The phrase "a likely voter" is correct and usable in written English.
It can be used in contexts related to elections, surveys, or political discussions to refer to someone who is expected to participate in voting.
Example: "The poll indicated that a likely voter is someone who has expressed a strong interest in the upcoming election."
Alternatives: "an expected voter" or "a probable voter".
Gallup's registered voter sample, therefore, seems to be acting like a likely voter screen in terms of the ethnic makeup of the electorate.
In a typical year, a likely voter model or screen functions like a nudge.
Polls from the media and academic institutions may have fluctuated by the hour, but drawing on hundreds of data points to judge whether someone was a likely voter proved more reliable than using a seven-question battery like Gallup's to do the same.
Most pollsters are modeling their surveys to a "likely voter electorate" based on what previous mid-term elections looked like.
If you have a sample that is biased toward enthusiastic respondents to begin with, and then apply a likely voter screen, it risks double-counting the enthusiasm factor, especially in cases like presidential general elections when overall turnout is quite high.
On the other hand, most of the state polls do not require a likely voter adjustment, since they were already conducted on a likely voter basis.
Their vote counts exactly the same as a "likely voters" -- and both received ballots in the mail last week.
Siena College based its percentages on all registered voters without applying a likely-voter model.
I get even more concerned when I see a likely-voter screen on top of a sample that was already especially likely to vote.
And if there's only a likely-voter survey, the model shifts the numbers toward Mr. Obama by a couple of points as a proxy for a registered voter poll.
And if only a registered-voter version is available, we shift the numbers by two or three points toward Mr. Romney in order to make it equivalent to a likely-voter poll.
