Numerous inaccuracies found in political prediction polls

GHN News Editor - Prior
to the 2010 mid-term election, pollsters were out in force taking the
pulse of the American people with respect to voting patterns, that
researchers say in many respects were faulty and biased as well, thus influencing outcomes.

Nate Silver did an analysis of some of these polls on his

FiveThirtyEight blog, finding not only a number of inaccuracies but also
bias in the predictions made.

Virginia Miori, Ph.D., assistant professor of decision and system sciences at Saint Joseph’s University
in Philadelphia and an expert on predictive analytics, maintains this
type of finding is commensurate with other findings that reflect
problems caused by bias. “Surveys and polls are known for problems with
bias even in the best cases,” she says.

What determines a poll's accuracy has to do with the methodology used and the size of the sampling.

“Simply stated, the polling agencies (like those reviewed by Silver)
did not question the right combination of individuals,” says Miori. “In
addition, a particular polling agency will be very likely to ask
questions biased toward the results they are seeking.”

 Miori
continues by describing polling as something requires precision and
scientific methods.  Even the type of day the poll is taken can figure
into its results.

“Consider
blue collar workers versus white collar workers. They are available at
different times of the day and are likely to have very different access
to technology such as cell phones during both work and non-work hours.
If a poll is taken over a specific four-hour period, as this was, it is
likely that these groups would not be as equally represented,” she says.
“Further, consider that one person may answer the same question
differently based on their mood, or the type of day they've had.”

To ensure accuracy, the pollster must use methods that are consistent and scientifically based, says Miori.

“The
best we can do when polling is to maintain complete consistency in the
approach, ask unbiased questions and strive to survey a sample that
closely matches the characteristics of the population of voters. The
polling agencies with the least interest in the outcome of the election
always perform the best.”

Nate Silver is the New York Times "political calculator."  Today's entry asks,Is Pelosi America’s Most Unpopular Politician?which
might be interesting to find out and to learn whether Silver uses the
type of strategy he advocates for pollsters in presenting his opinions.

The list of the various poll predictions are found here, reflecting considerable differences and spread of results on the predictions.

Scott Rasmussen often is a guest on Sean Hannity and
other Fox News shows and has been accused of bias for the Republicans by
libertarian foes.  His poll is often quoted by Republican groups, but
his results widely quoted across the political spectrum.  It is also interesting to note that Rasmussen has 69,985 Twitter followers but follows only four individuals/groups, one of which is a director and the other three all Fox News commentators.