Discriminant analysis by quantile regression with application on the climate change problem

Cathy W S Chen, Yi Tung Hsu, Masanobu Taniguchi

    Research output: Contribution to journalArticle

    Abstract

    With the widespread use of discriminant analysis in various fields, e.g. multivariate data, regression models, and times series observations, this paper introduces a quantile regression statistic to classify time series data into a certain category. Results show that the misclassification probability of the discriminant statistic converges to zero as the sample size tends to infinity. We also evaluate the performance of the statistics when the categories are contiguous. We apply the proposed method in quantile autoregression to a dataset of the monthly mean maximum temperature at Melbourne, Australia from January 1944 to December 2015. The findings illuminate interesting features of climate change and allow us to check the change at each quantile of the innovation distribution. Because the proposed method is general, there are many potential applications of this approach.

    Original languageEnglish
    JournalJournal of Statistical Planning and Inference
    DOIs
    Publication statusAccepted/In press - 2016 Apr 5

    Fingerprint

    Quantile Regression
    Climate Change
    Discriminant analysis
    Discriminant Analysis
    Quantile
    Climate change
    Statistic
    Statistics
    Probability of Misclassification
    Autoregression
    Time series
    Multivariate Data
    Time Series Data
    Discriminant
    Regression Model
    Sample Size
    Classify
    Infinity
    Tend
    Converge

    Keywords

    • Classification and discrimination
    • Misclassification probability
    • Quantile regression
    • Time series analysis
    • Weather data

    ASJC Scopus subject areas

    • Statistics and Probability
    • Statistics, Probability and Uncertainty
    • Applied Mathematics

    Cite this

    @article{0d9c58f18b8c4951a05bb9abf85ca6a5,
    title = "Discriminant analysis by quantile regression with application on the climate change problem",
    abstract = "With the widespread use of discriminant analysis in various fields, e.g. multivariate data, regression models, and times series observations, this paper introduces a quantile regression statistic to classify time series data into a certain category. Results show that the misclassification probability of the discriminant statistic converges to zero as the sample size tends to infinity. We also evaluate the performance of the statistics when the categories are contiguous. We apply the proposed method in quantile autoregression to a dataset of the monthly mean maximum temperature at Melbourne, Australia from January 1944 to December 2015. The findings illuminate interesting features of climate change and allow us to check the change at each quantile of the innovation distribution. Because the proposed method is general, there are many potential applications of this approach.",
    keywords = "Classification and discrimination, Misclassification probability, Quantile regression, Time series analysis, Weather data",
    author = "Chen, {Cathy W S} and Hsu, {Yi Tung} and Masanobu Taniguchi",
    year = "2016",
    month = "4",
    day = "5",
    doi = "10.1016/j.jspi.2017.02.002",
    language = "English",
    journal = "Journal of Statistical Planning and Inference",
    issn = "0378-3758",
    publisher = "Elsevier",

    }

    TY - JOUR

    T1 - Discriminant analysis by quantile regression with application on the climate change problem

    AU - Chen, Cathy W S

    AU - Hsu, Yi Tung

    AU - Taniguchi, Masanobu

    PY - 2016/4/5

    Y1 - 2016/4/5

    N2 - With the widespread use of discriminant analysis in various fields, e.g. multivariate data, regression models, and times series observations, this paper introduces a quantile regression statistic to classify time series data into a certain category. Results show that the misclassification probability of the discriminant statistic converges to zero as the sample size tends to infinity. We also evaluate the performance of the statistics when the categories are contiguous. We apply the proposed method in quantile autoregression to a dataset of the monthly mean maximum temperature at Melbourne, Australia from January 1944 to December 2015. The findings illuminate interesting features of climate change and allow us to check the change at each quantile of the innovation distribution. Because the proposed method is general, there are many potential applications of this approach.

    AB - With the widespread use of discriminant analysis in various fields, e.g. multivariate data, regression models, and times series observations, this paper introduces a quantile regression statistic to classify time series data into a certain category. Results show that the misclassification probability of the discriminant statistic converges to zero as the sample size tends to infinity. We also evaluate the performance of the statistics when the categories are contiguous. We apply the proposed method in quantile autoregression to a dataset of the monthly mean maximum temperature at Melbourne, Australia from January 1944 to December 2015. The findings illuminate interesting features of climate change and allow us to check the change at each quantile of the innovation distribution. Because the proposed method is general, there are many potential applications of this approach.

    KW - Classification and discrimination

    KW - Misclassification probability

    KW - Quantile regression

    KW - Time series analysis

    KW - Weather data

    UR - http://www.scopus.com/inward/record.url?scp=85014697804&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=85014697804&partnerID=8YFLogxK

    U2 - 10.1016/j.jspi.2017.02.002

    DO - 10.1016/j.jspi.2017.02.002

    M3 - Article

    JO - Journal of Statistical Planning and Inference

    JF - Journal of Statistical Planning and Inference

    SN - 0378-3758

    ER -