Econometrics professor and author. Dogs = 2, cats >= 10.
Jeffrey Wooldridge
Loading...
📣 We're hiring a postdoc to join us on education research projects at Oxford @oxfordecondept.bsky.social @oxfordcsae.bsky.social. Join me @gamblingondev.bsky.social @roccozizzamia.bsky.social on multiple exciting projects! Applications due June 7th.
www.economics.ox.ac.uk/csae-postdoc...
drlate supports estimators of LATE and LATT, including regression adjustment, inverse probability weighting, augmented IPW, and IPWRA. Outcome and treatment models can be specified as linear, logistic, or Poisson regressions.
Today a student raised the bar for what’s required to visit me outside of my office hours.
We expect to have a new draft of this paper in the next few months.
"Dr. Late" can provide a cure when the treatment is confounded, you want to allow TE heterogeneity, and you want to take functional form seriously.
The instrument propensity score is specified as a logistic regression (logit) and can be estimated by maximum likelihood (ML), covariate balancing propensity score (CBPS), or inverse probability tilting (IPT). The instrument must be binary.
