Monmouth Poll: Clinton +4 in Ohio

[Seriously?]

The thing is Seriously?, 2012 exit polls and actual polls of likely/registered voters showed there to be more Democrats than Republican in Ohio. Why would Monmouth find there to be more Republicans?

They got a crap underlying sample here. That's my point. There was a lot of massaging to make this thing even workable. I am well aware that the exit poll numbers were in the D+7 or so range. They massaged this poll to D+4. The raw sample was R+4.

Did they massage this poll so that it ended up D+4, or did they do other demographic weights that happened to bring the sample to D+4?  There is a huge, huge methodological difference between those two things.  Obviously, neither is desirable, but with polling response rates what they are these days, demographic weighting is probably becoming more and more pronounced in polls.  That may make it more desirable than declining to re-weigh.

Monmouth claims they did other demographic weights to get there. They claimed they accounted for race, gender, age, region and "voter reg history."

One would think "voter reg history," would be taken into account in the LV screen.

The odd thing is that gender was perfect in the raw totals and didn't need a reweigh.
Race needed a 2-3 point adjustment, depending on what you consider the 10 folks that refused to be.
Age needed a 2-point adjustment to get out the oldies from the 50+ crowd.

The methodology did not discuss breakdown by region, so who knows what alterations needed to be made there.

I don't know how the math gets to the eight point shift there, unless they used some magic trick to take a lot of the crossover Ds to R in this cycle and put them back into the D category from 2012. I do know that there was a lot of interest on the GOP side in Ohio this primary cycle.

The difficulty for a lot of the pollsters in Ohio this season is the nature of their open primary system. There were quite a few Democrats that crossed over to vote for Kasich.

[Desroko]

The thing is Seriously?, 2012 exit polls and actual polls of likely/registered voters showed there to be more Democrats than Republican in Ohio. Why would Monmouth find there to be more Republicans?

They got a crap underlying sample here. That's my point. There was a lot of massaging to make this thing even workable. I am well aware that the exit poll numbers were in the D+7 or so range. They massaged this poll to D+4. The raw sample was R+4.

Did they massage this poll so that it ended up D+4, or did they do other demographic weights that happened to bring the sample to D+4?  There is a huge, huge methodological difference between those two things.  Obviously, neither is desirable, but with polling response rates what they are these days, demographic weighting is probably becoming more and more pronounced in polls.  That may make it more desirable than declining to re-weigh.

Demographic weighting is industry-standard, not undesirable. Even in the days of 25% response rates, (good) pollsters weighted because of differential turnout among RV subsamples, and unequal selection probabilities within households.

[Seriously?]

The thing is Seriously?, 2012 exit polls and actual polls of likely/registered voters showed there to be more Democrats than Republican in Ohio. Why would Monmouth find there to be more Republicans?

They got a crap underlying sample here. That's my point. There was a lot of massaging to make this thing even workable. I am well aware that the exit poll numbers were in the D+7 or so range. They massaged this poll to D+4. The raw sample was R+4.

Did they massage this poll so that it ended up D+4, or did they do other demographic weights that happened to bring the sample to D+4?  There is a huge, huge methodological difference between those two things.  Obviously, neither is desirable, but with polling response rates what they are these days, demographic weighting is probably becoming more and more pronounced in polls.  That may make it more desirable than declining to re-weigh.

Demographic weighting is industry-standard, not undesirable. Even in the days of 25% response rates, (good) pollsters weighted because of differential turnout among RV subsamples, and unequal selection probabilities within households.

I am well aware that it is industry standard, but when you get to this pronounced of a shift, it becomes a question whether the entire sample should be thrown out (aka the 1 of 20 polls that is unreliable as a matter of science). I don't think I've seen a poll that when accounting for demographics shifted the D/R/I by 8% before.

[heatcharger]

I am well aware that it is industry standard, but when you get to this pronounced of a shift, it becomes a question whether the entire sample should be thrown out (aka the 1 of 20 polls that is unreliable as a matter of science). I don't think I've seen a poll that when accounting for demographics shifted the D/R/I by 8% before.

