Rasmussen is out with a new survey of 750 likely voters about the Rhode Island governor’s race, conducted on Oct. 21. Margin of error is plus or minus 4 points. Here are the results:

• Lincoln Chafee: 35%
• Frank Caprio: 28%
• John Robitaille: 25%
• Ken Block: 6%
• Not sure: 6%

The big headline is how close Democrat Frank Caprio and Republican John Robitaille are compared with Rasmussen’s previous survey on Oct. 4 – more good news for the Republican after yesterday’s announcement that the national G.O.P. is going to invest in his campaign. This is the first time Rasmussen has had Caprio under 30% since March. Chafee’s two-point gain is within the margin of error, and Robitaille is back where he was in May. Undecideds are steadily shrinking in number.

Here’s an updated version of my chart tracking Rasmussen’s results since it started polling the race in February (Block isn’t in here because Rasmussen only started including him recently):

The growing support for Robitaille helps explain why Caprio is going after him in a new mailing, as The Associated Press’ Eric Tucker reported earlier today:

Today’s Rasmussen survey is the first new independent poll on the governor’s race we’ve gotten in two weeks, but it won’t be the last before voters cast their ballots. WPRI will release another poll conducted by Fleming & Associates between now and Nov. 2.

The gubernatorial candidates will meet for our last televised debate of the campaign next Tuesday night at 7 p.m. – it will be held at PPAC, and you can order free tickets here if you’d like to attend in person. Or you can watch at home and enjoy my patented live-tweeting.

Update: No surprise, Robitaille spokesman Mike Napolitano was in a good mood when I called him to ask about the new Rasmussen survey.

“We think it’s great,” Napolitano said. “We’re three points behind Caprio and it’s 6% undecided. And with all the money they’ve spent – especially all the money Caprio’s spent – he’s actually gone down. So obviously John’s positive message is resonating with voters.”

“This is an extremely close race,” he added. No argument there from me.

Update #2: The Block campaign will be glad to see its candidate above the 5% threshold required for the Moderate Party to stay on the ballot going forward.

• Lincoln Chafee: 33%
• Frank Caprio: 30%
• John Robitaille: 22%
• Ken Block: 4%
• undecided: 10%

This is the fifth poll done in the last five weeks. For an overview of how things look across the various surveys, check out this post I did yesterday.

(h/t: Ian Donnis)

Except in Democrat Frank Caprio’s case – he consistently wins about a third of voters – these polls are all over the map, with a 10-point spread between the highest and lower results for both independent Lincoln Chafee and John Robitaille, the Republican.

And when it comes to undecided voters, the divergence is even starker – Brown found a whopping 30% of voters haven’t mind up their minds, whereas Rasmussen said just 9% haven’t.

Anything’s possible, but it’s hard to believe the share of undecided voters more than tripled in the week and a half between those two surveys. Digging in a little deeper, one factor I see is that in both Rasmussen’s and our own WPRI/Fleming poll, more effort was made to probe whether self-described undecideds actually had a preferred candidate.

Marion Orr

Marion Orr, who oversees the Brown poll, told me most of the calls for his poll were made by Brown students trained and paid for their work, although sometimes he supplements them with outsiders. Orr also said they are specifically dissuaded from probing voters further.

“They’re trained not to sway the respondents,” he told me. “If they say they’re undecided, that’s what we put them down for.”

Brown’s methodology often leads to a high undecided figure – the Taubman Center had 19% of Rhode Islanders undecided between Obama and McCain two months before the last presidential election [pdf].

The problem there is that winding up with such a large share of undecided voters can limit what the poll tells us. It’s fine if those voters are truly undecided – but as the other poll results showed, it’s possible that further questioning could find a large number of them leaning one way or another, which is what we really want to know. Indeed, Victor Profughi, who did the controversial WJAR/Quest poll, told me last week he regretted not doing more to see whether undecided voters were actually leaning one way or another.

Another question is, who are we polling?

Brown surveyed 565 registered voters, while the other three polls all talked with likely voters, defined different ways. Although Rhode Island has around 700,000 registered voters, only about half of them are expected to show up at the polls next month – and what we really want to know is which way the half that votes is leaning. That’s why Joe Fleming limits our WPRI polls to likely voters as we get close to an election.

For the record, Orr said he did screen his respondents to see which ones were likely to vote, but he wound up deciding to release the results for registered voters instead. “We wanted to include a broader sample,” he said.

“People are still making up their minds,” Orr added. “It’s still a close race, in the sense that there are so many people who are undecided.” About half of those undecided voters uncovered by the Brown poll described themselves as independents, he noted. “I suspect these last few weeks will be decisive.”

