Recovery of original individual person data (IPD) inferences from empirical IPD summaries only: Applications to distributed computing under disclosure constraints.

There are many settings where individual person data (IPD) are not available, due to privacy or technical reasons, and one must work with IPD proxies, such as summary statistics, to approximate original IPD inferences, that is, the results of statistical analyses that would ideally have been perform...

Full description

Bibliographic Details
Published in:Statistics in Medicine Vol. 39; no. 8; pp. 1183 - 1199
Main Authors: Bonofiglio, Federico, Schumacher, Martin, Binder, Harald
Format: research Journal Article
Published: Wiley-Blackwell 4/15/2020
Online Access:View this record in EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=141996442&site=ehost-live
header:
  @attributes:
    shortDbName: ccm
    uiTerm: 141996442
    longDbName: CINAHL Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    dissinfo:
    jinfo:
      jid:
        02776715
        2DZ
      jtl: Statistics in Medicine
      issn: 02776715
      maglogo: Y
    pubinfo:
      dt: 4/15/2020
      vid: 39
      iid: 8
      pid: 480
      pub: Wiley-Blackwell
      place: Malden, Massachusetts
    artinfo:
      ui:
        141996442
        141996442
        145824896
        NLM31944335
        141996442
        10.1002/sim.8470
        NLM31944335
        141996442
      ppf: 1183
      ppct: 16
      formats:
      tig:
        atl: Recovery of original individual person data (IPD) inferences from empirical IPD summaries only: Applications to distributed computing under disclosure constraints.
      aug:
        au:
          Bonofiglio, Federico
          Schumacher, Martin
          Binder, Harald
        affil: Institute of Medical Biometry and Statistics, Faculty of Medicine, Medical Center University of Freiburg, Freiburg, Germany
      sug:
        subj:
          Study Design
          Truth Disclosure
          Logistic Regression
          Data Analysis, Statistical
          Human
          Data Security
          Comparative Studies
          Multicenter Studies
          Evaluation Research
          Validation Studies
          Scales
          Funding Source
      ab: There are many settings where individual person data (IPD) are not available, due to privacy or technical reasons, and one must work with IPD proxies, such as summary statistics, to approximate original IPD inferences, that is, the results of statistical analyses that would ideally have been performed on individual-level data. For instance, in a distributed computing setting, as implemented in the DataSHIELD software framework, different centers can only share IPD proxies to obtain pooled IPD inferences. Such privacy requirements limit the scope of statistical investigation. For example, it can be challenging to perform between-center random-effect regression models. To increase modeling freedom we propose a method that only uses simple nondisclosive summaries of the original IPD as input, such as empirical marginal moments and correlation matrices, and generates artificial data compatible with those summary features. Specifically, data are generated from a Gaussian copula with marginal and joint components specified by the above summaries. The goal is to reproduce original IPD features in the artificial data, such that original IPD inferences are recovered from the artificial data. In an application example, and through simulations, we show that we can recover estimates of a multivariable IPD random-effect logistic regression, from artificial data generated via the Gaussian copula using the above IPD summaries, suggesting the proposed approach provides a generally applicable strategy for distributed computing settings with data protection constraints.
      pubtype: Academic Journal
      doctype:
        research
        Journal Article
      ougenre: Article
    language: English
    refInfo:
    holdings:
      @attributes:
        islocal: N