Student Sliced Inverse Regression - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Journal Articles Computational Statistics and Data Analysis Year : 2017

Student Sliced Inverse Regression


Sliced Inverse Regression (SIR) has been extensively used to reduce the dimension of the predictor space before performing regression. SIR is originally a model free method but it has been shown to actually correspond to the maximum likelihood of an inverse regression model with Gaussian errors. This intrinsic Gaussianity of standard SIR may explain its high sensitivity to outliers as observed in a number of studies. To improve robustness, the inverse regression formulation of SIR is therefore extended to non-Gaussian errors with heavy-tailed distributions. Considering Student distributed errors it is shown that the inverse regression remains tractable via an Expectation- Maximization (EM) algorithm. The algorithm is outlined and tested in the presence of outliers, both in simulated and real data, showing improved results in comparison to a number of other existing approaches.
Fichier principal
Vignette du fichier
elsarticle-StudentSIR.pdf (442.02 Ko) Télécharger le fichier (3.58 Ko) Télécharger le fichier
Origin Files produced by the author(s)
Origin Files produced by the author(s)
Comment This archive contains the Matlab code associated with the simulation section of the paper. Simulations.m is the main file, sir2.m is the function for standard SIR and stSirI.m is the function for Student SIR.

Dates and versions

hal-01294982 , version 1 (14-06-2016)
hal-01294982 , version 3 (08-08-2016)
hal-01294982 , version 2 (08-08-2016)




Alessandro Chiancone, Florence Forbes, Stéphane Girard. Student Sliced Inverse Regression. Computational Statistics and Data Analysis, 2017, 113, pp.441-456. ⟨10.1016/j.csda.2016.08.004⟩. ⟨hal-01294982v3⟩
1358 View
407 Download



Gmail Mastodon Facebook X LinkedIn More