Sliced Inverse Regression for the inference of stellar fundamental parameters

2017/06/30 by V. Watson, Watson, V., JF. Trouilhet +5
Physics and Astronomy · #FOS: Physical sciences #Instrumentation and Methods for Astrophysics (astro-ph.IM) #Solar and Stellar Astrophysics (astro-ph.SR) #astro-ph.IM #astro-ph.SR

paper · pdf · doi:10.48550/arxiv.1706.10121

in French. to appear in: http://www.gretsi.fr/ XXVI-th colloquium proc. (text in french; maths in maths)

arxiv created 2017/06/30 · arxiv updated 2017/07/03

Abstract

We aim at finding the value of an explanatory variable, through its expression in a large data-vector, without knowing the link function between the explanatory variable and the data-space. Sliced Inverse Regression (SIR) method allows for the projection of a data-vector onto a subspace consistent with the explanatory variable variation. We suggest a method based on the SIR subspace, that gives the most efficient estimation of an unknown explanatory variable.

Related

• Sliced Inverse Regression: application to fundamental stellar parameters
• Inference of an explanatory variable from observations in a high-dimensional space: application to high-resolution spectra of stars
• Inverse regression for ridge recovery: A data-driven approach for parameter reduction in computer experiments
• The Approach of Sliced Inference in Systems of Stochastic Differential Equations with Comments on the Heston Model
• On the Structural Dimension of Sliced Inverse Regression