Antonio Gasparrini: Open access: a researcher's perspective

Open access: a researcher’s perspective Antonio Gasparrini London School of Hygiene and Tropical Medicine, London, UK Open Research and Data Open Access Week 22 October 2012 - Birbeck College, London

My backgroundGraduated in biology in Italy, then 4 years working asepidemiologist in a cancer research center in FlorenceMSc + postgraduate school (still in Italy) + PhD (in UK) inmedical statistics,Worked at LSHTM in the last 5 years, mainly in statisticalmethodology and software development

My MRC fellowshipAwarded a Research Methodology fellowship from MRC (Dec2011 – Nov 2014)Project developed on my previous researchSuccess of this project critical for next funding applicationNeed to comply with the MRC regulations on open accessMy budget for open access costs: 6000£ in total

OutlineSome points: My perspective: as scientist and junior academic Publishing: steps and costs My publications as a case study Open research: beyond publications

The scientist’s perspectiveI favour a system which: guarantees high-quality research allows the independent assessment of research ﬁndings ensures the dissemination of the such ﬁndings

The academic’s perspectiveI favour a system which: covers the costs of my research delivers a fast and eﬀective peer-review process provides tools for disseminating my work

Publishing a research paper: steps Literature review Drafting the manuscript Choice of the journal and submission Review and acceptance Copyright agreement Open access fee PublicationActors: the researcher, the institution, the research community,the funder, the journals/publishersAn eﬃcient and fair system?

A ﬁrst articlePublished online in Statistics in Medicine (2012): The choice of the journal Copyright transferred Open access fee ∼2250£ Impact factor 1.99

Submitted and published versions Statistics Research ArticleResearch Article in Medicine Received 9 August 2011, Accepted 11 May 2012 Published online in Wiley Online LibraryReceived XXXX (wileyonlinelibrary.com) DOI: 10.1002/sim.5471(www.interscience.wiley.com) DOI: 10.1002/sim.0000Multivariate meta-analysis for non-linear and Multivariate meta-analysis forother multi-parameter associations non-linear and other multi-parameter associationsA. Gasparrinia ∗† , B. Armstrongb , M. G. Kenwarda A. Gasparrini,a * † B. Armstrongb and M. G. KenwardaIn this paper we formalize the application of multivariate meta-analysis and meta-regression to synthesize estimatesof multi-parameter associations obtained from different studies. This modelling approach extends the standard In this paper, we formalize the application of multivariate meta-analysis and meta-regression to synthesizetwo-stage analysis used to combine results across different sub-groups or populations. The most straightforward estimates of multi-parameter associations obtained from different studies. This modelling approach extends the standard two-stage analysis used to combine results across different sub-groups or populations. The mostapplication is for the meta-analysis of non-linear relationships, described for example by regression coefficients straightforward application is for the meta-analysis of non-linear relationships, described for example byof splines or other functions, but the methodology easily generalizes to any setting where complex associations regression coefficients of splines or other functions, but the methodology easily generalizes to any settingare described by multiple correlated parameters. The modelling framework of multivariate meta-analysis is where complex associations are described by multiple correlated parameters. The modelling framework ofimplemented in the package mvmeta within the statistical environment R. As an illustrative example, we propose multivariate meta-analysis is implemented in the package mvmeta within the statistical environment R. Asa two-stage analysis for investigating the non-linear exposure-response relationship between temperature and non- an illustrative example, we propose a two-stage analysis for investigating the non-linear exposure–responseaccidental mortality using time series data from multiple cities. Multivariate meta-analysis represents a useful relationship between temperature and non-accidental mortality using time-series data from multiple cities.analytical tool for studying complex associations through a two-stage procedure. Copyright c 2011 John Wiley & Multivariate meta-analysis represents a useful analytical tool for studying complex associations through a two-stage procedure. Copyright © 2012 John Wiley & Sons, Ltd.Sons, Ltd. Keywords: meta-analysis; multivariate analysis; multivariate meta-analysis; non-linear; splinesKeywords: meta-analysis; multivariate analysis; multivariate meta-analysis; non-linear; splines 1. Introduction1. Introduction Meta-analysis is a standard, well-grounded statistical procedure for combining the evidence from inde-Meta-analysis is a standard, well-grounded statistical procedure for combining the evidence from independent studies pendent studies that address the same research hypothesis [1]. This methodology was developed origi-that address the same research hypothesis [1]. This methodology was developed originally for pooling the results from nally for pooling the results from published observational or experimental studies, for which individualpublished observational or experimental studies, for which individual data were not available. Recently, meta-analysis has data were not available. Recently, meta-analysis has been described more broadly as a research synthesisbeen described more broadly as a research synthesis method, with the aim of estimating an average association across method, with the aim of estimating an average association across studies and to explore the degree andstudies and to explore the degree and sources of heterogeneity [2]. The analytical approach adopted in this context may be sources of heterogeneity [2]. The analytical approach adopted in this context may be described as adescribed as a two-stage hierarchical procedure: in the first stage, study-specific estimates of the association of interest are two-stage hierarchical procedure: in the first stage, study-specific estimates of the association of interestderived from individual data, controlling for individual-level covariates; in the second stage, these estimates are combined are derived from individual data, controlling for individual-level covariates; in the second stage, theseacross studies, optionally exploring the association with study-level predictors. The two-stage approach, a specific form estimates are combined across studies, optionally exploring the association with study-level predictors.of individual patient data (IPD) meta-analysis, has been shown to be a flexible and computationally efficient method [3], The two-stage approach, a specific form of individual patient data (IPD) meta-analysis, has been shownand has been adopted in different contexts: to pool estimates from multiple randomized controlled trials [4]; to combineresults from survival models on time-to-event data in multi-centre cohorts [5]; and to synthesize associations from Poisson to be a flexible and computationally efficient method [3] and has been adopted in different contexts: totime series models in multi-city analyses [6]. pool estimates from multiple randomized controlled trials [4]; to combine results from survival models The common approach to two-stage meta-analysis consists of summarizing the association in a single parameter on time-to-event data in multi-centre cohorts [5]; and to synthesize associations from Poisson time-seriesestimate from the first stage, optionally controlling for individual-level confounders. This procedure allows standard meta- models in multi-city analyses [6].analytic techniques to be applied. However, complex associations, such as non-linear exposure-responses, are usually The common approach to two-stage meta-analysis consists of summarizing the association in a singledescribed with functions defined by multiple parameters, and require more sophisticated meta-analytical approaches, parameter estimate from the first stage, optionally controlling for individual-level confounders. Thiscapable of handling the multivariate nature of the summary estimates. Multivariate meta-analysis, a method originally procedure allows standard meta-analytic techniques to be applied. However, complex associations, such as non-linear exposure–responses, are usually described with functions defined by multiple parameters and require more sophisticated meta-analytical approaches capable of handling the multivariate nature of the summary estimates. Multivariate meta-analysis, a method originally developed to pool multiplea Department of Medical Statistics, London School of Hygiene and Tropical Medicineb Department of Social and Environmental Health Research, London School of Hygiene and Tropical Medicine∗ Correspondence to: Antonio Gasparrini, London School of Hygiene and Tropical Medicine, Keppel Street, London WC1E 7HT, UK.† E-mail: antonio.gasparrini@lshtm.ac.uk a Department of Medical Statistics, London School of Hygiene and Tropical Medicine, London, U.K. b Department of Social and Environmental Health Research, London School of Hygiene and Tropical Medicine, London, U.K.Contract/grant sponsor: Medical Research Council (UK), grants G0701030 and G1002296 *Correspondence to: Antonio Gasparrini, London School of Hygiene and Tropical Medicine, Keppel Street, London WC1E 7HT, U.K. † E-mail: antonio.gasparrini@lshtm.ac.ukStatist. Med. 2011, 00 1–18 Copyright c 2011 John Wiley & Sons, Ltd.Prepared using simauth.cls [Version: 2010/03/10 v3.00] Copyright © 2012 John Wiley & Sons, Ltd. Statist. Med. 2012

