{ "id": "epd4nk0c8a", "slug": "sufficient-dimension-reduction", "title": "Sufficient dimension reduction", "updated": "2026-09-30", "topic_path": [ { "id": "physical", "label": "Physical world and mathematics", "api_url": "https://www.edgepedia.org/api/v1/topics/physical" }, { "id": "physical.math", "label": "Mathematics and statistics", "api_url": "https://www.edgepedia.org/api/v1/topics/physical.math" }, { "id": "physical.math.statistics", "label": "Statistics and probability", "api_url": "https://www.edgepedia.org/api/v1/topics/physical.math.statistics" }, { "id": "physical.math.statistics.multivariate-analysis", "label": "Multivariate association and dimension reduction", "api_url": "https://www.edgepedia.org/api/v1/topics/physical.math.statistics.multivariate-analysis" }, { "id": "physical.math.statistics.multivariate-analysis.alpha-mo-to-w", "label": "Titles Mo to W", "api_url": "https://www.edgepedia.org/api/v1/topics/physical.math.statistics.multivariate-analysis.alpha-mo-to-w" } ], "geo": [ { "id": "geo.nongeo.t1946.physical.math.statistics.multivariate-analysis", "label": "Non-geographic · 1946 to 2000: Multivariate association and dimension reduction", "api_url": "https://www.edgepedia.org/api/v1/geo/geo.nongeo.t1946.physical.math.statistics.multivariate-analysis", "path": [ { "id": "geo.nongeo", "label": "Non-geographic", "api_url": "https://www.edgepedia.org/api/v1/geo/geo.nongeo" }, { "id": "geo.nongeo.t1946", "label": "Non-geographic · 1946 to 2000", "api_url": "https://www.edgepedia.org/api/v1/geo/geo.nongeo.t1946" }, { "id": "geo.nongeo.t1946.physical", "label": "Physical world and mathematics", "api_url": "https://www.edgepedia.org/api/v1/geo/geo.nongeo.t1946.physical" }, { "id": "geo.nongeo.t1946.physical.math", "label": "Mathematics and statistics", "api_url": "https://www.edgepedia.org/api/v1/geo/geo.nongeo.t1946.physical.math" }, { "id": "geo.nongeo.t1946.physical.math.statistics", "label": "Statistics and probability", "api_url": "https://www.edgepedia.org/api/v1/geo/geo.nongeo.t1946.physical.math.statistics" }, { "id": "geo.nongeo.t1946.physical.math.statistics.multivariate-analysis", "label": "Multivariate association and dimension reduction", "api_url": "https://www.edgepedia.org/api/v1/geo/geo.nongeo.t1946.physical.math.statistics.multivariate-analysis" } ] } ], "excerpt": "Sufficient dimension reduction (SDR) is a family of statistical methods that replaces a predictor vector with a few linear combinations retaining all information about the response.", "snippet": "Sufficient dimension reduction (SDR) is a family of statistical methods that replaces a predictor vector with a few linear combinations retaining all information about the response.", "node": "physical.math.statistics.multivariate-analysis.alpha-mo-to-w", "markdown": "# Sufficient dimension reduction\n\nSufficient dimension reduction (SDR) is a family of statistical methods that replaces a vector of predictors \\( X \\in \\mathbb{R}^{p} \\) with a few linear combinations \\( B^{\\mathrm T} X \\) that retain all information about the response \\( Y \\), in the sense that the conditional distribution of \\( Y \\) given \\( X \\) equals the conditional distribution of \\( Y \\) given \\( B^{\\mathrm T} X \\).[1](https://www.jmlr.org/papers/volume16/cunningham15a/cunningham15a.pdf) The method was first proposed by Ker-Chau Li in 1991 as sliced inverse regression,[2](https://doi.org/10.1080/01621459.1991.10475035) and the modern subspace framework was formalized by [R. Dennis Cook](https://www.edgepedia.org/r-dennis-cook) in 1994.