I received my PhD in Statistics from University of Washington and MA in Statistics from Harvard University.
Prior to joining Ghent University, I worked as a postdoctoral research fellow in Biostatistics at the University of North Carolina Chapel Hill.

I enjoy working on causal inference for applications motivated by behavioral and social sciences. My current research focuses on developing statistical methods for inferring causal effects in mediation analyses.

I enjoy working on causal inference for applications motivated by behavioral and social sciences. My current research focuses on developing statistical methods for inferring causal effects in mediation analyses.

Loh, W. W., Moerkerke B., Loeys T., and Vansteelandt S. (2020).
Heterogeneous indirect effects for multiple mediators using interventional effect models.
*Epidemiologic Methods, Accepted.
*

Preprint

R code on GitHub

Loh, W. W., Moerkerke B., Loeys T., and Vansteelandt S. (2020).
Nonlinear mediation analysis with high‐dimensional mediators whose causal structure is unknown.
*Biometrics, Accepted.
*

Paper

R code on GitHub

Loh, W. W., Moerkerke B., Loeys T., and Vansteelandt S. (2020).
Disentangling indirect effects through multiple mediators without assuming any causal structure among the mediators.
*Psychological Methods, Accepted.
*

Preprint

*Loh, W. W., Moerkerke B., Loeys T., Poppe L., Crombez G., and Vansteelandt S. (2020).
Estimation of controlled direct effects in longitudinal mediation analyses with latent variables in randomised studies.
Multivariate Behavioral Research. 55(5), 763-785
Paper
*

*Loh, W. W., and Vansteelandt S. (2020).
Confounder selection strategies targeting stable treatment effect estimators.
Statistics In Medicine, Accepted.
Paper
R code on GitHub*

Loh, W., & Ren, D. (2020).
Estimating social influence in a social network using potential outcomes.
*Psychological Methods, Accepted.
*

Paper

Preprint

*Loh, W. W., and Kim J. (2020).
Evaluating the impact of misclassification when estimating heterogeneous causal effects.
Under review
*

*Loh, W. W., Hudgens M.G., Clemens J.D., Ali M., and Emch, M.E. (2020).
Randomization inference with general interference and censoring.
Biometrics, 235-245.
Paper
R code on GitHub*

Loh, W. W., Richardson, T. S., and Robins, J. M. (2017).
An apparent paradox explained.
*Statistical Science, 32(3), 356-361.*

Paper

Rigdon, J., Loh, W. W., and Hudgens, M. G. (2017).
Response to comment on 'Randomization inference for treatment effects on a binary outcome'.
*Statistics in Medicine, 36(5), 876-880.*

Paper

R package

Loh, W. W., and Richardson, T. S. (2015).
A finite population likelihood ratio test of the sharp null hypothesis for compliers.
*In Thirty-First Conference on Uncertainty in Artificial Intelligence.*

Paper

R package

Loh, W. W., and Richardson, T. S. (2013).
A finite population test of the sharp null hypothesis for compliers.
*In UAI Workshop on Approaches to Causal Structure Learning, 15 July, Bellevue, Washington.*

Paper

We think in terms of what would happen (**potential outcomes**),
and what could have happened (**counterfactuals**).
The idea of simulating potential outcomes is nicely described in this episode of the TV show **Person of Interest**:
If-Then-Else.