm` | Pension (`p401k`) dataset and high-dimensional inference | Estimation | | `SuperLearner` | Stacked machine-learning nuisance estimation | Nonparametric | | `npcausal` | Influence-function-based ATE/ATT estimators (Edward Kennedy) | Nonparametric | | `tmle` | Targeted maximum likelihood estimation | Nonparametric | | `DoubleML`, `mlr3`, `mlr3learners` | Double/debiased ML for partially linear and interactive models | Nonparametric | | `did` | Callaway & Sant'Anna estimators; `mpdta` example dataset | DiD | | `etwfe` | Wooldridge's extended TWFE for staggered DiD | DiD | | `fixest` | High-dimensional fixed-effects OLS, Poisson, IV; clustered SEs | DiD, IV/RDD, Poisson-IV | | `synthdid` | Standard DiD, synthetic control, synthetic DiD; Prop 99 example | DiD | | `sem` | Classical two-stage least squares via `tsls()` | IV/RDD | | `MASS` | Multivariate normal sampling for IV simulations | IV/RDD | | `rdrobust` | Local-polynomial RDD, sharp and fuzzy designs | IV/RDD | | `gmm` | Generalized method of moments for nonlinear IV | Poisson-IV | | `lavaan` | SEM and CFA syntax for classical mediation | Mediation | | `medoutcon` | Causal mediation: controlled, natural, interventional effects | Mediation | | `pcalg` | PC, GES, FCI, RFCI causal-discovery algorithms | Causal Discovery (both chapters) | | `Rgraphviz`, `graph` | Rendering CPDAG/PAG output from `pcalg` | Causal Discovery | ## `dagitty` and `ggdag` The `dagitty` package provides a small DSL for graphs and the standard graph-theoretic identification queries: ```r library(dagitty) g <- dagitty("dag { X -> A X -> Y A -> Y }") adjustmentSets(g, exposure = "A", outcome = "Y") ``` `adjustmentSets` returns *all* minimal sufficient sets for the backdoor criterion. Bidirected edges encoded as `A <-> Y` represent unobserved common causes (an ADMG), and `dagitty` correctly returns no adjustment set in that case. `ggdag` consumes `dagitty` objects and renders them through `ggplot2`: ```r library(ggdag) ggdag(g) + theme_dag_blank() ``` ## `causaleffect` When `dagitty::adjustmentSets` returns an empty list, the effect may still be identified through a non-backdoor route (front-door, more general ID-algorithm patterns). `causaleffect` implements Tikka & Karvanen's R port of the Pearl–Shpitser ID algorithm: ```r library(igraph) library(causaleffect) g <- graph_from_literal(A -+ M, M -+ Y, A -+ Y, Y -+ A) g <- set_edge_attr(g, "description", index = c(2, 4), value = "U") causal.effect(y = "Y", x = "A", G = g, simp = TRUE) # → \sum_{M} P(M|A)\left(\sum_{A} P(Y|A,M) P(A)\right) ``` The bidirected edge convention is two reciprocal directed edges with `description = "U"`. The function either returns a symbolic identification expression or raises an error indicating the effect is not identifiable. ## `etwfe` and `fixest` `fixest` is the workhorse for regression models with high-dimensional fixed effects. Its `feols`, `fepois`, and `feglm` use a formula DSL that keeps DiD and IV specifications readable: ```r library(fixest) feols(y ~ x | id + year, data = df, vcov = ~id) # TWFE, clustered SE fepois(y ~ x + offset(log(pop)) | id + year, data = df) # Poisson with FE feols(y ~ x | id + year | x_endo ~ z, data = df) # IV/2SLS ``` `etwfe` wraps `fixest` for Wooldridge's extended two-way fixed-effects DiD: ```r library(etwfe) mod <- etwfe(fml = lemp ~ lpop, tvar = year, gvar = first.treat, data = mpdta, vcov = ~countyreal) emfx(mod, type = "event") ``` `emfx()` aggregates the cohort × time interaction coefficients into an overall ATT, event-time effects, or calendar-time effects. ## `pcalg` `pcalg` provides PC, GES, FCI, RFCI, GIES, and LINGAM under one consistent S4 interface. It uses the `graph` package for graph objects and `Rgraphviz` for plotting. The Bioconductor dependencies must be installed via `BiocManager` before `pcalg` can be installed from CRAN. ```r library(pcalg) # Constraint-based: PC algorithm pc_fit <- pc(suffStat = list(C = cor(data), n = nrow(data)), indepTest = gaussCItest, labels = colnames(data), alpha = 0.01) # Score-based: Greedy Equivalence Search ges_fit <- ges(new("GaussL0penObsScore", data)) # Latent-variable case: FCI / RFCI fci_fit <- fci(suffStat = list(C = cor(data), n = nrow(data)), indepTest = gaussCItest, labels = colnames(data), alpha = 0.01) rfci_fit <- rfci(suffStat = list(C = cor(data), n = nrow(data)), indepTest = gaussCItest, labels = colnames(data), alpha = 0.01) ``` Both observed (PC, GES) and latent (FCI, RFCI) chapters use these as the primary algorithms. ## `lavaan` and `medoutcon` `lavaan` ports the SEM model-string syntax familiar from EQS, Mplus, and LISREL into R. It is used in the mediation chapter for classical SEM mediation: ```r library(lavaan) model <- " m ~ a * x y ~ b * m + c * x indirect := a * b total := c + indirect " fit <- sem(model, data = df) parameterEstimates(fit) ``` For causal mediation under the potential-outcomes framework, the book uses `medoutcon` (Hejazi & van der Laan), which estimates controlled, natural, and interventional direct/indirect effects with cross-fitted nuisance estimators. ## Practical Advice The packages above form the practical toolkit for the methods in this book, but the broader R causal ecosystem is much larger. A few good entry points outside what's used directly here: - `MatchIt` and `WeightIt` for matching and weighting estimators of the ATE/ATT - `grf` (Generalized Random Forests) for heterogeneous treatment effects and instrumental-forest IV - `bnlearn` for an alternative causal-discovery toolkit focused on Bayesian networks - `lavaan.survey` and `blavaan` for survey-weighted and Bayesian SEM - `mediation` for the classical Imai/Keele/Tingley mediation framework When upgrading any of these packages, re-render affected chapters after deleting the relevant `_freeze/<chapter>/` directory so that Quarto does not reuse stale cached results.

22.1 Working With The Environment

22.2 Package Map

22.3 dagitty and ggdag

22.4 causaleffect

22.5 etwfe and fixest

22.6 pcalg

22.7 lavaan and medoutcon