Brown University’s Taubman Center just released a new poll of 565 registered voters in Rhode Island. Survey conducted Sept. 27-29; MoE plus or minus 4.1 percent. Here are some headlines:

• Caprio: 30%
• Chafee: 23%
• Robitaille: 14%
• Block: 2%
• undecided: 30%

First impression – that’s an astonishingly high number of undecided voters, and this poll’s results are closer to the infamous Profughi survey than ours or Rasmussen’s. This shows Caprio pulling away from Chafee compared with Brown’s last poll in August, which had Caprio at 28% and Chafee at 27%, a statistical tie.

Update #1: I just got off the phone with Joe Fleming, our Eyewitness News political analyst. He’s too much of a gentleman to critique his fellow pollsters’ work, but overall he said his take on the state of the campaign has not changed since last week. “I still think the governor’s race is too close to call,” he said. Brown is “showing a 7-point margin, but they’re also showing 30% undecided, which makes it really difficult to say what’s happening.”

In the 1st Congressional District, Brown polled 289 respondents, giving this part of the survey a margin of error of plus or minus 6%. Results:

• Cicilline: 39%
• Loughlin: 21%
• Raposa: 6%
• undecided: 31%

Other races:

• Lieutenant Governor: Roberts 36%, Healey 23%, Venturini 7%, undecided 34%
• Secretary of State: Mollis 39%, Taylor 28%, undecided 33%
• AG: Kilmartin 26%, Wallin 14%, McKenna 10%, Little 7%, Rainville 2%, undecided 41%
• Treasurer: Raimondo 38%, King 20%, undecided 42%

In the 2nd Congressional District, Brown polled 276 voters, so there’s an MoE of plus or minus 6.1%. They have Langevin at 47%, Zaccaria at 13%, and undecideds at 34%.

The survey of 500 likely voters by Fleming & Associates was conducted Sept. 22-26. The margin of error is 4.38%. Here are some favorable/unfavorable numbers:

• Barack Obama: 45%/54%
• Sheldon Whitehouse: 41%/53%
• Jack Reed: 56%/40%
• James Langevin: 46%/41%

And that wraps up our poll results. Click here for all our poll coverage, and here for complete results with crosstabs.

• Cicilline: 48%
• Loughlin: 29%
• Undecided: 22%

Much more, including the candidates’ reactions, in our complete story on WPRI.com.

You can also read our results for the governor’s race and how they compare with other polling, details on how the poll was done and voters’ opinions on 38 Studios, Deepwater Wind and pension reform.

Next up Thursday at 10 and 11 p.m., find out how Rhode Islanders feel about President Obama and U.S. Sens. Jack Reed and Sheldon Whitehouse.

Of the three, the most controversial proved to be the WJAR/Quest poll done by retired RIC professor Victor Profughi, which gave Democrat Frank Caprio a huge 12-point lead over independent Lincoln Chafee. By contrast, the two men were separated by just three points in both Rasmussen’s and our poll – well within the margin of error. (In fact, the Rasmussen and WPRI polls both had the two at 33%-30%, with Chafee ahead in theirs and Caprio on top in ours.)

Here’s a comparison of how Caprio, Chafee and Republican John Robitaille fared in the three polls, along with the percentage of undecided voters:

As Profughi pointed out to me in an e-mail, all three polls tell the same story about Frank Caprio’s support being in the 30%-35% range. But there is a nine-point spread between Profughi’s and Rasmussen’s results for Chafee, 10 points for Robitaille, and a whopping 14 points for the share of voters undecided.

Our WPRI poll by Joe Fleming is much closer to Rasmussen’s results, and campaign aides told us it largely matched their internal surveys. One notable difference in the samples: Profughi’s was only 12% Republicans, compared with 17% in ours, and 50% independents, versus 39% in ours. (All this is a reminder of why the way a poll is conducted makes such a difference.)

In retrospect, Profughi told me he should have pushed harder to see if self-identified undecided voters were actually leaning toward one candidate or another. “[W]e didn’t do nearly enough to break those who told us they were undecided first time out,” he said.

The Profughi poll drew head-scratches from the campaigns and the pundits, with Chafee’s campaign naturally leading the way in questioning his findings.

Chafee spokesman Mike Trainor called the results “highly suspect” in light of the Rasmussen survey, and pointed out that a poll Profughi did shortly before the 2006 Republican U.S. Senate primary gave Cranston Mayor Steve Laffey a huge 51%-34% lead over Chafee. Two weeks later, Chafee defeated Laffey 54%-46%. (Primary electorates are notoriously hard to poll, and Profughi himself called the Laffey-Chafee survey “an embarrassment” and “a whopper.”)

