|Where:||Join us from anywhere!|
|Cost:||Free—but registrations are limited|
You can use treatment-effects estimators to draw causal inferences from observational data. You can use lasso when you want to control for many potential covariates.
With standard treatment-effects models, there is an intrinsic conflict between two required assumptions. The conditional independence assumption is likely to be satisfied with many variables in the model, while the overlap assumption is likely to be satisfied with fewer variables in the model. This webinar shows how to overcome this conflict by using Stata 17's telasso command.
telasso estimates the average treatment effects with high-dimensional controls while using lasso for model selection. This estimator is robust to the model-selection mistakes. Moreover, it is doubly robust, so only one of the outcome or treatment model needs to be correctly specified.
The webinar is free, but you must register to attend. Registrations are limited so register soon.
We will send you an email prior to the start of the course with instructions on how to access the webinar.
Di Liu is a senior econometrician in the econometric development team at StataCorp LLC. Di is fascinated by writing statistical software for researchers and doing research in both theoretical and applied econometrics. He is the primary developer of many Stata features, including lasso for prediction, lasso for inference, spatial autoregressive models, heckpoisson, and betareg. Di has a PhD degree in economics from Concordia University in Montreal, Canada; an engineer's degree in software engineering and statistics from Polytech'Lille in Lille, France; and master's and bachelor's degrees in computer science from Hohai University in Nanjing, China.