fect – User Manual

Welcome!

This Quarto book serves as a user manual for the fect package in R, which implements counterfactual (imputation) estimators for causal inference with panel data and performs diagnostic tests.

fect covers a series of counterfactual estimators, including the five estimators from the last version and integrating the latest version of the gsynth package for the generalized synthetic control method (Gsynth). This Quarto book also facilitates the application of various new difference-in-differences (DID) estimators. For details of these methods, see

• Xu (2017) for Gsynth [Paper]

• Liu, Wang, and Xu (2024) for counterfactural estimators [Paper]

• Chiu et al. (2025) for a survey of the new DID estimators [Paper]

Source Code

For those interested in exploring the algorithms used in fect for calculating estimates, please visit the source GitHub Repo for further details.

Why Counterfactual Estimators?

There are several reasons why you might consider using counterfactual estimators for your panel data applications:

• Because “causal inference is a missing data problem” (Holland 1986), it is natural to impute treated counterfactuals when the ATT, if well defined, is the primary quantity of interest.
• Counterfactual estimators help avoid the (negative) weighting problem, which has been highlighted in recent applied econometrics literature regarding TWFE models, e.g., Chaisemartin and D’Haultfœuille (2020); Goodman-Bacon (2021).
  
• Among the newer estimators that accommodate heterogeneous treatment effects, the fixed effect counterfactual estimator (imputation based on TWFE) is the most efficient under homoskedasticity (Borusyak, Jaravel, and Spiess 2024).
  
• Counterfactual estimators enable the use of more complex modeling strategies, such as linear factor models and matrix completion methods, which naturally connect to the synthetic control setting.

However, these counterfactual estimators come with important limitations:

• Most rely on some form of the parallel trends assumption or a low-rank structure.
  
• They generally do not accommodate dynamic treatment assignment based on sequential ignorability.
  
• Methods for continuous treatments are still underdeveloped and are not currently covered by fect.

Chiu et al. (2025) reanalyze numerous published studies in political science and offer detailed justifications for adopting these estimators.

Why the Merge?

I have decided to merge the two packages, gsynth and fect, as gsynth is fundamentally a counterfactual estimator. The two packages increasingly share similar code modules and features, including core algorithms (the ife and mc methods in both packages are essentially identical), tuning methods, and visualization tools. This merge will greatly simplify package maintenance moving forward.

However, some key differences between the two approaches remain:

• Gsynth is specifically designed for block and staggered DID settings without treatment reversal, while other methods accommodate treatment reversal under the assumption of limited carryover effects.
• Gsynth is particularly suited for cases where the number of treated units is small, including scenarios with only one treated unit. By setting vartype = "parametric", we can use a two-stage parametric bootstrapping procedure—analogous to conformal inference—to produce uncertainty estimates. In contrast, other methods rely on large samples, particularly a large number of treated units, to obtain reliable standard errors and confidence intervals using "bootstrap" or "jackknife".
• Compared with IFEct (method = "ife"), Gsynth does not rely on pre-treatment data from the treated units to impute \(\hat{Y}(0)\). This approach significantly speeds up computation and improves stability.

Therefore, we recommend setting method = "gsynth" in fect for scenarios where the treatment does not reverse (or is coded accordingly) and the number of treated units is small .

Moving forward, I will discontinue maintaining gsynth and focus on adding more functionalities to fect.

Organization

The user guide is structured into the following chapters:

• Chapter 1
  This chapter covers installation instructions and introduces the datasets.

• Chapter 2
  This chapter explains how to apply the five estimators and diagnostic tests available in previous versions of fect.

• Chapter 3
  In this chapter, we explore various plotting options available in fect.

• Chapter 4
  This chapter provides a step-by-step guide to implementing all the functionalities of the original gsynth R package using fect.

• Chapter 5
  This chapter facilitates the application of various new DID estimators and sensitivity analyses.

• Chapter 6
  The final chapter summarizes the core inputs required for implementing the six methods, along with options for plotting and diagnostics.

Contributors

The following individuals have contributed to gsynth and fect, listed in the order of their involvement in the project:

• Yiqing Xu
  
• Licheng Liu
  
• Ye Wang
  
• Ziyi Liu (PhD Student at Berkeley Haas)
• Shijian Liu (PhD Student at NYU Stern)
• Tianzhu Qin
  
• Jinwen Wu (Predoc at Stanford PoliSci)

Special thanks to Ziyi and Tianzhu for their tireless efforts in improving this package. Thanks to Jinwen for setting up and maintaining this User Manual.