A second articleFirstly submitted to Biostatistics: Copyright transferred Open access fee ∼2250£ Impact factor 2.145Rejected, re-submitted to BMC Med Res Method: Copyright retained Open access fee ∼1475£ (∼1255£ with LSHTM discount) Impact factor 2.67

A third articlePublished in Journal of Statistical Software (2011): Not automatically indexed in PubMed Included ’manually’ through PubMed Central Copyright retained Open access fee: 0£ Impact factor 4.01

Open research: beyond publishingOpen data: research data collected with public funding availableto other researchersOpen source and free softwareReproducible research: open and thorough assessment ofresearch ﬁndings

A similar caseStatistical software is mainly based on commercial programs(e.g. Stata, SAS, SPSS)Substantial fees to be paid by research institutionsHowever, implementation of novel methodologies provided byresearchersSame story: researchers working (for free) for third parties...

An alternative modelAn example: the R softwareA project entirely based on a community of users and developersComparison with commercial programsModel also applicable to publishing

The third article againThe manuscript is freely available at journal’s web site and otherrepositoriesThe code for the analysis is included as supplementary materialThe software is implemented and fully documented in a freestatistical packageThe data are stored online and freely available through thesoftwareAll of this at no cost

The internet eraDiﬀerent approach to search and dissemination: what role forjournals?Drop in editorial and publication costs: do we really needpublishers?Role of funders, institutions and research community is criticalWhy so late?!

The open access eraImportant changes: Wellcome and RCUK policiesLimitations of the Finch ReportAlternative models already availableChanges require a diﬀerent approach from researchers

Antonio Gasparrini: Open access: a researcher's perspective

by NeilStewartCity on Oct 30, 2012

Accessibility

Categories

Upload Details

Usage Rights

Statistics

Antonio Gasparrini: Open access: a researcher’s perspective Presentation Transcript