The US model consists 24 stochastic equations and slightly over 100 identities. There are about 150 exogenous variables and many lagged endogenous variables. The stochastic equations are estimated by two-stage least squares. The data base for the model begins in the first quarter of 1952.
suggests it's fairly complex. The 150 exogenous variables and 100 identities further suggests that a lot of ceteris paribus assumptions are going on. I'd really have to spend some time with the model to assess the sensitivity of the model to those assumptions. Still, it could be interesting reading...thanks for pointing it out to me!
My understanding of Fair’s model fails at the first sentence. An economic approach to election modeling though appeals to me based on both the importance of economics and as an explanation of why election results so often seem to move in sync in modern nations. The reason is either economics or astrology, and I know enough to pick economics.