|
November 17, 2008, post mortem, presidential vote equation: The presidential vote equation did well in predicting the 2008 election. The following chart lists the nine predictions that were made from November 1, 2006, through October 30, 2008. The most important prediction from the point of view of judging the vote equation is the last one, which uses the actual economic values (actual as of October 30, 2008). The two-party vote was 53.4 percent for Obama and 46.6 percent for McCain.
Nine Predictions from the Presidential Vote Equation
(Rep. pred.-
Rep. act.)
Dem.--Rep. GROWTH INFLATION GOODNEWS ERROR
Nov. 1, 2006 53.5--46.5 1.8 3.6 1 -0.1
Jan. 31, 2007 53.4--46.6 1.7 3.4 1 0.0
Apr. 27, 2007 53.2--46.8 1.9 3.3 1 0.2
July 27, 2007 52.0--48.0 2.2 3.5 2 1.4
Oct. 31, 2007 51.9--48.1 2.2 3.3 2 1.5
Jan. 31, 2008 52.0--48.0 1.8 3.1 2 1.4
Apr. 30, 2008 52.2--47.8 1.5 3.0 2 1.2
July 31, 2008 51.5--48.5 1.0 3.0 3 1.9
Oct. 30, 2008 51.9--48.1 0.22 2.88 3 1.5
Actual 53.4--46.6 0.22 2.88 3
One feature of the predictions is that they
did not change much across time. On July 27, 2007, the
NIPA data revisions led to one more good news quarter, as did the
July 31, 2008, data revisions. Other things being equal, each additional
good news quarter leads to an increase in the incumbent (Republican) vote
share of 1.075 percentage points. The predictions for the Republicans
varied from 46.5 to 48.5 across this two-year period.
Another feature of the predictions is that they are all fairly accurate. The errors are well within the standard error of the equation of 2.5. In the final analysis the error was 1.5. In general, even two years before the election the equation was giving a fairly accurate view of the election outcome. The presidential vote equation is equation 1 in Table 2 in Presidential and Congressional Vote-Share Equations, American Journal of Political Science, January 2009, 55-72. November 17, 2008, post mortem, congressional vote equation: The congressional vote equation also did well in predicting the 2008 election. The following chart lists the nine predictions that were made from November 1, 2006, through October 30, 2008. Again, the most important prediction from the point of view of judging the vote equation is the last one, which uses the actual economic values (actual as of October 30, 2008). The actual two-party vote share for the House of Representatives was 54.8 percent for the Democrats and 45.2 percent for the Republicans, although these values at the present time are only estimates.
Nine Predictions from the Congressional Vote Equation
(Rep. pred.-
Rep. act.)
Dem.--Rep. GROWTH INFLATION GOODNEWS ERROR
Nov. 1, 2006 56.7--43.5 1.8 3.6 1 -1.9
Jan. 31, 2007 56.6--43.4 1.7 3.4 1 -1.8
Apr. 27, 2007 56.5--43.5 1.9 3.3 1 -1.7
July 27, 2007 55.8--44.2 2.2 3.5 2 -1.0
Oct. 31, 2007 55.8--44.2 2.2 3.3 2 -1.0
Jan. 31, 2008 55.9--44.1 1.8 3.1 2 -1.1
Apr. 30, 2008 55.9--44.1 1.5 3.0 2 -1.1
July 31, 2008 55.5--44.5 1.0 3.0 3 -0.7
Oct. 30, 2008 55.8--44.2 0.22 2.88 3 -1.0
Actual 54.8--45.2 0.22 2.88 3
Again, the predictions did not change much across time, and they are all
fairly accurate. In the final analysis the error was -1.0 percent, well
within the standard error of the equation of 2.1 percent.
The congressional vote equation is equation 2a in Table 2 in
Presidential and Congressional Vote-Share
Equations, American Journal of Political Science, January 2009,
55-72.
|
| Presidential Vote Equation---2004 Update |
|
The following paper presents the 2004 update of the presidential vote
equation.
No specification changes have been made to the equation since the update
in November 1994, following the 1992 election---the "1992 update."
The equation has simply been
reestimated each four-year interval using the latest economic data and the
results of the previous election. The following paper
also contains the first prediction for 2008 using the
2004 update.
November 1, 2006: 2004 update and prediction for 2008
The following paper also presents the 2004 update of the presidential vote
equation in addition to estimated equations for the on-term and mid-term
House elections. All the estimated equations are presented in Table 2,
page 16, of this paper.
The following link allows you to compute your own predictions of the
2008 presidential election and the 2008 House election. The presidential
equation is in column 1 in Table 2 of the above paper, and the
House equation is in column 3. In the above
paper the vote-share variables are
Democratic vote shares, but for purposes of the following calculations the
vote-share variables have been taken to be incumbent (currently Republican)
vote
shares. With appropriate transformations, the estimated equations are
idential using either Democratic vote shares or incumbent vote shares.
Also, the constant terms in the two equations listed in this link
incorporate the effects of all the non-economic variables in the two
equations, which are known at this time. The currently unknown variables
are just the three economic variables.
Predictions for 2008 using the 2004 update:
Original paper:
Previous update papers:
Non technical discussions:
Web site material for previous elections:
Related work:
|