[3](https://doi.org/10.1080/01621459.1994.10476459)\n\n| Key fact | Detail |\n|---|---|\n| Sufficiency condition | \\( Y \\) is independent of \\( X \\) given \\( B^{\\mathrm T} X \\), so \\( X \\) can be replaced by \\( \\eta^{\\mathrm T} X \\) without loss of information on \\( Y \\mid X \\)[4](http://www.csam.or.kr/journal/view.html?doi=10.5351%2FCSAM.2016.23.2.105) |\n| Target | The central subspace \\( \\mathcal{S}_{Y\\mid X} \\), the intersection of all reduction subspaces satisfying the independence condition[5](https://www.mdpi.com/1099-4300/24/2/167) |\n| Core estimator | SIR uses the kernel matrix \\( K_{\\mathrm{sir}} = \\mathrm{var}\\{E(X\\mid Y)\\} \\)[6](https://www3.stat.sinica.edu.tw/statistica/oldpdf/A32n3101.pdf) |\n| Key condition | The linearity condition \\( E(X\\mid B^{\\mathrm T}X) \\) linear in \\( B^{\\mathrm T}X \\), which holds to good approximation when \\( p \\) is large[7](https://pmc.ncbi.nlm.nih.gov/articles/PMC3685755/) |\n| Practical barrier | Most methods need the inverse of a \\( p \\times p \\) sample covariance matrix, which fails when \\( n < p \\)[8](http://users.stat.umn.edu/~arothman/ESRPAHDR.pdf) |\n| Consistency limit | The SIR estimator is consistent if and only if \\( \\lim p/n = 0 \\)[9](https://export.arxiv.org/pdf/2304.06201v1.pdf) |\n\n## How it works\n\nA subspace spanned by the columns of a matrix \\( B \\) is a sufficient dimension reduction subspace if \\( Y \\) is independent of \\( X \\) given \\( B^{\\mathrm T} X \\). Under mild conditions the intersection of all such subspaces still satisfies the independence condition, and this intersection is the central subspace \\( \\mathcal{S}_{Y\\mid X} \\), the smallest-dimensional sufficient summary.[10](https://arxiv.org/pdf/1304.0580)\n\nThe computational trick behind the most widely used methods is inverse regression: instead of estimating the forward regression \\( E(Y\\mid X) \\), which requires multivariate nonparametric smoothing in \\( p \\) dimensions, SDR estimates the backward regression \\( E(X\\mid Y) \\), a curve in \\( \\mathbb{R}^{p} \\) indexed by a one-dimensional response. Li showed that under the linearity condition \\( E(X\\mid B^{\\mathrm T}X) \\) is linear in \\( B^{\\mathrm T}X \\), the inverse conditional mean \\( E(X\\mid Y) \\) lies in the central subspace, so a principal component analysis of \\( E(X\\mid Y) \\) recovers it.[6](https://www3.stat.sinica.edu.tw/statistica/oldpdf/A32n3101.pdf) This circumvents the curse of dimensionality.[5](https://www.mdpi.com/1099-4300/24/2/167)\n\nThe linearity condition is generally regarded as mild: Hall and Li showed it offers a good approximation when \\( p \\) diverges while \\( d \\) remains fixed, and it holds exactly when the predictors follow an elliptically contoured distribution, which includes the multivariate normal and multivariate \\( t \\).[7](https://pmc.ncbi.nlm.nih.gov/articles/PMC3685755/) A second condition, that \\( \\mathrm{var}(X\\mid B^{\\mathrm T}X) \\) be constant, is required by some methods; the condition is satisfied when the predictors have a multivariate normal distribution and holds approximately when they are elliptically contoured.[27](http://users.stat.umn.edu/~rdcook/RecentArticles/Shao.etal.pdf) • [11](https://ar5iv.labs.arxiv.org/html/2110.09620)\n\n## How it is done\n\n[Sliced inverse regression](https://www.edgepedia.org/sliced-inverse-regression) proceeds in four steps. First, standardize the predictors so their sample covariance is the identity. Second, slice the response \\( Y \\) into \\( h \\) intervals and compute the mean of the standardized predictors within each slice, an estimate of \\( E(X\\mid Y) \\) on that slice. Third, form the kernel matrix \\( K_{\\mathrm{sir}} = \\mathrm{cov}\\{E(X\\mid Y)\\} \\), the covariance of the inverse means. Fourth, perform a spectral decomposition; the eigenvectors associated with the largest \\( d \\) eigenvalues of \\( \\Sigma^{-1} \\mathrm{cov}\\{E(X\\mid Y)\\} \\), where \\( \\Sigma = \\mathrm{cov}(X) \\), estimate the central subspace.