IDEAS home Printed from https://ideas.repec.org/a/eee/jmvana/v171y2019icp1-21.html
   My bibliography  Save this article

Principal component analysis in an asymmetric norm

Author

Listed:
  • Tran, Ngoc M.
  • Burdejová, Petra
  • Ospienko, Maria
  • Härdle, Wolfgang K.

Abstract

Principal component analysis (PCA) is a widely used dimension reduction tool in high-dimensional data analysis. In risk quantification in finance, climatology and many other applications, however, the interest lies in capturing the tail variations rather than variation around the mean. To this end, we develop Principal Expectile Analysis (PEC), which generalizes PCA for expectiles. It can be seen as a dimension reduction tool for extreme-value theory, where fluctuations in the τ-expectile level of the data are approximated by a low-dimensional subspace. We provide algorithms based on iterative least squares, derive bounds on their convergence time, and compare their performance through simulations. We apply the algorithms to a Chinese weather dataset and fMRI data from an investment decision study.

Suggested Citation

  • Tran, Ngoc M. & Burdejová, Petra & Ospienko, Maria & Härdle, Wolfgang K., 2019. "Principal component analysis in an asymmetric norm," Journal of Multivariate Analysis, Elsevier, vol. 171(C), pages 1-21.
  • Handle: RePEc:eee:jmvana:v:171:y:2019:i:c:p:1-21
    DOI: 10.1016/j.jmva.2018.10.004
    as

    Download full text from publisher

    File URL: http://www.sciencedirect.com/science/article/pii/S0047259X17303962
    Download Restriction: Full text for ScienceDirect subscribers only

    File URL: https://libkey.io/10.1016/j.jmva.2018.10.004?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    As the access to this document is restricted, you may want to look for a different version below or search for a different version of it.

    Other versions of this item:

    References listed on IDEAS

    as
    1. Gao, Yafeng & Xu, Jiangmin & Yang, Shichao & Tang, Xiaomin & Zhou, Quan & Ge, Jing & Xu, Tengfang & Levinson, Ronnen, 2014. "Cool roofs in China: Policy review, building simulations, and proof-of-concept experiments," Energy Policy, Elsevier, vol. 74(C), pages 190-214.
    2. Kuan, Chung-Ming & Yeh, Jin-Huei & Hsu, Yu-Chin, 2009. "Assessing value at risk with CARE, the Conditional Autoregressive Expectile models," Journal of Econometrics, Elsevier, vol. 150(2), pages 261-270, June.
    3. Brenda López Cabrera & Franziska Schulz, 2017. "Forecasting Generalized Quantiles of Electricity Demand: A Functional Data Approach," Journal of the American Statistical Association, Taylor & Francis Journals, vol. 112(517), pages 127-136, January.
    4. Burdejova, Petra & Härdle, Wolfgang Karl & Kokoszka, Piotr & Xiong, Q., 2015. "Change point and trend analyses of annual expectile curves of tropical storms," SFB 649 Discussion Papers 2015-029, Humboldt University Berlin, Collaborative Research Center 649: Economic Risk.
    5. Piotr Majer & Peter Mohr & Hauke Heekeren & Wolfgang Karl Härdle, 2014. "Portfolio Decisions and Brain Reactions via the CEAD method," SFB 649 Discussion Papers SFB649DP2014-036, Sonderforschungsbereich 649, Humboldt University, Berlin, Germany.
    6. Burdejova, P. & Härdle, W. & Kokoszka, P. & Xiong, Q., 2017. "Change point and trend analyses of annual expectile curves of tropical storms," Econometrics and Statistics, Elsevier, vol. 1(C), pages 101-117.
    7. Majer, Piotr & Mohr, Peter N. C. & Heekeren, Hauke R. & Härdle, Wolfgang Karl, 2014. "Portfolio decisions and brain reactions via the CEAD method," SFB 649 Discussion Papers 2014-036, Humboldt University Berlin, Collaborative Research Center 649: Economic Risk.
    8. Fraiman, Ricardo & Pateiro-López, Beatriz, 2012. "Quantiles for finite and infinite dimensional data," Journal of Multivariate Analysis, Elsevier, vol. 108(C), pages 1-14.
    9. Abdelaati Daouia & Stéphane Girard & Gilles Stupfler, 2018. "Estimation of tail risk based on extreme expectiles," Journal of the Royal Statistical Society Series B, Royal Statistical Society, vol. 80(2), pages 263-292, March.
    10. Zhang, Lingsong & Lu, Shu & Marron, J.S., 2015. "Nested nonnegative cone analysis," Computational Statistics & Data Analysis, Elsevier, vol. 88(C), pages 100-110.
    11. Newey, Whitney K & Powell, James L, 1987. "Asymmetric Least Squares Estimation and Testing," Econometrica, Econometric Society, vol. 55(4), pages 819-847, July.
    12. Philippe Jorion, 2000. "Risk management lessons from Long‐Term Capital Management," European Financial Management, European Financial Management Association, vol. 6(3), pages 277-300, September.
    Full references (including those not matched with items on IDEAS)

