Predicting the Presidential Election

The first and only time I took a political science course was in the summer of 1991 at Le Moyne College as part of a summer college program for Central New York high school students. However, that does not stop me from believing that I can do as good a job or better of predicting the current and future state of the election as several esteemed political scientists and statisticians. I have the General Election Cattle Call, based entirely on current poll numbers and the partisan index. Here are some other models, many developed by professionals:

Helmut Norpoth, a professor at SUNY Stony Brook, uses a model that predicts the winner of the general election based on results during the primary season.

Ray Fair of Yale uses a purely macroeconomic model. His model regularly predicts that Bush will win a 1964-1972-1984 type landslide. This is understandable, since candidates with 51% unfavorables facing opponents with 33% unfavorables usually win 61% of the vote.

Allan Lichtman has a model based entirely on how well the incumbent governs. He claims its mathematical, but it seems a riddled with arbitrary abstractions to me.

Alfred Cuzan and Charles Bundrick of the University of West Florida have another model based upon the perceived relationship between economic indicators and election results. The methodology behind this model is quite sizable, and I have not had time to dig through it yet.

The Iowa Electronic Markets use a simulated stock market model.

J. Scott Armstrong of the University of Pennsylvania, has developed a model based upon poll averages and predictor model averages. Well, at least predictor models developed by professors. He probably wouldn't touch amateurs such as Scott Elliot and myself with a ten-foot poll.

Scott Elliot uses a model much like my own, where only the partisan index and current polling data are used in the calculation. His is the only model that projects Kerry in a better position than the General Election Cattle Call.

Randall Jones of the University of Central Oklahoma offers advice on how to predict election results.

And many, many more.

It particularly annoys me that a University of Pennsylvania professor named J. Scott Armstrong seems oblivious to the existence of my model. Not only does he have almost exactly the same name as the founder of MyDD, but also I live only three blocks from Penn's campus in University City, Philadelphia.

Why do I think my model will do better than those produced by experts? For starters, I reject the notion that any Presidential election before 1948 has any instructive relevance to contemporary Presidential elections. With wildly different electoral structures, Jim Crow still in full-force, no gender suffrage until 1920, highly different immigration patterns, no television, galacticly different nationwide educational opportunities, nearly unrecognizable industry distribution of the workforce, and no reliable polling information, my assumption is that any similarities between pre-1948 and post-1948 are purely coincidental. The forces that drive elections now are not the forces that once drove them.

My second assumption is that favorable / unfavorable polls are better indicators of the future of the campaign than economic models. This has to remain an assumption, since there are insufficient historical data points to demonstrate this claim one way or the other. However, I simply do not trust most broad economic indicators as useful gauges of the national mood concerning the economy.

My third assumption is that while they never seem to be directly on target, polls are usually pretty good indicators of the state of the race, and no better indicators are available. Also, Gallup does not have a lock on relevant polls, although many political scientists are loathe to use anything else since only Gallup has the long-term history needed to develop sufficient data points that can be used in a reliable study.

Still, over the weekend I will start to add some of these models to the President 2004 page, so that my projections are not the only ones available on MyDD. Welcome to Election Prediction central.

Tags: General 2008 (all tags)

Comments

5 Comments

Not Quite Fair
Chris-

I took Econ at Yale with Ray last semester. I wrote on my blog back in March that - as he himself explains - his system may not be as accurate as it has been in the past. The difference is that Bush is the first president to significantly separate job growth from GDP growth.

You can read my full post here: Unfair Predictions

Best,
Daniel
by Daniel Munz 2004-06-11 07:57AM | 0 recs
Lichtman
"He claims its mathematical, but it seems a riddled with arbitrary abstractions to me."

I read his page and he doesn't seem to be claiming any mathematical content - just his opinion of the "keys" he's outlined.  He's pretty upfront about it - he says I evaluate these 13 things and assign them to each party.  The one with most is my predicted winner.  He's clear enough that one could then argue about his analysis.  

Moreover, that's a pretty bold claim for someone who put together an "empirical" model that introduces an enormous amount of mathematical error.  At least Lichtman tells you which keys are quantitative (e.g "Real per-capita economic growth during the term equals or exceeds mean growth during the previous two terms.") versus subjective (e.g "The incumbent-party candidate is charismatic or a national hero.").  

by Scott Pauls 2004-06-11 10:16AM | 0 recs
Re: Lichtman
Touche.

