Here, we address the issue of forecasting from statistical models, and how they might be improved. Our real-world example is the forecasting of US presidential elections. First, we ask whether a model should be changed. To illustrate problems and opportunities, we examine the forecasting history...

We look at the substantive theory behind political forecasting models, which are generally based on theories of electoral behavior. We argue that the theory relied on for developing forecasting models should be as non-controversial as possible; what we call “core theory”. We take the lessons...

The behavior of the individual Spanish voter has come to be rather well-understood, thanks to a growing body of literature. However, no models have appeared to explain or forecast national election outcomes. This gap in the research contrasts sharply with the extensive election forecasting work...

In the field of election forecasting, France is a lead case. Recently, however, certain modelers stumbled badly in their efforts to forecast the 2007 presidential election. The difficulty appears due partly to the single-equation format that has constrained past work, and partly to a failure to...