Transportability from multiple environments with limited experiments

Elias Bareinboim, Sanghack Lee, Vasant Honavar, Judea Pearl

Research output: Contribution to journalConference article

5 Citations (Scopus)

Abstract

This paper considers the problem of transferring experimental findings learned from multiple heterogeneous domains to a target domain, in which only limited experiments can be performed. We reduce questions of transportability from multiple domains and with limited scope to symbolic derivations in the causal calculus, thus extending the original setting of transportability introduced in [1], which assumes only one domain with full experimental information available. We further provide different graphical and algorithmic conditions for computing the transport formula in this setting, that is, a way of fusing the observational and experimental information scattered throughout different domains to synthesize a consistent estimate of the desired effects in the target domain. We also consider the issue of minimizing the variance of the produced estimand in order to increase power.

Original languageEnglish (US)
JournalAdvances in Neural Information Processing Systems
StatePublished - Jan 1 2013
Event27th Annual Conference on Neural Information Processing Systems, NIPS 2013 - Lake Tahoe, NV, United States
Duration: Dec 5 2013Dec 10 2013

Fingerprint

Experiments

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Information Systems
  • Signal Processing

Cite this

@article{76ea336b3eaf497e825c3c602e4cba18,
title = "Transportability from multiple environments with limited experiments",
abstract = "This paper considers the problem of transferring experimental findings learned from multiple heterogeneous domains to a target domain, in which only limited experiments can be performed. We reduce questions of transportability from multiple domains and with limited scope to symbolic derivations in the causal calculus, thus extending the original setting of transportability introduced in [1], which assumes only one domain with full experimental information available. We further provide different graphical and algorithmic conditions for computing the transport formula in this setting, that is, a way of fusing the observational and experimental information scattered throughout different domains to synthesize a consistent estimate of the desired effects in the target domain. We also consider the issue of minimizing the variance of the produced estimand in order to increase power.",
author = "Elias Bareinboim and Sanghack Lee and Vasant Honavar and Judea Pearl",
year = "2013",
month = "1",
day = "1",
language = "English (US)",
journal = "Advances in Neural Information Processing Systems",
issn = "1049-5258",

}

Transportability from multiple environments with limited experiments. / Bareinboim, Elias; Lee, Sanghack; Honavar, Vasant; Pearl, Judea.

In: Advances in Neural Information Processing Systems, 01.01.2013.

Research output: Contribution to journalConference article

TY - JOUR

T1 - Transportability from multiple environments with limited experiments

AU - Bareinboim, Elias

AU - Lee, Sanghack

AU - Honavar, Vasant

AU - Pearl, Judea

PY - 2013/1/1

Y1 - 2013/1/1

N2 - This paper considers the problem of transferring experimental findings learned from multiple heterogeneous domains to a target domain, in which only limited experiments can be performed. We reduce questions of transportability from multiple domains and with limited scope to symbolic derivations in the causal calculus, thus extending the original setting of transportability introduced in [1], which assumes only one domain with full experimental information available. We further provide different graphical and algorithmic conditions for computing the transport formula in this setting, that is, a way of fusing the observational and experimental information scattered throughout different domains to synthesize a consistent estimate of the desired effects in the target domain. We also consider the issue of minimizing the variance of the produced estimand in order to increase power.

AB - This paper considers the problem of transferring experimental findings learned from multiple heterogeneous domains to a target domain, in which only limited experiments can be performed. We reduce questions of transportability from multiple domains and with limited scope to symbolic derivations in the causal calculus, thus extending the original setting of transportability introduced in [1], which assumes only one domain with full experimental information available. We further provide different graphical and algorithmic conditions for computing the transport formula in this setting, that is, a way of fusing the observational and experimental information scattered throughout different domains to synthesize a consistent estimate of the desired effects in the target domain. We also consider the issue of minimizing the variance of the produced estimand in order to increase power.

UR - http://www.scopus.com/inward/record.url?scp=84899031657&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84899031657&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:84899031657

JO - Advances in Neural Information Processing Systems

JF - Advances in Neural Information Processing Systems

SN - 1049-5258

ER -