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Shih-Kang Chao & Wolfgang K. Härdle & Chen Huang, 2016. "Multivariate Factorisable Sparse Asymmetric Least Squares Regression," SFB 649 Discussion Papers SFB649DP2016-058, Sonderforschungsbereich 649, Humboldt University, Berlin, Germany.
    2. Burdejová, Petra & Härdle, Wolfgang Karl, 2017. "Dynamic semi-parametric factor model for functional expectiles," SFB 649 Discussion Papers 2017-027, Humboldt University Berlin, Collaborative Research Center 649: Economic Risk.
    3. Lin, Liang-Ching & Chen, Ray-Bing & Huang, Mong-Na Lo & Guo, Meihui, 2020. "Huber-type principal expectile component analysis," Computational Statistics & Data Analysis, Elsevier, vol. 151(C).
    4. Cathy Yi-Hsuan Chen & Wolfgang Karl Härdle & Yarema Okhrin, 2017. "Tail event driven networks of SIFIs," SFB 649 Discussion Papers SFB649DP2017-004, Sonderforschungsbereich 649, Humboldt University, Berlin, Germany.
    5. Chao, Shih-Kang & Härdle, Wolfgang Karl & Huang, Chen, 2016. "Multivariate factorisable sparse asymmetric least squares regression," SFB 649 Discussion Papers 2016-058, Humboldt University Berlin, Collaborative Research Center 649: Economic Risk.
    6. Ana C S Costa & Diego E Pereira & Caio M Veríssimo & Marcos A D Bomfim & Rita C R E Queiroga & Marta S Madruga & Susana Alves & Rui J B Bessa & Maria E G Oliveira & Juliana K B Soares, 2019. "Developing cookies formulated with goat cream enriched with conjugated linoleic acid," PLOS ONE, Public Library of Science, vol. 14(9), pages 1-15, September.
    7. Osipenko, Maria, 2021. "Directional assessment of traffic flow extremes," Transportation Research Part B: Methodological, Elsevier, vol. 150(C), pages 353-369.
    8. Petra Burdejová & Wolfgang K. Härdle, 2019. "Dynamic semi-parametric factor model for functional expectiles," Computational Statistics, Springer, vol. 34(2), pages 489-502, June.
    9. Wang, Bingling & Li, Yingxing & Härdle, Wolfgang Karl, 2022. "K-expectiles clustering," Journal of Multivariate Analysis, Elsevier, vol. 189(C).
    10. Chen, Cathy Yi-Hsuan & Härdle, Wolfgang Karl & Okhrin, Yarema, 2017. "Tail event driven networks of SIFIs," SFB 649 Discussion Papers 2017-004, Humboldt University Berlin, Collaborative Research Center 649: Economic Risk.
    11. Chen, Cathy Yi-Hsuan & Härdle, Wolfgang Karl & Okhrin, Yarema, 2019. "Tail event driven networks of SIFIs," Journal of Econometrics, Elsevier, vol. 208(1), pages 282-298.

