BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//ox.ac.uk//NONSGML oxford.event//EN
X-WR-TIMEZONE:Europe/London
BEGIN:VTIMEZONE
TZID:Europe/London
X-LIC-LOCATION:Europe/London
BEGIN:DAYLIGHT
DTSTART:19700329T010000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:BST
TZOFFSETFROM:+0000
TZOFFSETTO:+0100
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:19701025T020000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:GMT
TZOFFSETFROM:+0100
TZOFFSETTO:+0000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
SUMMARY:Introducing RobustiPy: An efficient next-generation multiversal li
 brary with model selection\, averaging\, resampling\, and explainable AI
DTSTART;TZID=Europe/London:20260527T110000
DTEND;TZID=Europe/London:20260527T120000
DTSTAMP:20260517T060730Z
UID:9933e7d4-f628-f111-88b4-7c1e52046306
CREATED:20260326T093326Z
DESCRIPTION:For our next Data Engineering meeting\, we will be hearing fro
 m Dr Charles Rahal\, Associate Professor in Data Science and Informatics\,
  LCDS\, University of Oxford. We’re delighted to host Charles in what pr
 omises to be a great talk!\n\nDate: Wednesday 27 May\nTime: 11:00 – 12:0
 0\nTalk title: Introducing RobustiPy: An efficient next-generation multive
 rsal library with model selection\, averaging\, resampling\, and explainab
 le AI\nLocation: Big Data Institute\, Seminar Room 0\nRegistration: https:
 //forms.office.com/e/mSfmZVXC9Z?origin=lprLink\n\nAbstract\nScientific inf
 erence is often undermined by the vast but rarely explored `multiverse' of
  defensible modeling choices which can generate results as variable as the
  phenomena under study. We introduce RobustiPy\, an open-source Python lib
 rary that systematizes multiverse analysis and model-uncertainty quantific
 ation at scale. RobustiPy unifies bootstrap-based inference\, combinatoria
 l specification search\, model selection and averaging\, joint-inference r
 outines\, and explainable AI methods within a modular\, reproducible frame
 work. Beyond exhaustive specification curves\, it supports rigorous out-of
 -sample validation and quantifies the marginal contribution of each covari
 ate. We demonstrate its utility across five simulation designs and ten emp
 irical and high-profile replications spanning economics\, sociology\, psyc
 hology\, and medicine\, including a re-analysis of widely cited findings w
 ith documented discrepancies. Benchmarking on ~672 million simulated regre
 ssions shows that RobustiPy delivers state-of-the-art computational effici
 ency while expanding transparency in empirical research. By standardizing 
 and accelerating methods for robustness\, RobustiPy transforms how researc
 hers interrogate sensitivity across the analytical multiverse\, offering a
  practical foundation for more reproducible and interpretable computationa
 l science.\n\nShort biography\nCharles is an Associate Professor in Data S
 cience and Informatics at the University of Oxford\, and a former British 
 Academy Postdoctoral Fellow and a Sino-British Visiting Fellow at the Univ
 ersity of Hong Kong. He's also an Honorary Visiting Professor at Peking Un
 iversity. He maintains various open and interactive online projects\, such
  as the GWAS Diversity Monitor and RobustiPy\, and is active in the Open S
 cience movement. He has consulted on Methods Advisory Groups for the ONS (
 pro bono)\, and currently consults for the Banco de la República. He is b
 oth an Associate Member at Nuffield College and a Researcher at the Gradel
  Institute\, New College\, as well as an Associate Editor-In-Chief at the 
 Journal of Social Computing\, and an Associate Editor at ACM Transactions 
 on Social Computing. He is a moderator of SocArXiv\, as well as a Research
  Affiliate at the Public Knowledge Project\, while also convening the ‘M
 etrics and Models’ lab\, which has an open seminar series component to i
 t\; all are welcome to attend. \n\n—————————————
 —————————————————————\nAll membe
 rs of the University are welcome to join\, please let reception at BDI kno
 w you’re here for the Data Engineers meeting and sign-in. We hope you ca
 n join us!\n\nMicrosoft Teams meeting \nLink to be shared nearer the time\
 n————————————————————————
 ———————————\n If you wish to know more or receive in
 formation related to trainings and events at BDI\, please subscribe by ema
 iling bdi-announce-subscribe@maillist.ox.ac.uk. You’ll then receive an e
 mail from SYMPA and once you reply you’ll be on the list!
LAST-MODIFIED:20260327T092405Z
LOCATION:Big Data Institute - Lower Ground Seminar Room 0\, Lower Ground S
 eminar Room 0 Big Data Institute Old Road Campus Oxford Oxfordshire OX3 7L
 F United Kingdom
SPEAKER:Dr Charles Rahal (LCDS\, University of Oxford)
END:VEVENT
END:VCALENDAR