Factor models in high-dimensional time series

A time-domain approach

M. Hallin, M. Lippi

    Research output: Contribution to journalArticleScientificpeer-review

    Abstract

    High-dimensional time series may well be the most common type of dataset in the so-called “big data” revolution, and have entered current practice in many areas, including meteorology, genomics, chemometrics, connectomics, complex physics simulations, biological and environmental research, finance and econometrics. The analysis of such datasets poses significant challenges, both from a statistical as well as from a numerical point of view. The most successful procedures so far have been based on dimension reduction techniques and, more particularly, on high-dimensional factor models. Those models have been developed, essentially, within time series econometrics, and deserve being better known in other areas. In this paper, we provide an original time-domain presentation of the methodological foundations of those models (dynamic factor models usually are described via a spectral approach), contrasting such concepts as commonality and idiosyncrasy, factors and common shocks, dynamic and static principal components. That time-domain approach emphasizes the fact that, contrary to the static factor models favored by practitioners, the so-called general dynamic factor model essentially does not impose any constraints on the data-generating process, but follows from a general representation result.
    Original languageEnglish
    Pages (from-to)2678-2695
    JournalStochastic Processes and their Applications
    Volume123
    Issue number7
    DOIs
    Publication statusPublished - 2013

    Fingerprint

    Dynamic Factor Model
    Factor Models
    Econometrics
    Time Domain
    Time series
    High-dimensional
    Meteorology
    Chemometrics
    Dimension Reduction
    Principal Components
    Finance
    Genomics
    Shock
    Physics
    Model
    Simulation
    Dynamic models
    Presentation
    Concepts

    Cite this

    @article{90e14f66a7e8488d98c0c5f27fe4d19a,
    title = "Factor models in high-dimensional time series: A time-domain approach",
    abstract = "High-dimensional time series may well be the most common type of dataset in the so-called “big data” revolution, and have entered current practice in many areas, including meteorology, genomics, chemometrics, connectomics, complex physics simulations, biological and environmental research, finance and econometrics. The analysis of such datasets poses significant challenges, both from a statistical as well as from a numerical point of view. The most successful procedures so far have been based on dimension reduction techniques and, more particularly, on high-dimensional factor models. Those models have been developed, essentially, within time series econometrics, and deserve being better known in other areas. In this paper, we provide an original time-domain presentation of the methodological foundations of those models (dynamic factor models usually are described via a spectral approach), contrasting such concepts as commonality and idiosyncrasy, factors and common shocks, dynamic and static principal components. That time-domain approach emphasizes the fact that, contrary to the static factor models favored by practitioners, the so-called general dynamic factor model essentially does not impose any constraints on the data-generating process, but follows from a general representation result.",
    author = "M. Hallin and M. Lippi",
    year = "2013",
    doi = "10.1016/j.spa.2013.04.001",
    language = "English",
    volume = "123",
    pages = "2678--2695",
    journal = "Stochastic Processes and their Applications",
    issn = "0304-4149",
    publisher = "Elsevier",
    number = "7",

    }

    Factor models in high-dimensional time series : A time-domain approach. / Hallin, M.; Lippi, M.

    In: Stochastic Processes and their Applications, Vol. 123, No. 7, 2013, p. 2678-2695.

    Research output: Contribution to journalArticleScientificpeer-review

    TY - JOUR

    T1 - Factor models in high-dimensional time series

    T2 - A time-domain approach

    AU - Hallin, M.

    AU - Lippi, M.

    PY - 2013

    Y1 - 2013

    N2 - High-dimensional time series may well be the most common type of dataset in the so-called “big data” revolution, and have entered current practice in many areas, including meteorology, genomics, chemometrics, connectomics, complex physics simulations, biological and environmental research, finance and econometrics. The analysis of such datasets poses significant challenges, both from a statistical as well as from a numerical point of view. The most successful procedures so far have been based on dimension reduction techniques and, more particularly, on high-dimensional factor models. Those models have been developed, essentially, within time series econometrics, and deserve being better known in other areas. In this paper, we provide an original time-domain presentation of the methodological foundations of those models (dynamic factor models usually are described via a spectral approach), contrasting such concepts as commonality and idiosyncrasy, factors and common shocks, dynamic and static principal components. That time-domain approach emphasizes the fact that, contrary to the static factor models favored by practitioners, the so-called general dynamic factor model essentially does not impose any constraints on the data-generating process, but follows from a general representation result.

    AB - High-dimensional time series may well be the most common type of dataset in the so-called “big data” revolution, and have entered current practice in many areas, including meteorology, genomics, chemometrics, connectomics, complex physics simulations, biological and environmental research, finance and econometrics. The analysis of such datasets poses significant challenges, both from a statistical as well as from a numerical point of view. The most successful procedures so far have been based on dimension reduction techniques and, more particularly, on high-dimensional factor models. Those models have been developed, essentially, within time series econometrics, and deserve being better known in other areas. In this paper, we provide an original time-domain presentation of the methodological foundations of those models (dynamic factor models usually are described via a spectral approach), contrasting such concepts as commonality and idiosyncrasy, factors and common shocks, dynamic and static principal components. That time-domain approach emphasizes the fact that, contrary to the static factor models favored by practitioners, the so-called general dynamic factor model essentially does not impose any constraints on the data-generating process, but follows from a general representation result.

    U2 - 10.1016/j.spa.2013.04.001

    DO - 10.1016/j.spa.2013.04.001

    M3 - Article

    VL - 123

    SP - 2678

    EP - 2695

    JO - Stochastic Processes and their Applications

    JF - Stochastic Processes and their Applications

    SN - 0304-4149

    IS - 7

    ER -