arXiv · 2611.15684
Sliced Inverse Regression Revisited: When the Number of Predictors Grows Proportionally With the Sample Size
Abstract
Li (1991) introduced sliced inverse regression (SIR) as a dimension reduction method and established its theoretical properties under the assumption that the number of predictors $p$ remains fixed as the sample size $n$ tends to infinity. In this paper, we revisit the theoretical properties of SIR in the high-dimensional regime where $p/n \to γ\in [0,1)$, assuming normally distributed predictors and a fixed number of slices. We show that the sample SIR eigenvalues exhibit an upward bias when $γ>0$, that their fluctuations are governed by the Gaussian orthogonal ensemble, and that the signal eigenvalues are asymptotically normal after an appropriate bias correction. We demonstrate that Li's chi-squared test requires a scaling adjustment to achieve the nominal asymptotic size when $γ>0$. We further propose two additional tests that achieve the nominal asymptotic size: an exact test based on Li's test statistic and a largest-eigenvalue test. In addition, we derive closed-form limits for the accuracy of the estimated SIR directions and show that their first-order expansions in $γ$ agree with Li's approximation. Finally, we establish the limiting distribution of the estimated sufficient predictors for a new observation and show that, when $γ>0$, they contain an additional independent Gaussian noise component. Simulation studies corroborate our theoretical findings.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Peng Zeng, Hanwen Huang. 2026-11-11. Sliced Inverse Regression Revisited: When the Number of Predictors Grows Proportionally With the Sample Size. https://searcharxiv.com/abs/2611.15684
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Searcharxiv by Indiciae: BibTeX · RIS.