Profile

338Canada

Profile for 338Canada. Every fact below is a verbatim quote from a real document we have stored. ↩ See the full Record

Relationships
Established facts
  • TheWrit.ca/338Canada are the closest to a Canadian equivalent of FiveThirtyEight · source
  • Canadian by-elections expose systematic riding-level model error that is invisible at the national-aggregate level · source
  • Toronto–St. Paul's was an uninstrumented event · source
  • Philippe J. Fournier publishes pollster ratings page · source
  • there is no methodological consensus in Canadian psephology on whether to correct for cumulative known-directional bias · source
  • Fournier's public methodology page describes a mostly proportional swing model with regional adjustments · source
  • the model weights polls by recent accuracy · source
  • the binomial standard error is √(0.40·0.60/1500) = 1.26 percentage points · source
Drawn from 2 source documents in the Library. Every attribute and relationship above traces back to a verbatim quote.