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Tran, Ngoc Mai & Osipenko, Maria & Härdle, Wolfgang Karl, 2014. "Principal component analysis in an asymmetric norm," SFB 649 Discussion Papers 2014-001, Humboldt University Berlin, Collaborative Research Center 649: Economic Risk.
    2. Ngoc Mai Tran & Maria Osipenko & Wolfgang Karl Härdle, 2014. "Principal Component Analysis in an Asymmetric Norm," SFB 649 Discussion Papers SFB649DP2014-001, Sonderforschungsbereich 649, Humboldt University, Berlin, Germany.
    3. Shih-Kang Chao & Wolfgang K. Härdle & Chen Huang, 2016. "Multivariate Factorisable Sparse Asymmetric Least Squares Regression," SFB 649 Discussion Papers SFB649DP2016-058, Sonderforschungsbereich 649, Humboldt University, Berlin, Germany.
    4. Chao, Shih-Kang & Härdle, Wolfgang Karl & Huang, Chen, 2016. "Multivariate factorisable sparse asymmetric least squares regression," SFB 649 Discussion Papers 2016-058, Humboldt University Berlin, Collaborative Research Center 649: Economic Risk.
    5. Petra Burdejová & Wolfgang K. Härdle, 2019. "Dynamic semi-parametric factor model for functional expectiles," Computational Statistics, Springer, vol. 34(2), pages 489-502, June.
    6. Burdejová, Petra & Härdle, Wolfgang Karl, 2017. "Dynamic semi-parametric factor model for functional expectiles," SFB 649 Discussion Papers 2017-027, Humboldt University Berlin, Collaborative Research Center 649: Economic Risk.
    7. Taoufik Bouezmarni & Mohamed Doukali & Abderrahim Taamouti, 2024. "Testing Granger non-causality in expectiles," Econometric Reviews, Taylor & Francis Journals, vol. 43(1), pages 30-51, January.
    8. Litimein, Ouahiba & Laksaci, Ali & Mechab, Boubaker & Bouzebda, Salim, 2023. "Local linear estimate of the functional expectile regression," Statistics & Probability Letters, Elsevier, vol. 192(C).
    9. Daouia, Abdelaati & Paindaveine, Davy, 2019. "Multivariate Expectiles, Expectile Depth and Multiple-Output Expectile Regression," TSE Working Papers 19-1022, Toulouse School of Economics (TSE), revised Feb 2023.
    10. repec:hal:journl:hal-04672516 is not listed on IDEAS
    11. Daouia, Abdelaati & Girard, Stéphane & Stupfler, Gilles, 2018. "Tail expectile process and risk assessment," TSE Working Papers 18-944, Toulouse School of Economics (TSE).
    12. James Ming Chen, 2018. "On Exactitude in Financial Regulation: Value-at-Risk, Expected Shortfall, and Expectiles," Risks, MDPI, vol. 6(2), pages 1-28, June.
    13. Daouia, Abdelaati & Girard, Stéphane & Stupfler, Gilles, 2017. "Extreme M-quantiles as risk measures: From L1 to Lp optimization," TSE Working Papers 17-841, Toulouse School of Economics (TSE).
    14. Daouia, Abdelaati & Padoan, Simone A. & Stupfler, Gilles, 2023. "Extreme expectile estimation for short-tailed data, with an application to market risk assessment," TSE Working Papers 23-1414, Toulouse School of Economics (TSE), revised May 2024.
    15. Daouia, Abdelaati & Girard, Stéphane & Stupfler, Gilles, 2021. "ExpectHill estimation, extreme risk and heavy tails," Journal of Econometrics, Elsevier, vol. 221(1), pages 97-117.
    16. Man, Rebeka & Tan, Kean Ming & Wang, Zian & Zhou, Wen-Xin, 2024. "Retire: Robust expectile regression in high dimensions," Journal of Econometrics, Elsevier, vol. 239(2).
    17. Yundong Tu & Siwei Wang, 2023. "Variable Screening and Model Averaging for Expectile Regressions," Oxford Bulletin of Economics and Statistics, Department of Economics, University of Oxford, vol. 85(3), pages 574-598, June.
    18. Daouia, Abdelaati & Stupfler, Gilles & Usseglio-Carleve, Antoine, 2023. "An expectile computation cookbook," TSE Working Papers 23-1458, Toulouse School of Economics (TSE).
    19. Girard, Stéphane & Stupfler, Gilles & Usseglio-Carleve, Antoine, 2022. "Functional estimation of extreme conditional expectiles," Econometrics and Statistics, Elsevier, vol. 21(C), pages 131-158.
    20. Chao, Shih-Kang & Härdle, Wolfgang K. & Huang, Chen, 2018. "Multivariate factorizable expectile regression with application to fMRI data," Computational Statistics & Data Analysis, Elsevier, vol. 121(C), pages 1-19.
    21. Härdle, Wolfgang Karl & Ling, Chengxiu, 2018. "How Sensitive are Tail-related Risk Measures in a Contamination Neighbourhood?," IRTG 1792 Discussion Papers 2018-010, Humboldt University of Berlin, International Research Training Group 1792 "High Dimensional Nonstationary Time Series".

    More about this item

    Keywords

    Asymmetric norm; Dimension reduction; Expectile; Growth data; Quantile; Risk attitude; Temperature;
    All these keywords.

    JEL classification:

    • C38 - Mathematical and Quantitative Methods - - Multiple or Simultaneous Equation Models; Multiple Variables - - - Classification Methdos; Cluster Analysis; Principal Components; Factor Analysis
    • C55 - Mathematical and Quantitative Methods - - Econometric Modeling - - - Large Data Sets: Modeling and Analysis
    • C61 - Mathematical and Quantitative Methods - - Mathematical Methods; Programming Models; Mathematical and Simulation Modeling - - - Optimization Techniques; Programming Models; Dynamic Analysis
    • C63 - Mathematical and Quantitative Methods - - Mathematical Methods; Programming Models; Mathematical and Simulation Modeling - - - Computational Techniques
    • D81 - Microeconomics - - Information, Knowledge, and Uncertainty - - - Criteria for Decision-Making under Risk and Uncertainty

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:eee:jmvana:v:171:y:2019:i:c:p:1-21. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Catherine Liu (email available below). General contact details of provider: http://www.elsevier.com/wps/find/journaldescription.cws_home/622892/description#description .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.