BEGIN:VCALENDAR VERSION:2.0 METHOD:PUBLISH PRODID:-//Telerik Inc.//Sitefinity CMS 15.4//EN BEGIN:VTIMEZONE TZID:UTC BEGIN:STANDARD DTSTART;VALUE=DATE:20250101 TZNAME:UTC TZOFFSETFROM:+0000 TZOFFSETTO:+0000 END:STANDARD END:VTIMEZONE BEGIN:VEVENT DESCRIPTION:Date: Tuesday 5th May 2026Time: \;14:00 - 15:00 GMT | 9:00 - 10:00 EST (US) \; \;| 15:00 - 16:00 CETLocation: \;Online vi a ZoomSpeakers: \;Nick Galwey\, \;GSK (Retired)Who is this event i ntended for?: \;Statisticians interested in learning about False Disco very Rate and Shrunk Estimates \;What is the benefit of attending?:To gain a deeper understanding of tools used to address multiplicity\, explor e how these methods relate to one another\, and see how they perform when applied to both real human gene‑expression data and simulated datasets.Bri ef event overview:This talk will explore the &ldquo\;replication crisis&rd quo\; in science\, focusing on how testing large numbers of hypotheses can lead to false positive findings. It introduces key statistical approaches &mdash\;False Discovery Rate (FDR) and shrinkage methods&mdash\;to address this issue\, and explains their conceptual foundations and connections. T he session will also highlight how these tools can be understood within an empirical-Bayesian framework\, linking significance testing with effect s ize estimation.Cost:This webinar is free to both Members of PSI and Non-Me mbers.Registration:To register for this event\, please click hereOverview: Science is currently facing a &lsquo\;replication crisis&rsquo\; &ndash\; a concern that many scientific findings reported are difficult or impossib le to reproduce. \;  \;A major cause of this is the availability o f technology that permits the exploration and testing of very large number s of hypotheses\, some of which will almost certainly show significant or large effects by chance\, even when no real effects are present: this is t he &lsquo\;multiplicity&rsquo\; or &lsquo\;multiple testing&rsquo\; proble m. \;  \;The statistical tools available to address this problem i nclude:the False Discovery Rate (FDR)\, which is specified in relation to the subset of the m hypotheses tested for which the discovery of an effect is reported\, and which indicates the proportion of these &lsquo\;discove ries&rsquo\; that is expected to be false\; andshrunk estimates\, which re duce the estimated effect\, in relation to every individual hypothesis\, f rom the observed value towards the null value.This talk will first examine the conceptual basis for each of these tools\, then consider how they are connected. \;  \;Though the FDR and shrunk estimates are both con ventionally presented in the frequentist statistical framework\, they can both also be presented in empirical-Bayesian terms\, the prior probability distribution being calculated from the data relating to the m hypotheses tested\, as follows:in the case of the FDR\, from the proportion of the m significance tests conducted that give a p-value at or below the specified significance threshold\, and that are therefore announced as &lsquo\;disc overies&rsquo\;\; andin the case of shrunk estimates\, from the distributi on of the observed effect sizes over the m hypotheses.Based on this connec tion\, a formal relationship between FDR values and shrunk estimates will be presented\, and it will be argued that these two tools can profitably b e used in conjunction. \;  \;Their combined application\, both to real (human gene expression) data and to simulated data\, will be illustra ted. \;  \;Speaker detailsSpeakerBiographyNick Galwey\, \;Form er Statistics Leader\, \;GSK (retired)Nick was a demonstrator and lect urer in biometry and plant breeding at the University of Cambridge from 19 79 to 1995\, when he was appointed to a senior lectureship at the Universi ty of Western Australia\, Perth. \;  \;In 2001 he returned to the UK\, working as a statistical geneticist at Oxagen Limited\, Oxfordshire\, until 2004. He then moved to GlaxoSmithKline\, first as a statistical gen eticist and later as a statistician\, supporting pre clinical and clinical research and epidemiology\, until he retired in September 2024. \; &n bsp\;He is the author\, or a co-author\, of more than 100 scientific paper s. \; His most recent book is:Galwey\, N.W. (2025) The False Discovery Rate: Its Meaning\, Interpretation and Application in Data Science. Chich ester\, UK: Wiley. 266pp. ISBN 9781119889779 \; DTEND:20260505T150000Z DTSTAMP:20260506T143405Z DTSTART:20260505T140000Z LOCATION: SEQUENCE:0 SUMMARY:Connecting the False Discovery Rate to Shrunk Estimates UID:RFCALITEM639136748454864937 X-ALT-DESC;FMTTYPE=text/html:Date: Tuesday 5th May 2026
Time: \;14:00 - 15:00 GMT | 9:00 - 10:00 EST (US)& nbsp\; \;| 15:00 - 16:00 CET
Location: \;Onl ine via Zoom
Speakers: \;Nick Galwey\, \ ;GSK (Retired)

