Peer-Reviewed Publications

    Adaptively preconditioned Krylov spaces to identify irrelevant predictors

    Kondylis, A.; Whittaker, J.
    Published
    Aug 24, 2010
    DOI
    10.1016/j.chemolab.2010.08.010
    Link to publication
    Summary

    Linear regression methods have problems in estimation when the predictor variables are highly correlated and when their number exceeds the number of available observations. PLS is one well known method for handling such ill-conditioned regression problems. It does so by approximating the regression solution in a low dimensional subspace. While it copes with collinearity and singularity problems, PLS does not have a variable selection procedure intrinsic to the method. However, it is often the case that one needs to decide which predictors, among the numerous and correlated ones, are the more relevant. The PLS coefficient is a good starting point for the identification of relevant variables in ill-conditioned regression settings. We propose to adaptively precondition the space generated by PLS in order to determine the most relevant predictors. The relevant subset is determined by a multiple testing procedure, and preconditioning stops when this set no longer changes. The principal objective is to do regression modelling and to recover solutions that are easy to interpret in the high dimensional regression setting. We use dimension reduction in a PLS fashion, using information on the response to guide the variable selection procedure. A variety of examples is studied with good results.

    Related Publications

    The evolution of tobacco sales and use following the introduction of heated tobacco products in Japan

    Post-Market Studies and Surveillance Study

    Differences in Biomarkers of Potential Harm After 2+ Years of Tobacco Heating System Use Compared to Cigarette Smoking: A Cross-Sectional Study

    Smoke-free products;Clinical

    Nicotine Pharmacokinetics and Subjective Effects of Nicotine Pouch 1.0 Compared to Velo® Ice Cool and Zyn® Cool Mint Mini Dry in Healthy Smokers

    Clinical Studies

    Nicotine Pharmacokinetics Following Use of the P4M3 Gen 2.0 E-Cigarette Compared to Smoking Cigarettes

    Clinical Studies

    International Expert Consensus on Relevant Health and Functioning Concepts to Assess in Users of Tobacco and Nicotine Products: Delphi Study

    Smoke-free products;Perception and Behavior

    A comparative assessment of HPHC yields and in vitro toxicity for 1R6F reference cigarette smoke versus aerosol generated by Tobacco Heating System 3.0

    Pre-clinical Toxicology

    PMIScience.com is operated by Philip Morris International for the purpose of publishing and disseminating scientific information about Philip Morris International’s efforts in support of its smoke-free product portfolio. This site is a global site for use by scientists, the public health and regulatory communities, and other stakeholders with an interest in tobacco policy. The purpose of this site is not advertising or marketing, nor is it directed at any specific market. It is not intended for use by consumers. New tobacco products sold in the United States are subject to FDA regulation; therefore the content of this site is not intended to make, and nor should it be construed as making, any product related claims in the United States without proper FDA authorization. ​
    ​
    Reduced Risk Products ("RRPs”) is the term we use to refer to products that present, are likely to present, or have the potential to present less risk of harm to smokers who switch to these products versus continuing smoking. PMI has a range of RRPs in various stages of development, scientific assessment and commercialization. All of our RRPs are smoke-free products that deliver nicotine with far lower quantities of harmful and potentially harmful constituents than found in cigarette smoke.