1. NCCU Academic Hub
  2. Publications
  3. College of Commerce
  4. Periodical Articles
  5. Item

Publications-Periodical Articles

Article View/Open

Publication Export

Google ScholarTM

NCCU Library

Citation Infomation

Related Publications in TAIR

題名 Discussion on ＂Stability Selection＂ by Meinshausen and Buhlmann
作者 顏佑銘
Yen, Tso-Jung ;Yen, Yu-Min
貢獻者 國貿系
關鍵詞 High dimensional data;Resampling;Stability selection;Structure estimation
日期 2010-09
上傳時間 24-Nov-2014 14:17:07 (UTC+8)
摘要 Estimation of structure, such as in variable selection, graphical modelling or cluster analysis, is notoriously difficult, especially for high dimensional data. We introduce stability selection. It is based on subsampling in combination with (high dimensional) selection algorithms. As such, the method is extremely general and has a very wide range of applicability. Stability selection provides finite sample control for some error rates of false discoveries and hence a transparent principle to choose a proper amount of regularization for structure estimation. Variable selection and structure estimation improve markedly for a range of selection methods if stability selection is applied. We prove for the randomized lasso that stability selection will be variable selection consistent even if the necessary conditions for consistency of the original lasso method are violated. We demonstrate stability selection for variable selection and Gaussian graphical modelling, using real and simulated data.
關聯 Journal of the Royal Statistical Society: Series B, 72, 413-417
資料類型 article
DOI http://dx.doi.org/10.1111/j.1467-9868.2010.00740.x
dc.contributor 國貿系en_US
dc.creator (作者) 顏佑銘zh_TW
dc.creator (作者) Yen, Tso-Jung ;Yen, Yu-Minen_US
dc.date (日期) 2010-09en_US
dc.date.accessioned 24-Nov-2014 14:17:07 (UTC+8)-
dc.date.available 24-Nov-2014 14:17:07 (UTC+8)-
dc.date.issued (上傳時間) 24-Nov-2014 14:17:07 (UTC+8)-
dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/71618-
dc.description.abstract (摘要) Estimation of structure, such as in variable selection, graphical modelling or cluster analysis, is notoriously difficult, especially for high dimensional data. We introduce stability selection. It is based on subsampling in combination with (high dimensional) selection algorithms. As such, the method is extremely general and has a very wide range of applicability. Stability selection provides finite sample control for some error rates of false discoveries and hence a transparent principle to choose a proper amount of regularization for structure estimation. Variable selection and structure estimation improve markedly for a range of selection methods if stability selection is applied. We prove for the randomized lasso that stability selection will be variable selection consistent even if the necessary conditions for consistency of the original lasso method are violated. We demonstrate stability selection for variable selection and Gaussian graphical modelling, using real and simulated data.en_US
dc.format.extent 11506361 bytes-
dc.format.mimetype application/pdf-
dc.language.iso en_US-
dc.relation (關聯) Journal of the Royal Statistical Society: Series B, 72, 413-417en_US
dc.subject (關鍵詞) High dimensional data;Resampling;Stability selection;Structure estimationen_US
dc.title (題名) Discussion on ＂Stability Selection＂ by Meinshausen and Buhlmannen_US
dc.type (資料類型) articleen
dc.identifier.doi (DOI) 10.1111/j.1467-9868.2010.00740.x-
dc.doi.uri (DOI) http://dx.doi.org/10.1111/j.1467-9868.2010.00740.x-