BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:Asking (the right) research questions in data science ST-LE-2026-0
 8
DTSTART:20260326T090000Z
DTEND:20260326T113000Z
DTSTAMP:20260513T090100Z
UID:indico-event-104@events.gfbio.org
CONTACT:data-train@vw.uni-bremen.de\;+49 (421) 218 60043
DESCRIPTION:Speakers: Vanessa Didelez (Leibniz-Institut für Präventionsf
 orschung und Epidemiologie - BIPS)\n\nMotivation“An approximate answer t
 o the right question is worth a great deal more than a precise answer to t
 he wrong question” said the renowned statistician John Tukey as early as
  1969.Based on my own experience in statistical consultations\, much confu
 sion occurs due to a mismatch between research question and data/methods. 
 However\, even more fundamentally\, the research question is often not eve
 n clearly articulated at the outset – perhaps because researchers antici
 pate that the right question can only be answered approximately. But how c
 an we discuss what data and methods are suitable\, if we are unclear or va
 gue about the question to be answered? It seems that now\, in the era of b
 ig data characterised by an abundance of data and a similar abundance of m
 ethods for analysing the data\, the issue of asking the right question rec
 eives a new urgency.Learning contents In this course we will discuss the 
 different types of research questions one might face in a variety of appli
 ed fields within data science\, such as psychology\, epidemiology\, geneti
 cs\, or political & social sciences. Key distinctions concern questions th
 at are (i) descriptive\, (ii) predictive\, or (iii) causal (i.e. about cou
 nterfactual prediction). We will consider how these types of research ques
 tions are interrelated with the choices / requirements of data\, methods o
 f analysis\, and the need for more or less specific subject matter backgro
 und knowledge. We will see how starting with a clear and explicit research
  question helps with assessing\, and maybe avoiding\, potential sources of
  (structural) bias in answering that research question.Key topics that wil
 l be covered:Types of research questions (descriptive\, predictive\, causa
 l/counterfactual)Issues of validity and structural bias (e.g. selection\, 
 confounding\, ascertainment)The target trial principleLearning outcomes U
 pon completion\, participants of the course will be able to:categorise res
 earch questions as descriptive\, predictive or causalelicit a research que
 stion by formulating a target trialdetermine implications for the required
  data and choice of appropriate methodsidentify possible threats to validi
 ty / sources of structural bias.Prior knowledge---Further readingMiguel A.
  Hernán\, John Hsu & Brian Healy (2019) A Second Chance to Get Causal Inf
 erence Right: A Classification of Data Science Tasks\, CHANCE\, 32:1\, 42-
 49.Miguel A. Hernán\, James M. Robins\, Using Big Data to Emulate a Targe
 t Trial When a Randomized Trial Is Not Available\, American Journal of Epi
 demiology\, Volume 183\, Issue 8\, 15 April 2016\, Pages 758–764.Huitfel
 dt A.\, Is caviar a risk factor for being a millionaire? BMJ 2016\; 355:i6
 536 doi:10.1136/bmj.i6536\; https://www.bmj.com/content/355/bmj.i6536 htt
 ps://catalogofbias.org/ \n\nhttps://events.gfbio.org/event/104/
LOCATION:Zoom
URL:https://events.gfbio.org/event/104/
END:VEVENT
END:VCALENDAR