10  Developments

Causal inference literature, following developments are gaining popularity:

10.1 TMLE

• Pang et al. 2016 Epidemiology
• Pang et al. 2016 Int. J Biostat.
• Ju et al. 2019 Stat Meth Med Res.

• Parametric versions implemented
• Super learner could be very time consuming

(Pang, Schuster, Filion, Eberg, et al. 2016; Pang, Schuster, Filion, Schnitzer, et al. 2016; Ju, Gruber, et al. 2019)

10.2 Super learner

• Wyss et al. 2018 Epidemiology
• Ju et al. 2019 J App Stat.

• Parametric versions implemented, or
• Bias not used as a performance measure

(Ju, Combs, et al. 2019; Wyss et al. 2018)

10.3 Cross-validation

• Naimi et al. (2021) Am J Epidemiol.
  • TMLE not performing as well
• Balzer Westling (2021) Am J Epidemiol.

(Naimi, Mishler, and Kennedy 2021; Balzer and Westling 2021)

10.4 Super learner guideline

• Phillips et al. 2023 Int J Epidemiol.

(Phillips et al. 2023)

10.5 Cross-fitting and double robust

Zivich and Breskin (2021): Cross-fitting + together with double robust approaches in low-dimensional setting

(Zivich and Breskin 2021)

Tip

We want to assess the performance in the high-dimensional setting when

• many proxies (some irrelevant) are available.
• complex structure is present.

Balzer, Laura B, and Ted Westling. 2021. “Demystifying Statistical Inference When Using Machine Learning in Causal Research.” American Journal of Epidemiology. https://doi.org/10.1093/aje/kwab200.

Ju, Cheng, Mary Combs, Samuel D Lendle, Jessica M Franklin, Richard Wyss, Sebastian Schneeweiss, and Mark J van der Laan. 2019. “Propensity Score Prediction for Electronic Healthcare Databases Using Super Learner and High-Dimensional Propensity Score Methods.” Journal of Applied Statistics 46 (12): 2216–36.

Ju, Cheng, Susan Gruber, Samuel D Lendle, Antoine Chambaz, Jessica M Franklin, Richard Wyss, Sebastian Schneeweiss, and Mark J van Der Laan. 2019. “Scalable Collaborative Targeted Learning for High-Dimensional Data.” Statistical Methods in Medical Research 28 (2): 532–54.

Naimi, Ashley I, Alan E Mishler, and Edward H Kennedy. 2021. “Challenges in Obtaining Valid Causal Effect Estimates with Machine Learning Algorithms.” American Journal of Epidemiology. https://doi.org/10.1093/aje/kwab201.

Pang, Menglan, Tibor Schuster, Kristian B Filion, Maria Eberg, and Robert W Platt. 2016. “Targeted Maximum Likelihood Estimation for Pharmacoepidemiologic Research.” Epidemiology (Cambridge, Mass.) 27 (4): 570.

Pang, Menglan, Tibor Schuster, Kristian B Filion, Mireille E Schnitzer, Maria Eberg, and Robert W Platt. 2016. “Effect Estimation in Point-Exposure Studies with Binary Outcomes and High-Dimensional Covariate Data–a Comparison of Targeted Maximum Likelihood Estimation and Inverse Probability of Treatment Weighting.” The International Journal of Biostatistics 12 (2).

Phillips, Rachael V, Mark J van der Laan, Hana Lee, and Susan Gruber. 2023. “Practical Considerations for Specifying a Super Learner.” International Journal of Epidemiology. https://doi.org/10.1093/ije/dyad023.

Wyss, Richard, Sebastian Schneeweiss, Mark Van Der Laan, Samuel D Lendle, Cheng Ju, and Jessica M Franklin. 2018. “Using Super Learner Prediction Modeling to Improve High-Dimensional Propensity Score Estimation.” Epidemiology 29 (1): 96–106.

Zivich, Paul N, and Alexander Breskin. 2021. “Machine Learning for Causal Inference: On the Use of Cross-Fit Estimators.” Epidemiology (Cambridge, Mass.) 32 (3): 393.