Access

You are not currently logged in.

Access your personal account or get JSTOR access through your library or other institution:

login

Log in to your personal account or through your institution.

What Do We Know at 7 PM on Election Night?

ANDREW GELMAN and NATE SILVER
Mathematics Magazine
Vol. 83, No. 4 (October 2010), pp. 258-266
DOI: 10.4169/002557010x521787
Stable URL: http://www.jstor.org/stable/10.4169/002557010x521787
Page Count: 9
  • Download ($16.00)
  • Subscribe ($19.50)
  • Cite this Item
Item Type
Article
References
What Do We Know at 7 PM on Election Night?
Preview not available

Abstract

Summary We use a probability forecasting model to estimate the chance of different branches on the tree of state-by-state outcomes on election night. Forecasting models can use data from pre-election surveys as well as extrapolation based on previous election results. We implement conditional probability calculations numerically using a matrix representing 10,000 simulations of the outcomes in the 50 states.

Page Thumbnails