top of page

David Haziza

In the second EMOS webinar on 15 December 2022, David Haziza examined how machine learning methods perform in the context of unit nonresponse in survey data and familiarised participants with techniques for treating unit nonresponse.

The webinar included an introduction to nonresponse and nonresponse bias and gave insights into propensity score and adjusted estimators as well as the empirical comparison of machine learning methods.


David Haziza is Professor in the Department of Mathematics and Statistics at the University of Ottawa. He is also a consultant at Statistics Canada. His research interests include inference in the presence of missing data, inference in the presence of influential values, resampling methods and machine learning methods.

Prerequisites for the webinar: Basic survey sampling and basic machine learning techniques.

Further readings and resources: None


EMOS webinars: David Haziza on
"The use of machine learning methods for the treatment of unit nonresponse in surveys"

bottom of page