Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining 2017
DOI: 10.1145/3097983.3098032
|View full text |Cite
|
Sign up to set email alerts
|

Estimating Treatment Effect in the Wild via Differentiated Confounder Balancing

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
38
0

Year Published

2018
2018
2023
2023

Publication Types

Select...
5
5

Relationship

1
9

Authors

Journals

citations
Cited by 63 publications
(38 citation statements)
references
References 22 publications
0
38
0
Order By: Relevance
“…Methods Standard approaches in ITE prediction include model-agnostic methods (meta-learners [38; 44], modified outcome methods [5] and their combinations [35]) that implicitly predict the CATE, as well as tree-based approaches which are particularly suited for direct treatment effect estimation [4; 55]. A prolific series of increasingly performing algorithm targeted towards ITE prediction have been proposed, using a variety of techniques to adjust for the covariate shift, such as generative adversarial nets [56], auto-encoders [43], double machine learning [15], representation learning [54; 58] or confounder balancing algorithms [37]. Another recent trend is to study theoretical limits in ITE prediction and especially generalization bounds [2].…”
Section: Individual Treatment Effectmentioning
confidence: 99%
“…Methods Standard approaches in ITE prediction include model-agnostic methods (meta-learners [38; 44], modified outcome methods [5] and their combinations [35]) that implicitly predict the CATE, as well as tree-based approaches which are particularly suited for direct treatment effect estimation [4; 55]. A prolific series of increasingly performing algorithm targeted towards ITE prediction have been proposed, using a variety of techniques to adjust for the covariate shift, such as generative adversarial nets [56], auto-encoders [43], double machine learning [15], representation learning [54; 58] or confounder balancing algorithms [37]. Another recent trend is to study theoretical limits in ITE prediction and especially generalization bounds [2].…”
Section: Individual Treatment Effectmentioning
confidence: 99%
“…Sample reweighting methods aim to correct the treatment assignment using observational data in order to overcome the subject selection bias. For instance, these methods include Inverse Propensity Weighting (IPW) based on propensity score [17] and confounder balancing methods [12]. Other methods include doubly-robust approaches which combine covariate adjustment with propensity score weighting [3], [4], [5].…”
Section: Related Workmentioning
confidence: 99%
“…In the literature of causality [23], an ideal model to resolve selection bias is to make policy based on causal variables, which keep stable across different domains [24]. Popular methods based one observational data to estimate the causal effect of a treatment on the outcome include propensity score matching [25,26], markov blankets [27,28] and confounder balancing [29,30] and etc [31]. Lately [32] leverage causality for predictive modeling.…”
Section: Proportional Bias Settingmentioning
confidence: 99%