Figure - uploaded by Pavel D. Atanasov
Content may be subject to copyright.
Study design for Main Research Question; n denotes the number of forecasters in each cell. All data are from Season 4.

Study design for Main Research Question; n denotes the number of forecasters in each cell. All data are from Season 4.

Source publication
Preprint
Full-text available
What systems should we use to elicit and aggregate judgmental forecasts? Who should be asked to make such forecasts? We address these questions by assessing two widely-used crowd prediction systems: prediction markets and prediction polls. Our main test compares a prediction market against team-based prediction polls, using data from a large, multi...

Context in source publication

Context 1
... superforecasters were invited to travel-expenses-paid in-person workshops that took place at university campuses after Seasons 2, 3, and 4. Once qualified, elite forecasters retained this status unless they dropped out or asked to rejoin the sub-elite crowd. Prediction markets with elite forecasters (Supermarkets) consisted of n = 122 traders working independently in an LMSR prediction market (also see Table 2). Team prediction polls with elite forecasters (Superpolls) consisted of 10 teams with 12 to 16 forecasters each, totaling n = 139 forecasters. ...