Trainor also pointed to Profughi’s prediction earlier this month about the Democratic primary for mayor of Providence: “I still think Taveras or Lombardi will be the winner, but l’m not as sure who is ahead of whom.” Taveras beat Lombardi 49%-29%. (“I never said Lombardi would win the Providence primary,” Profughi later wrote on Projo.com.)

To his credit, Profughi has been willing to engage with the criticism on WPRO, Projo.com and Rhode Island’s Future. He said he polled 496 “likely voters” (as opposed to just registered voters) by telephone, selected randomly from official voter lists and screened by asking whether they planned to vote in November.

Polls can have a big impact on political races, especially when they go against the conventional wisdom. But after sifting through this month’s polling data, my take is the same as Joe Fleming’s – this contest is still a tight race between Caprio and Chafee, each with around 30%-35% support, just as it has been for months.

Rasmussen has taken seven polls since February, and graphing the results shows just how little has changed over the last nine months (and how off-trend the 23% support for Chafee found by Profughi was):

Here at WPRI, we’re planning to do another poll closer to Election Day, and I assume Rasmussen will continue to track the race. I’m not sure what others will do. But many questions remain with less than five weeks to go: Who are those undecided voters, and what are they waiting to hear? What issues and messages will resonate in these final weeks? Has either Chafee or Caprio maxed out his support? Stay tuned.

• Frank Caprio (D): 33%
• Lincoln Chafee (I): 30%
• John Robitaille (R): 19%
• Undecided: 15%
• Ken Block (M): 4%

Much more, including who’s winning independents and how Rhode Islanders feel about the state’s direction, over in our complete story on WPRI.com. You can also read details on how the poll was done and voters’ opinions on pension reform.

Next up at 10 on Fox and 11 on WPRI, find out how Rhode Islanders feel about the 38 Studios and Deepwater Wind deals.

Tim White and Joe Fleming talk polling

Tomorrow is a big day around here, as we release the findings from our third Eyewitness News poll of the year. We asked Rhode Islanders what they think about every hot topic – the governor’s race, Cicilline vs. Loughlin, President Obama’s job performance, the 38 Studios and Deepwater Wind deals, the Bush tax cuts, and more.

Tim White and I have been digging through the findings with our pollster, Eyewitness News political analyst Joe Fleming, and although I can’t put out any numbers yet – under threat of death from the powerful Jay Howell – take it from me that this is one meaty poll, with a host of interesting findings.

I’ll have a preview with the results of one question tomorrow morning, and then Tim will have the results for statewide races and issues in the evening at 6 p.m. and 11 p.m., with federal races and topics following Thursday at 6 and 11. (I have my eye on tomorrow at 11, when we’ll find out how voters feel about the 38 Studios deal.)

In the meantime, here’s some background on how a survey like this gets done.

Joe Fleming is an old hand at this – he’s been conducting polls for a quarter-century. For this poll, Fleming & Associates contacted 500 likely voters registered in Rhode Island. Their phone numbers were generated randomly by a computer.

But the group has to be representative of the broader electorate to be valid, meaning it has to have the right proportions of men to women, younger voters to older ones, Democrats to Republicans to independents, etc. That’s accomplished through what’s known as “weighting” – calling and calling until you have spoken to enough young people, enough independents, enough women.

Weighting can make or break a poll, Joe emphasized to Tim and me. If you think about it, the only reason we do surveys at all is to get a sense of what people are thinking – and if the poll isn’t an accurate snapshot of the public, it won’t be an accurate snapshot of public opinion.

In addition, for this poll we wanted to speak to “likely voters,” as opposed to registered voters, so we only asked questions of people who said there was more than 50-50 chance they will cast a vote in the November election. That poses another challenge in putting together a proper sample. Plus, sometimes a call turns up a disconnected phone line or an answering machine.

How labor intensive is it to get the weighting right? I think this statistic says it all: Fleming’s team had to call nearly 8,000 people to get the final sample of 500 voters right. That’s an average of 16 calls to come up with one poll respondent – repeated 500 times.

One question Tim had was about cell phones, considering that a growing number of households, particularly younger ones, are dropping landline phone service. Joe said statistical studies show that any impact there is small, and controlling for it is part of the reason his team makes so many calls, to ensure an accurate sample.

The poll was conducted from last Wednesday, Sept. 22, through Sunday night, Sept. 26. Here’s how our 500 poll respondents break down:

• Male: 47%
• Female: 53%

• Congressional District 1: 50%
• Congressional District 2: 50%

• Ages 18-39: 23%
• Ages 40-59: 43%
• Ages 60+: 33%

• Union household: 21%
• Non-union household: 78%

• Democrats: 42%
• Republicans: 17%
• Independents: 39%

And if you want to get up to speed on what we found in our earlier polls this year, check out January’s results and May’s results.