BIROn - Birkbeck Institutional Research Online

    Penalized likelihood estimation of a trivariate additive probit model

    Filippou, P. and Marra, G. and Radice, Rosalba (2017) Penalized likelihood estimation of a trivariate additive probit model. Biostatistics 18 (3), pp. 569-585. ISSN 1465-4644.

    This is the latest version of this item.

    [img]
    Preview
    Text
    Paper16261.pdf - Author's Accepted Manuscript

    Download (1MB) | Preview
    [img]
    Preview
    Text
    Supp material_TRIV.pdf - Supplemental Material

    Download (457kB) | Preview

    Abstract

    This paper proposes a penalized likelihood method to estima te a trivariate probit model, which accounts for several types of covariate effects (such as linear, nonl inear, random and spatial effects), as well as error correlations. The proposed approach also addresses the dif ficulty in estimating accurately the correlation coefficients, which characterize the dependence of binary r esponses conditional on covariates. The param- eters of the model are estimated within a penalized likeliho od framework based on a carefully structured trust region algorithm with integrated automatic multiple smoothing parameter selection. The relevant nu- merical computation can be easily carried out using the SemiParTRIV() function in a freely available R package. The proposed method is illustrated through a case s tudy whose aim is to model jointly adverse ∗ To whom correspondence should be addressed. c The Author 2017. Published by Oxford University Press. All r ights reserved. For permissions, please e-mail: journals.p ermissions@oup.com 2 P. F ILIPPOU , G. M ARRA AND R. R ADICE birth binary outcomes in North Carolina.

    Metadata

    Item Type: Article
    Additional Information: This is a pre-copyedited, author-produced PDF of an article accepted for publication following peer review. The version of record is available online at the link above.
    Keyword(s) / Subject(s): additive predictor, correlation-based penalty, penalized regression spline, simultaneous parameter estima- tion, trivariate probit model
    School: Birkbeck Schools and Departments > School of Business, Economics & Informatics > Economics, Mathematics and Statistics
    Depositing User: Rosalba Radice
    Date Deposited: 15 Feb 2017 11:48
    Last Modified: 01 Aug 2018 00:10
    URI: http://eprints.bbk.ac.uk/id/eprint/18129

    Available Versions of this Item

    • Penalized likelihood estimation of a trivariate additive probit model. (deposited 15 Feb 2017 11:48) [Currently Displayed]

    Statistics

    Downloads
    Activity Overview
    48Downloads
    149Hits

    Additional statistics are available via IRStats2.

    Archive Staff Only (login required)

    Edit/View Item Edit/View Item