Chao WangAre observational studies not able to account for unobserved confounders?Observational studies are often accused of not being able to account for unobserved confounders, as opposed to randomised controlled trials…Oct 11, 2022Oct 11, 2022
Chao WangWhy you should consider cluster-robust standard errors in panel and multilevel data analysisFor panel or multilevel data analysis, two popular models are fixed-effects (FE) and random-effects (RE) models. I discussed the two models…Jun 17, 2022Jun 17, 2022
Chao WangQuick thoughts on the M5 accuracy competitionThe M5 time-series forecasting competition results are out (Makridakis et al. 2022). Here are some of my quick comments:May 16, 2022May 16, 2022
Chao WangSimple method works equally well as sophisticated ones for treatment effect estimationThe paper by Luque-Fernandez et al. (2018) is an interesting article which compares a number of treatment effect estimators, such as…May 6, 2022May 6, 2022