Who is this e vent intended for?: \;
Statisticians interested in learning about False Discovery Rate and Shrunk Estimates
 \;
What is the benefit of attending?:
T o gain a deeper understanding of tools used to address multiplicity\, expl ore how these methods relate to one another\, and see how they perform whe n applied to both real human gene‑expression data and simulated datasets.< /div>

Brief event overview:
This talk will explore the &ldquo\;replication crisis&rdquo\; in science \, focusing on how testing large numbers of hypotheses can lead to false p ositive findings. It introduces key statistical approaches&mdash\;False Di scovery Rate (FDR) and shrinkage methods&mdash\;to address this issue\, an d explains their conceptual foundations and connections. The session will also highlight how these tools can be understood within an empirical-Bayes ian framework\, linking significance testing with effect size estimation.< /div>

Cost:
This webinar i s free to both Members of PSI and Non-Members.

Registration:
To register for this event\, plea se click here
< br />
Overview:

Science is current ly facing a &lsquo\;replication crisis&rsquo\; &ndash\; a concern that man y scientific findings reported are difficult or impossible to reproduce.&n bsp\;  \;A major cause of this is the availability of technology that permits the exploration and testing of very large numbers of hypotheses\, some of which will almost certainly show significant or large effects by c hance\, even when no real effects are present: this is the &lsquo\;multipl icity&rsquo\; or &lsquo\;multiple testing&rsquo\; problem. \;  \;T he statistical tools available to address this problem include:

  • the False Discovery Rate (FDR)\, which is specified in relation to the su bset of the m hypotheses tested for which the discovery of an effect is re ported\, and which indicates the proportion of these &lsquo\;discoveries&r squo\; that is expected to be false\; and
  • shrunk estimates\, which reduce the estimated effect\, in relation to every individual hypothesis\ , from the observed value towards the null value.

T his talk will first examine the conceptual basis for each of these tools\, then consider how they are connected. \;  \;Though the FDR and sh runk estimates are both conventionally presented in the frequentist statis tical framework\, they can both also be presented in empirical-Bayesian te rms\, the prior probability distribution being calculated from the data re lating to the m hypotheses tested\, as follows:

  • in the case of the FDR\, from the proportion of the m significance tests conducted that give a p-value at or below the specified significance thres hold\, and that are therefore announced as &lsquo\;discoveries&rsquo\;\; a nd
  • in the case of shrunk estimates\, from the distribution of the observed effect sizes over the m hypotheses.
Based on this connection\, a formal relationship betw een FDR values and shrunk estimates will be presented\, and it will be arg ued that these two tools can profitably be used in conjunction. \; &nb sp\;Their combined application\, both to real (human gene expression) data and to simulated data\, will be illustrated. \;  \;

Speaker details

Speaker

Biography

Nick Galwey\, \;For mer Statistics Leader\, \;GSK (retired)
Nick was a demonstrator and lecturer in biometry and plant breeding a t the University of Cambridge from 1979 to 1995\, when he was appointed to a senior lectureship at the University of Western Australia\, Perth.  \;  \;In 2001 he returned to the UK\, working as a statistical genetic ist at Oxagen Limited\, Oxfordshire\, until 2004. He then moved to GlaxoSm ithKline\, first as a statistical geneticist and later as a statistician\, supporting pre clinical and clinical research and epidemiology\, until he retired in September 2024. \;  \;He is the author\, or a co-autho r\, of more than 100 scientific papers. \; His most recent book is:
Galwey\, N.W. (2025) The False Discovery Rate: Its Meaning\, Inter pretation and Application in Data Science. Chichester\, UK: Wiley. 266pp. ISBN 9781119889779 \;



END:VEVENT END:VCALENDAR