[28](https://arxiv.org/pdf/1304.4056) • [4](http://www.csam.or.kr/journal/view.html?doi=10.5351%2FCSAM.2016.23.2.105) • [12](https://pmc.ncbi.nlm.nih.gov/articles/PMC3777433/)\n\nOther kernel matrices target what SIR misses. Because SIR can fail when \\( E(X\\mid Y) \\equiv 0 \\) for symmetrically distributed covariates, Cook and Weisberg proposed sliced average variance estimation (SAVE), which uses the second-moment kernel \\[ K_{\\mathrm{save}} = E\\left[\\{I_p - \\mathrm{var}(X\\mid Y)\\}^{2}\\right] \\] in place of the SIR kernel.[13](https://doi.org/10.2307/2290564) • [6](https://www3.stat.sinica.edu.tw/statistica/oldpdf/A32n3101.pdf) Li's 1991 paper also introduced SIR-II, which uses the second inverse moment under linearity plus a constant [conditional variance](https://www.edgepedia.org/conditional-variance) assumption, and SIR-\\( \\alpha \\), which combines the two kernels.[2](https://doi.org/10.1080/01621459.1991.10475035) • [14](https://arxiv.org/html/2202.00876v1) Directional regression, proposed by Bing Li and Shaoli Wang in 2007, uses a kernel; the spaces spanned by the SAVE and DR kernels are contained in \\( \\mathcal{S}_{Y\\mid X} \\), so both can recover the central subspace where SIR may not.[15](https://doi.org/10.1198/016214507000000536) • [6](https://www3.stat.sinica.edu.tw/statistica/oldpdf/A32n3101.pdf)\n\nThe methods differ in coverage and efficiency. SAVE is exhaustive, meaning it can recover the full central subspace, while SIR is not; yet SIR is more efficient than SAVE.[11](https://ar5iv.labs.arxiv.org/html/2110.09620) • [7](https://pmc.ncbi.nlm.nih.gov/articles/PMC3685755/) In practice, SIR and ordinary least squares work better when the regression has a linear trend, while SAVE outperforms them under nonlinear trend.[4](http://www.csam.or.kr/journal/view.html?doi=10.5351%2FCSAM.2016.23.2.105)\n\nChoosing the structural dimension \\( d \\) is a distinct estimation problem. Li showed that the nonzero eigenvalues of the estimated SIR kernel matrix follow a \\( \\chi^{2} \\) distribution, giving a sequential \\( \\chi^{2} \\) test for \\( d \\).[2](https://doi.org/10.1080/01621459.1991.10475035) • [6](https://www3.stat.sinica.edu.tw/statistica/oldpdf/A32n3101.pdf) Four main approaches exist in the literature: sequential testing, bootstrap methods, BIC-type criteria, and sparse eigen-decomposition; the normality assumption behind the original test was later relaxed by several authors.[7](https://pmc.ncbi.nlm.nih.gov/articles/PMC3685755/)\n\nSlicing itself requires tuning. Slicing \\( Y \\) too coarsely fails to capture the full dependence and produces bias; slicing too finely leaves few observations per slice and produces high variability, and no universal guidance on the number of slices exists.[9](https://export.arxiv.org/pdf/2304.06201v1.pdf) Cumulative slicing estimation was proposed by Li-Ping Zhu, Li-Xing Zhu, and Zheng-Hui Feng in 2010 to avoid such tuning parameters.[16](https://doi.org/10.1198/jasa.2010.tm09666)\n\n## Origin\n\nThe historical basis for SDR was the observation by Brillinger and by Li and Duan that ordinary least squares regression coefficients are consistent, up to a constant, for their population counterparts in generalized single-index models with elliptically symmetric predictors; this was later reframed as the linearity assumption.[5](https://www.mdpi.com/1099-4300/24/2/167) Ker-Chau Li introduced the method in 1991 in the [Journal of the American Statistical Association](https://www.edgepedia.org/journal-of-the-american-statistical-association), in a paper that presented sliced inverse regression and the notion of effective dimension reduction (e.d.r.).[2](https://doi.org/10.1080/01621459.1991.10475035) In the discussion of that paper, Cook and Weisberg proposed SAVE.[13](https://doi.org/10.2307/2290564) Cook's 1994 paper on the interpretation of regression plots developed the subspace viewpoint,[3](https://doi.org/10.1080/01621459.1994.10476459) and the framework of sufficient dimension reduction is influenced by Li's e.d.r. work.[6](https://www3.stat.sinica.edu.tw/statistica/oldpdf/A32n3101.pdf) A general condition for the existence of the central subspace was given by Xiangrong Yin, Bing Li, and R. Dennis Cook in 2008.