Report bugs

Please report any bugs to me (yiqingxu [at] stanford.edu) or submit an issue on GitHub. Please include your minimally replicable code & data file and a panelView treatment status plot. Your feedback is highly valued!

fect:

gsynth: (retiring)

Athey, Susan, Mohsen Bayati, Nikolay Doudchenko, Guido Imbens, and Khashayar Khosravi. 2021. “Matrix Completion Methods for Causal Panel Data Models.” Journal of the American Statistical Association 116 (536): 1716–30.

Bleiberg, Joshua. 2021. “STACKEDEV: Stata Module to Implement Stacked Event Study Estimator.” Statistical Software Components, Boston College Department of Economics.

Borusyak, Kirill, Xavier Jaravel, and Jann Spiess. 2024. “Revisiting Event-Study Designs: Robust and Efficient Estimation.” Review of Economic Studies 91: 3253–85.

Callaway, Brantly, and Pedro HC Sant’Anna. 2021. “Difference-in-Differences with Multiple Time Periods.” Journal of Econometrics 225 (2): 200–230.

Cengiz, Doruk, Arindrajit Dube, Attila Lindner, and Ben Zipperer. 2019. “The Effect of Minimum Wages on Low-Wage Jobs*.” The Quarterly Journal of Economics 134 (3): 1405–54.

Chaisemartin, Clément de, Diego Ciccia, Xavier D’Haultfœuille, Felix Knau, Mélitine Malézieux, and Doulo Sow. 2024. “Event-Study Estimators and Variance Estimators Computed by the Did_multiplegt_dyn Command.” Available at SSRN.

Chaisemartin, Clément de, and Xavier D’Haultfœuille. 2020. “Two-Way Fixed Effects Estimators with Heterogeneous Treatment Effects.” The American Economic Review 110 (9): 2964–96.

Chiu, Albert, Xingchen Lan, Ziyi Liu, and Yiqing Xu. 2025. “Causal Panel Analysis Under Parallel Trends: Lessons from a Large Reanalysis Study.” American Political Science Review.

De Chaisemartin, Clément, and Xavier d’Haultfoeuille. 2020. “Two-Way Fixed Effects Estimators with Heterogeneous Treatment Effects.” American Economic Review 110 (9): 2964–96.

———. 2024. “Difference-in-Differences Estimators of Intertemporal Treatment Effects.” Review of Economics and Statistics, 1–45.

Gardner, John. 2021. “Two-Stage Differences in Differences.” Working Paper, Boston College. https://bit.ly/3AF32Af.

Gobillon, Laurent, and Thierry Magnac. 2016. “Regional Policy Evaluation: Interactive Fixed Effects and Synthetic Controls.” Review of Economics and Statistics 98 (3): 535–51.

Goodman-Bacon, Andrew. 2021. “Difference-in-Differences with Variation in Treatment Timing.” Journal of Econometrics 225 (2): 254–77.

Grumbach, Jacob M., and Alexander Sahn. 2020. “Race and Representation in Campaign Finance.” American Political Science Review 114 (1): 206–21.

Hainmueller, Jens, and Dominik Hangartner. 2019. “Does Direct Democracy Hurt Immigrant Minorities? Evidence from Naturalization Decisions in Switzerland.” American Journal of Political Science 63 (3): 530–47.

Holland, Paul W. 1986. “Statistics and Causal Inference.” Journal of the American Statistical Association 81 (396): 945–60.

Imai, Kosuke, In Song Kim, and Erik H Wang. 2023. “Matching Methods for Causal Inference with Time-Series Cross-Sectional Data.” American Journal of Political Science 67 (3): 587–605.

Liu, Licheng, Ye Wang, and Yiqing Xu. 2024. “A Practical Guide to Counterfactual Estimators for Causal Inference with Time-Series Cross-Sectional Data.” American Journal of Political Science 68 (1): 160–76.

Rambachan, Ashesh, and Jonathan Roth. 2023. “A More Credible Approach to Parallel Trends.” Review of Economic Studies, rdad018.

Roth, Jonathan. 2024. “Interpreting Event-Studies from Recent Difference-in-Differences Methods.” arXiv Preprint arXiv:2401.12309.

Sun, Liyang, and Sarah Abraham. 2021. “Estimating Dynamic Treatment Effects in Event Studies with Heterogeneous Treatment Effects.” Journal of Econometrics 225 (2): 175–99.

Xu, Yiqing. 2017. “Generalized Synthetic Control Method: Causal Inference with Interactive Fixed Effects Models.” Political Analysis 25 (1): 57–76.