Statistical Inference in the Presence of Imputed Survey Data Through Regression Trees and Random Forests
:
DSS Statistics Seminar, organized in collaboration with Istat Advisory Committee on statistical methods
Room VI (Building CU002 - Città Universitaria)
Webinar.https://uniroma1.zoom.us/j/86881977368?pwd=SWRFc VFjMDZTa0lXZk05TE1zNm5adz09
Item nonresponse in surveys is usually handled through some form of imputation. Regression trees and random forests provide flexible tools for obtaining a set of imputed values. In this presentation, we lay out a set of conditions on the imputation model sufficient for the consistency of imputed estimators based on regression trees and random forests. We will introduce a novel variance estimator that accounts for sampling and nonresponse. The choice of hyper-parameters will also be discussed. Finally, we will present the results from a simulation study that investigates the performance of point and variance estimators in terms of bias, efficiency and coverage rate.
Relatore:
David Haziza
Affiliazione Relatore:
University of Ottawa
Data:
06/06/2023 - 12:00
Luogo:
[Blended]
Allegati: