Question:
the election for President were held today, and the candidates were Hillary Clinton, the Democrat, Donald Trump, the Republican, Gary Johnson, the Libertarian, and Jill Stein, the Green-Rainbow Party candidate, would you vote for Hillary Clinton, Donald Trump, Gary Johnson, Jill Stein, or some other candidate for President? If no preference is stated initially: At this moment do you lean more toward Hillary Clinton, Donald Trump, Gary Johnson, or Jill Stein?
Clinton 56%
Trump 26%
Johnson 8%
Stein 3%
Don't Know 3%
Refulsed 3%

About this Poll
The Western New England University Polling Institute conducted a telephone survey Oct. 23 – Nov. 2, 2016. Western New England University sponsored and funded the study. The survey sample consists of telephone interviews in English only with 504 adults ages 18 and older drawn from across Massachusetts using random-digit-dialing. The sample yielded 470 adults who said they are registered to vote in Massachusetts, and 417 voters classified as likely to vote in the Nov. 8, 2016 general election. Likely voters were identified in one of two ways. (1) Seventy-three voters who said they had already voted early or by absentee ballot were counted as part of the subsample of likely voters. (2) Individuals who had not yet voted at the time of the phone interview were classified as likely voters based on their responses to questions about interest in the upcoming election, likelihood of voting in the election, participation in the 2012 presidential and 2014 gubernatorial elections, and knowledge of the location and name of their polling place.

All surveys are subject to sampling error, which is the expected probable difference between interviewing everyone in a population versus a scientific sampling drawn from that population. The margin of sampling error for a sample of 470 registered voters is +/- 4.5 percent at a 95 percent confidence interval, and the margin of sampling error for a sample of 417 likely voters is +/- 5 percent at a 95 percent confidence interval. Thus if 55 percent of likely voters said they support Hillary Clinton for president, one would be 95 percent sure that the true figure would be between 50 percent and 60 percent (55 percent +/- 5 percent) had all likely voters in Massachusetts been interviewed, rather than just a sample. Sampling error increases as the sample size decreases, so statements based on various population subgroups are subject to more error than are statements based on the total sample. Sampling error does not take into account other sources of variation inherent in public opinion studies, such as non-response, question wording, or context effects.