Modeling confounding by half-sibling regression

被引:33
作者
Schoelkopf, Bernhard [1 ]
Hogg, David W. [2 ]
Wang, Dun [2 ]
Foreman-Mackey, Daniel [2 ]
Janzing, Dominik [1 ]
Simon-Gabriel, Carl-Johann [1 ]
Peters, Jonas [1 ]
机构
[1] Max Planck Inst Intelligent Syst, Dept Empir Inference, D-72076 Tubingen, Germany
[2] NYU, Ctr Cosmol & Particle Phys, 550 1St Ave, New York, NY 10003 USA
关键词
machine learning; causal inference; astronomy; exoplanet detection; systematic error modeling; UNWANTED VARIATION; ERROR-CORRECTION; EXPRESSION DATA; ASSOCIATION; DISCOVERY;
D O I
10.1073/pnas.1511656113
中图分类号
O [数理科学和化学]; P [天文学、地球科学]; Q [生物科学]; N [自然科学总论];
学科分类号
07 ; 0710 ; 09 ;
摘要
We describe a method for removing the effect of confounders to reconstruct a latent quantity of interest. The method, referred to as "half-sibling regression," is inspired by recent work in causal inference using additive noise models. We provide a theoretical justification, discussing both independent and identically distributed as well as time series data, respectively, and illustrate the potential of the method in a challenging astronomy application.
引用
收藏
页码:7391 / 7398
页数:8
相关论文
共 23 条
[1]   AUTONOMY [J].
ALDRICH, J .
OXFORD ECONOMIC PAPERS-NEW SERIES, 1989, 41 (01) :15-34
[2]  
[Anonymous], 2012, ICML
[3]  
[Anonymous], 2000, CAUSALITY
[4]   The Derivation, Properties, and Value of Kepler's Combined Differential Photometric Precision [J].
Christiansen, Jessie L. ;
Jenkins, Jon M. ;
Caldwell, Douglas A. ;
Burke, Christopher J. ;
Tenenbaum, Peter ;
Seader, Shawn ;
Thompson, Susan E. ;
Barclay, Thomas S. ;
Clarke, Bruce D. ;
Li, Jie ;
Smith, Jeffrey C. ;
Stumpe, Martin C. ;
Twicken, Joseph D. ;
Van Cleve, Jeffrey .
PUBLICATIONS OF THE ASTRONOMICAL SOCIETY OF THE PACIFIC, 2012, 124 (922) :1279-1287
[5]   A SYSTEMATIC SEARCH FOR TRANSITING PLANETS IN THE K2 DATA [J].
Foreman-Mackey, Daniel ;
Montet, Benjamin T. ;
Hogg, David W. ;
Morton, Timothy D. ;
Wang, Dun ;
Schoelkopf, Bernhard .
ASTROPHYSICAL JOURNAL, 2015, 806 (02)
[6]   Using control genes to correct for unwanted variation in microarray data [J].
Gagnon-Bartsch, Johann A. ;
Speed, Terence P. .
BIOSTATISTICS, 2012, 13 (03) :539-552
[7]  
Hastie T., 2009, ELEMENTS STAT LEARNI, V2, DOI [10.1007/978-0-387-84858-7, DOI 10.1007/978-0-387-84858-7]
[8]  
Hoover KD, 2008, EC PHILOS, V6
[9]   Correcting gene expression data when neither the unwanted variation nor the factor of interest are observed [J].
Jacob, Laurent ;
Gagnon-Bartsch, Johann A. ;
Speed, Terence P. .
BIOSTATISTICS, 2016, 17 (01) :16-28
[10]  
Janzing D, 2009, 25 C UNC ART INT, P249