BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//jEvents 2.0 for Joomla//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
BEGIN:VEVENT
UID:064f3220b0c355310ba1ab39c9025ee8
CATEGORIES:Seminars
CREATED:20250108T112632
SUMMARY:Stefano della Vigna - University of California, Berkeley
DESCRIPTION;ENCODING=QUOTED-PRINTABLE:\n\nForecasting Social Science: Evidence from 100 Projects\n\n\nAbstract:\n
 Increasingly, researchers gather forecasts ex ante about the results of the
 ir research studies. Ex post, this allows for a comparison of these forecas
 ts with the results to capture the direction and extent of learning and to 
 counter the “we knew it already” audience response. But what do we know abo
 ut the accuracy of these forecasts? We use a unique data set from the Socia
 l Science Prediction Platform for all 100 of the projects posted in the 202
 0-24 period, including results for 60% of the projects. This unique data se
 t contains detailed information on the projects and the forecasters, includ
 ing tracking forecasts across projects. Using this data set, we examine 10 
 questions about these forecasts: (1) the average predicted effect size: (2)
  the comparison to realized effect sizes; (3) the predictability of effect 
 sizes with average forecasts. Turning to the accuracy of individual forecas
 ts, we compare (4) academics to non-academics, (5) experts in a field to no
 n-experts, (6) panelists to other forecasters, (7) we estimate the extent o
 f learning over time and (8) the impact of confidence on accuracy. Finally,
  we consider whether (9) there are superforecasters, with consistently high
 er accuracy and (10) we estimate the extent of wisdom of crowds. We draw th
 e implications of the findings for forecasting and updating in science.\n
DTSTAMP:20260517T104853Z
DTSTART:20250505T163000Z
DTEND:20250505T180000Z
SEQUENCE:0
TRANSP:OPAQUE
END:VEVENT
END:VCALENDAR