[17](https://doi.org/10.1016/j.jmva.2008.01.006)\n\n## Variants\n\nLikelihood-based SDR, proposed by Cook and Liliana Forzani in 2009, estimates the central subspace by maximum likelihood under normality.[18](https://doi.org/10.1198/jasa.2009.0106) Principal fitted components, introduced by Cook and Forzani in 2008, models the conditional distribution of the predictors given the fitted response and connects to probabilistic principal component analysis.[19](https://doi.org/10.1214/08-sts275) • [20](https://doi.org/10.1111/1467-9868.00196) Cook and Bing Li developed dimension reduction targeted at the conditional mean, giving the central mean subspace as a smaller target when only the regression function matters.[21](https://doi.org/10.1214/aos/1021379861)\n\nKernel and nonlinear extensions replace linear projections with function classes. Kernel dimension reduction uses reproducing kernel [Hilbert space](https://www.edgepedia.org/hilbert-space) embeddings, and for universal kernels cross-covariance operators determine conditional independence.[11](https://ar5iv.labs.arxiv.org/html/2110.09620) • [1](https://www.jmlr.org/papers/volume16/cunningham15a/cunningham15a.pdf) A general theory for nonlinear SDR was formulated by Kuang-Yao Lee, Bing Li, and Francesca Chiaromonte in 2013, who generalized SIR and SAVE to GSIR and GSAVE within a central class framework; both estimators require no numerical optimization because they are computed by spectral decomposition of linear operators.[22](https://doi.org/10.1214/12-aos1071) Principal support vector machines, proposed by Bing Li, Andreas Artemiou, and Lexin Li in 2011, recast inverse regression through support vector machines for both linear and nonlinear SDR.[23](https://doi.org/10.1214/11-aos932) A published review recommends KCCA, GSIR, and GSAVE for nonlinear SDR in practice, noting that KCCA and GSIR rely on \\( E[f(X)\\mid Y] \\) while GSAVE extracts information from \\( \\mathrm{var}(f(X)\\mid Y) \\).\n\nFor high-dimensional predictors, sparse sliced inverse regression was proposed by Lexin Li and Christopher J Nachtsheim in 2006,[24](https://doi.org/10.1198/004017006000000129) and shrinkage inverse regression estimation for model-free variable selection by Howard D. Bondell and Lexin Li in 2008.[25](https://doi.org/10.1111/j.1467-9868.2008.00686.x) Seeded dimension reduction, proposed by Cook, Bing Li, and Francesca Chiaromonte in 2007, avoids inverting the predictor covariance matrix and reduces to partial least squares in a special case.[26](https://doi.org/10.1093/biomet/asm038) • [8](http://users.stat.umn.edu/~arothman/ESRPAHDR.pdf) Slicing-free methods based on the martingale difference divergence matrix handle high-dimensional covariates with univariate or multivariate responses without choosing a slice scheme.[9](https://export.arxiv.org/pdf/2304.06201v1.pdf)\n\n## Applications\n\nKernel dimension reduction links SDR to kernel machine learning, since cross-covariance operators determine conditional independence for universal kernels.[1](https://www.jmlr.org/papers/volume16/cunningham15a/cunningham15a.pdf) Extensions to multivariate responses, functional data, and supervised classification have also been developed.[14](https://arxiv.org/html/2202.00876v1)\n\n## Limitations and alternatives\n\nThe distributional conditions are the main failure mode. SIR can fail completely when \\( E(X\\mid Y) \\equiv 0 \\), as with symmetrically distributed covariates.[6](https://www3.stat.sinica.edu.tw/statistica/oldpdf/A32n3101.pdf) When the linearity or constant variance condition is violated, SIR and directional regression show substantial bias, while semiparametric estimators remain consistent.[12](https://pmc.ncbi.nlm.nih.gov/articles/PMC3777433/) The presence of any categorical predictor violates the elliptical or normal distributional assumption and voids transformation and reweighting remedies.