This Daily Beast article clearly describes certain polling practices and defines registered-voters versus likely-voters (“those registered voters who are the most committed to casting a ballot, who have given the most thought to the election, and who exhibit a record of voting in the past that suggests they will do so again in the future”).
While I knew those definitions and had a sense of margin of error etc…I was intrigued by this…
“Many pollsters report their election questions on all registered voters up through around September, and then begin to narrow their analysis to the subset of registered voters that appear to be most likely to vote.”
Were the recent polls giving Romney an edge a reflection of the shift that took place between using registered voters to the likely voters?
Further, aren’t there issues with random-digit dialing? “Random digit dialing is more expensive than calling “listed samples,” but is not biased in any way.” What about likely or registered voters who have no desire to participate in a phone survey? Would the lack of their opinion not make a difference?