Efficiency loss and the linearity condition in dimension reduction
نویسندگان
چکیده
Linearity, sometimes jointly with constant variance, is routinely assumed in the context of sufficient dimension reduction. It is well understood that, when these conditions do not hold, blindly using them may lead to inconsistency in estimating the central subspace and the central mean subspace. Surprisingly, we discover that even if these conditions do hold, using them will bring efficiency loss. This paradoxical phenomenon is illustrated through sliced inverse regression and principal Hessian directions. The efficiency loss also applies to other dimension reduction procedures. We explain this empirical discovery by theoretical investigation.
منابع مشابه
Efficiency Loss Caused by Linearity Condition in Dimension Reduction.
Linearity, sometimes jointly with constant variance, is routinely assumed in the context of sufficient dimension reduction. It is well understood that, when these conditions do not hold, blindly using them may lead to inconsistency in estimating the central subspace and the central mean subspace. Surprisingly, we discover that even if these conditions do hold, using them will bring efficiency l...
متن کاملSIR: Dimension Reduction in the Presence of Linearly or Nonlinearly Related Predictors
Sufficient dimension reduction (sdr) is an effective tool for reducing highdimensional predictor spaces in regression problems. sdr achieves dimension reduction without loss of any regression information and without the need to assume any particular parametric form of a model. This is particularly useful for high-dimensional applications such as data mining, marketing, and bioinformatics. Howev...
متن کاملEnhancing Efficiency of Neural Network Model in Prediction of Firms Financial Crisis Using Input Space Dimension Reduction Techniques
The main focus in this study is on data pre-processing, reduction in number of inputs or input space size reduction the purpose of which is the justified generalization of data set in smaller dimensions without losing the most significant data. In case the input space is large, the most important input variables can be identified from which insignificant variables are eliminated, or a variable ...
متن کاملInvestigation of the efficiency of various reactive mufflers by noise reduction and transmission loss analyses
Transmission loss and noise reduction of reactive mufflers are determined by linear acoustic theory and unsteady flow field study, respectively. The effects of extending the inlet tube of the muffler, adding holes to the extension, and the number of holes on both transmission loss and noise reduction are investigated. In noise reduction analysis, the Navier-Stokes equations and k-ε model are us...
متن کاملThe Aluffi Algebra and Linearity Condition
The Aluffi algebra is an algebraic version of characteristic cycles in intersection theory which is an intermediate graded algebra between the symmetric algebra (naive blowup) and the Rees algebra (blowup). Let R be a commutative Noetherian ring and J ⊂I ideals of R. We say that J ⊂I satisfy linearity condition if the Aluffi algebra of I/J is isomorphic with the symmetric algebra. In this pa...
متن کامل