[7](https://pmc.ncbi.nlm.nih.gov/articles/PMC3685755/)\n\nSample size relative to dimension is the second barrier. Nearly all classical SDR methods require the inverse of a \\( p \\times p \\) sample covariance matrix, so application is problematic when \\( n < p \\), and accurate estimation of a general \\( p \\times p \\) covariance can require \\( n \\gg p \\).[8](http://users.stat.umn.edu/~arothman/ESRPAHDR.pdf) The SIR estimator is consistent if and only if \\( \\lim p/n = 0 \\).[9](https://export.arxiv.org/pdf/2304.06201v1.pdf)\n\nCompared with alternatives, SDR answers a different question than unsupervised reduction. Principal components regression, which reduces first and regresses second, can produce deeply suboptimal results because it ignores the response; partial least squares partially answers this by trading off input covariance and predictive power.[1](https://www.jmlr.org/papers/volume16/cunningham15a/cunningham15a.pdf) Determining the dimensionality of the reduced feature space remains an open problem for nonlinear SDR, since the central class is a function class rather than a linear subspace.\n\n## References\n\n1. [Linear Dimensionality Reduction: Survey, Insights, and Generalizations (JMLR)](https://www.jmlr.org/papers/volume16/cunningham15a/cunningham15a.pdf)\n2. [Ker-Chau Li (1991). Sliced Inverse Regression for Dimension Reduction. Journal of the American Statistical Association.](https://doi.org/10.1080/01621459.1991.10475035)\n3. [R. Dennis Cook (1994). On the Interpretation of Regression Plots. Journal of the American Statistical Association.](https://doi.org/10.1080/01621459.1994.10476459)\n4. [Tutorial: Methodologies for sufficient dimension reduction in regression (Communications for Statistical Applications and Methods, 2016)](http://www.csam.or.kr/journal/view.html?doi=10.5351%2FCSAM.2016.23.2.105)\n5. [Sufficient Dimension Reduction: An Information-Theoretic Viewpoint (Entropy, 2022)](https://www.mdpi.com/1099-4300/24/2/167)\n6. [A Review on Sliced Inverse Regression, Sufficient Dimension Reduction, and Applications (Statistica Sinica)](https://www3.stat.sinica.edu.tw/statistica/oldpdf/A32n3101.pdf)\n7. [A Review on Dimension Reduction (Li, Yin & Zhu, International Statistical Review)](https://pmc.ncbi.nlm.nih.gov/articles/PMC3685755/)\n8. [Estimating sufficient reductions of the predictors in abundant high-dimensional regressions (Cook, Forzani & Rothman)](http://users.stat.umn.edu/~arothman/ESRPAHDR.pdf)\n9. [Slicing-free Inverse Regression in High-dimensional Sufficient Dimension Reduction (arXiv, 2023)](https://export.arxiv.org/pdf/2304.06201v1.pdf)\n10. [A General Theory for Nonlinear Sufficient Dimension Reduction (Lee, Li, Chiaromonte et al.)](https://arxiv.org/pdf/1304.0580)\n11. [Sufficient Dimension Reduction for High-Dimensional Regression and Low-Dimensional Embedding: Tutorial and Survey](https://ar5iv.labs.arxiv.org/html/2110.09620)\n12. [Efficient estimation in sufficient dimension reduction (Ma & Zhu)](https://pmc.ncbi.nlm.nih.gov/articles/PMC3777433/)\n13. [R. Dennis Cook, Sanford Weisberg (1991). Sliced Inverse Regression for Dimension Reduction: Comment. Journal of the American Statistical Association.](https://doi.org/10.2307/2290564)\n14. [A selective review of sufficient dimension reduction for multivariate response regression (published in Journal of Statistical Planning and Inference, 2023)](https://arxiv.org/html/2202.00876v1)\n15. [Bing Li, Shaoli Wang (2007). On Directional Regression for Dimension Reduction. Journal of the American Statistical Association.](https://doi.org/10.1198/016214507000000536)\n16. [Li-Ping Zhu, Li-Xing Zhu, Zheng-Hui Feng (2010). Dimension Reduction in Regressions Through Cumulative Slicing Estimation. Journal of the American Statistical Association.](https://doi.org/10.1198/jasa.2010.tm09666)\n17. [Xiangrong Yin, Bing Li, R. Dennis Cook (2008). Successive direction