Point taken.

by Chris Bowers 2004-06-11 11:53AM | 0 recs
For "amateur" formulas here is one...
and you can track change over time by following Wayne's diary on kos

http://www.dailykos.com/user/Wayne%20in%20Missouri/diary

Weekly Electoral Vote Update Kerry 292 Bush 246

by Wayne in Missouri

Fri Jun 11th, 2004 at 13:04:19 CST

In an attempt to find out where the candidates are today in the electoral vote I used the following formula:

Take median of Bush vs. Kerry in the last six national polls.

Average Bush or Kerry's lead with the partisan index for each state found here: http://www.mydd.com/special/president

Average the combined total of procedures above to the latest state poll for each candidate (if no state polls later than 5/11/04 no state poll used).

Where a national poll or state poll has both Bush vs Kerry matchups and Bush vs. Kerry vs. Nader matchups I used the Bush vs. Kerry matchup in 43 states and the Bush vs. Kerry vs. Nader in the 7 states where Nader has qualified for ballot status (AZ, CO, FL, KS, MI, MT, MS)

This method combines national polls, a state's partisan History and state polls to try to arrive at a relatively objective picture of where the candidates stand today.

This week's results: Kerry has a 1.5% lead over Bush (0.5% when Nader is included) nationally and leads the electoral vote 292-246.

State by state Bush vs. Kerry matchups are in extended text for every state.

Diaries :: Wayne in Missouri's diary ::

SOLID KERRY STATES (172 electoral votes)
DC (3) Kerry +77.2
RI (4) Kerry +30.1
MA (12) Kerry +26.6
NY (31) Kerry +24.5
HA (4) Kerry +19.3
MD (10) Kerry +17.4
CT (7) Kerry +15.2
NJ (15) Kerry +14.4
DE (3) Kerry +14.1
IL (21) Kerry +13.0
ME (4) Kerry +12.6
VT (3) Kerry +10.9
CA (55) Kerry +10.4

LEAN KERRY (21 electoral votes)

WA (11) Kerry +7.3
MN (10) Kerry +6.0

TOO CLOSE TO CALL (128 EV--99 for Kerry, 29 for Bush)

OR (7) Kerry +4.0
MI (17) Kerry +3.5
PA (21) Kerry +3.1
IA (7) Kerry +1.3
FL (27) Kerry +0.8
WI (10) Kerry +0.6
NM (5) Kerry +0.4
NV (5) Kerry +0.4

NH (4) Bush +0.1
OH (20) Bush +0.7
WV (5) Bush +0.8

LEAN BUSH (84 Electoral Votes)

MO (11) Bush +4.2
VA (13) Bush +4.5
AZ (10) Bush +5.6
LA (9) Bush +6.3
CO (9) Bush +6.7
TN (11) Bush +7.4
AR (6) Bush +7.5
NC (15) Bush +7.9

SOLID BUSH (133 electoral votes)

SC (8) Bush +12.4
KY (8) Bush +13.5
GA (15) Bush +13.9
MS (6) Bush +16.9
AL (9) Bush +17.5
IN (11) Bush +17.9
SD (3) Bush +17.9
TX (34) Bush +18.6
KS (6) Bush +20.8
MT (4) Bush +22.5
OK (7) Bush +22.5
ND (3) Bush +26.6
NE (5) Bush +28.0
AK (3) Bush +30.0
ID (4) Bush +38.5
WY (3) Bush +39.1
UT (4) Bush +42.2

by Keith Brekhus 2004-06-11 12:06PM | 0 recs
Re: Predicting the Presidential Election
...of Pennsylvania professor named J. Scott Armstrong seems oblivious to the existence of my model. Not only does he have almost exactly the same name as the founder of MyDD...

lol. Hey, we got the extra server finally shipped, and it should be going up next week, so we'll have the new-fangled EV-proportional map up within a few weeks at the latest.

by Jerome Armstrong 2004-06-11 01:38PM | 0 recs

Diaries

Advertise Blogads