The summary series is Kerry Percent of the Kerry plus Bush total, the right number to know
if one assumes that all electoral votes will be shared between the two major candidates.
The series is based upon commercial results posted to pollingreport.com, supplemented with
the Rasmussen Reports daily tracking poll.  It assumes comparability across survey
organizations, but not across sampling methods (adults, registered or likely voters) or
question formats (Bush v. Kerry as opposed to Bush v. Kerry v. Nader).  Where
multiple surveys are reported on the same date, aggregation weights by sample size,
i.e., reproducing the grand mean of several studies as if they were one big study.

Dating is by the beginning date of field work, typically about four days earlier than
reporting dates.  Thus the series always appears to be a few days old, even though based
on the most recent available data.  (One can get a decent approximation of release dates
by forward shifting the time scale about four days.) The series will be updated daily through
election day.

The methodology for rendering mixed date and only partially comparable survey results into
a single underlying series is developed in James A. Stimson, Tides of Consent: Public Opinion
in American Politics, New York: Cambridge University Press, 2004 (July), see particularly
Chapter 4: The Great Horse Race: Finding Meaning in Presidential Campaigns. Cambridge
University Press Listing (excerpt, table of contents, front matter, etc.).

Filtering: The smooth line in the graph is an estimate based upon the Hodrick-Prescott filter,
a means of estimating the smooth underlying movement of a time series while limiting the
effects of unpatterned very short term (one day, one poll) variation. The filtered estimate
should capture real long-term shifts in sentiment better than the raw series. Its final day
estimate is the basis for the electoral college forecast.

Electoral College Forecast

The Electoral College forecast begins with the 2000 Bush v. Gore state results.  It assumes
that the states will behave in 2004 as they did in 2000 (except for minor home state adjustments
to Tennessee and Massachusetts) but will add or subtract votes from the party totals in line with
the national popular vote. Thus, if the Kerry-Edwards team were to get exactly the popular vote
percent (about 50.3) as Gore in 2000, then all the states would be predicted to vote as they did
in 2000 (with actual electoral votes reflecting the new apportionment, a net gain of 7 votes for
the "red" states). The net deviation (from 50.3) in the national popular vote is then added  or
subtracted from each state total and its electoral vote given to whichever side surpasses 50% in
the state.

A Comment on Accuracy and Forecasting of Early Season Horse Race Polls:
Early polls are accurate in the sense that they capture the state of political decision-making at
the moment and with relatively little error. These summary estimates are even more accurate
than individual polls because they exploit all the available data and thus are produced from tens
of thousands of respondents, not a few hundred typical of individual releases. But the
fundamental fact of the matter is that most Americans do not know what they are going to do
early in the campaign season and no technology can capture knowledge that does not exist.
Thus the forecasting properties of early polls are quite poor. Indeed, except for one-sided
contests, they hardly forecast at all. (See Tides, Chapter 4 for a demonstration.) After the
party conventions the polls begin to be good forecasting tools.

Jim Stimson