extraction for estimating the central subspace in a multiple-index regression. Journal of Multivariate Analysis.](https://doi.org/10.1016/j.jmva.2008.01.006)\n18. [R. Dennis Cook, Liliana Forzani (2009). Likelihood-Based Sufficient Dimension Reduction. Journal of the American Statistical Association.](https://doi.org/10.1198/jasa.2009.0106)\n19. [R. Dennis Cook, Liliana Forzani (2008). Principal Fitted Components for Dimension Reduction in Regression. Statistical Science.](https://doi.org/10.1214/08-sts275)\n20. [Michael E. Tipping, Christopher M. Bishop (1999). Probabilistic Principal Component Analysis. Journal of the Royal Statistical Society Series B (Statistical Methodology).](https://doi.org/10.1111/1467-9868.00196)\n21. [R.Dennis Cook, Bing Li (2002). Dimension reduction for conditional mean in regression. The Annals of Statistics.](https://doi.org/10.1214/aos/1021379861)\n22. [Kuang-Yao Lee, Bing Li, Francesca Chiaromonte (2013). A general theory for nonlinear sufficient dimension reduction: Formulation and estimation. The Annals of Statistics.](https://doi.org/10.1214/12-aos1071)\n23. [Bing Li, Andreas Artemiou, Lexin Li (2011). Principal support vector machines for linear and nonlinear sufficient dimension reduction. The Annals of Statistics.](https://doi.org/10.1214/11-aos932)\n24. [Lexin Li, Christopher J Nachtsheim (2006). Sparse Sliced Inverse Regression. Technometrics.](https://doi.org/10.1198/004017006000000129)\n25. [Howard D. Bondell, Lexin Li (2008). Shrinkage Inverse Regression Estimation for Model-Free Variable Selection. Journal of the Royal Statistical Society Series B (Statistical Methodology).](https://doi.org/10.1111/j.1467-9868.2008.00686.x)\n26. [R. D. Cook, B. Li, F. Chiaromonte (2007). Dimension reduction in regression without matrix inversion. Biometrika.](https://doi.org/10.1093/biomet/asm038)\n27. [Shao.etal (users.stat.umn.edu)](http://users.stat.umn.edu/~rdcook/RecentArticles/Shao.etal.pdf)\n28. [arxiv.org](https://arxiv.org/pdf/1304.4056)\n\n---\n*Topic: Encyclopedia › Physical world and mathematics › Mathematics and statistics › Statistics and probability › Multivariate association and dimension reduction › Titles Mo to W*\n\n*Initially written Sep 29, 2026 · Reviewed: Sep 30, 2026 · Edited: Sep 30, 2026 · Last review: Sep 30, 2026*\n\n*Copyright 2026 EdgeChat AI, a subsidiary of Biostate AI.*\n\nLicense: Edgepedia Community License 1.0, https://www.edgepedia.org/edgepedia/license\n", "same_as": [ "http://users.stat.umn.edu/~arothman/ESRPAHDR.pdf", "http://users.stat.umn.edu/~rdcook/RecentArticles/Shao.etal.pdf" ], "url": "https://www.edgepedia.org/sufficient-dimension-reduction", "markdown_url": "https://www.edgepedia.org/sufficient-dimension-reduction.md", "license": { "name": "Edgepedia Community License 1.0", "url": "https://www.edgepedia.org/edgepedia/license", "summary": "Free with credit, commercial use included. AI training is open to everyone. For other uses, organizations over USD 100M in revenue or 100M monthly users license separately.", "spdx": "LicenseRef-Edgepedia-Community-1.0" }, "credit": "\"Sufficient dimension reduction\", Edgepedia (EdgeChat), https://www.edgepedia.org/sufficient-dimension-reduction. Edgepedia Community License 1.0.", "credit_md": "\"[Sufficient dimension reduction](https://www.edgepedia.org/sufficient-dimension-reduction)\", Edgepedia (EdgeChat), [https://www.edgepedia.org/sufficient-dimension-reduction](https://www.edgepedia.org/sufficient-dimension-reduction). [Edgepedia Community License 1.0](https://www.edgepedia.org/edgepedia/license).", "credit_html": "\"Sufficient dimension reduction\", Edgepedia (EdgeChat), https://www.edgepedia.org/sufficient-dimension-reduction. Edgepedia Community License 1.0.", "speakable": "Sufficient dimension reduction is a family of statistical methods that replaces a predictor vector with a few linear combinations retaining all information about the response." }