What people like you don't understand is: PARTY ID DOESN'T MATTER THAT MUCH.

Party ID is merely a state of mind question, not a concrete demographic. Party registration is, but that's rarely asked in polls.

Didn't you learn anything from 2012? Unskewing by Party ID has never made any sense.

[Erich Maria Remarque]

I am well aware that it is industry standard, but when you get to this pronounced of a shift, it becomes a question whether the entire sample should be thrown out (aka the 1 of 20 polls that is unreliable as a matter of science). I don't think I've seen a poll that when accounting for demographics shifted the D/R/I by 8% before.

What people like you don't understand is: PARTY ID DOESN'T MATTER THAT MUCH.

Party ID is merely a state of mind question, not a concrete demographic. Party registration is, but that's rarely asked in polls.

Didn't you learn anything from 2012? Unskewing by Party ID has never made any sense.

Achtung! It is not what he is talking about.

But this poll is pretty much in line with other polls. Relatively small sample size might skew crosstabs, why they probably had to reweigh it that much.

[Desroko]

I am well aware that it is industry standard, but when you get to this pronounced of a shift, it becomes a question whether the entire sample should be thrown out (aka the 1 of 20 polls that is unreliable as a matter of science). I don't think I've seen a poll that when accounting for demographics shifted the D/R/I by 8% before.

What people like you don't understand is: PARTY ID DOESN'T MATTER THAT MUCH.

Party ID is merely a state of mind question, not a concrete demographic. Party registration is, but that's rarely asked in polls.

Didn't you learn anything from 2012? Unskewing by Party ID has never made any sense.

Achtung! It is not what he is talking about.

But this poll is pretty much in line with other polls. Relatively small sample size might skew crosstabs, why they probably had to reweigh it that much.

He's complaining that a random sample is being weighted to resemble a representative sample. That's inane, and a good sign that he actually doesn't know what he's talking about. For a host of reasons, initial random samples are almost never representative of actual voting populations.

[Erich Maria Remarque]

I am well aware that it is industry standard, but when you get to this pronounced of a shift, it becomes a question whether the entire sample should be thrown out (aka the 1 of 20 polls that is unreliable as a matter of science). I don't think I've seen a poll that when accounting for demographics shifted the D/R/I by 8% before.

What people like you don't understand is: PARTY ID DOESN'T MATTER THAT MUCH.

Party ID is merely a state of mind question, not a concrete demographic. Party registration is, but that's rarely asked in polls.

Didn't you learn anything from 2012? Unskewing by Party ID has never made any sense.

Achtung! It is not what he is talking about.

But this poll is pretty much in line with other polls. Relatively small sample size might skew crosstabs, why they probably had to reweigh it that much.

He's complaining that a random sample is being weighted to resemble a representative sample. That's inane, and a good sign that he actually doesn't know what he's talking about. For a host of reasons, initial random samples are almost never representative of actual voting populations.

No, he's complaining about the size of this shift. It might indicate that sample is too skewed to be "restored", but since Monmouth is a A pollster, they know what they are doing.

I'd be desirable, if all pollsters were more transparent about how reweighting works, but since it is part of their success, they won't share

[Wells]

Their Senate poll had Portman up eight, so I don't see why anyone is complaining.

[Alcon]

The thing is Seriously?, 2012 exit polls and actual polls of likely/registered voters showed there to be more Democrats than Republican in Ohio. Why would Monmouth find there to be more Republicans?

They got a crap underlying sample here. That's my point. There was a lot of massaging to make this thing even workable. I am well aware that the exit poll numbers were in the D+7 or so range. They massaged this poll to D+4. The raw sample was R+4.

Did they massage this poll so that it ended up D+4, or did they do other demographic weights that happened to bring the sample to D+4?  There is a huge, huge methodological difference between those two things.  Obviously, neither is desirable, but with polling response rates what they are these days, demographic weighting is probably becoming more and more pronounced in polls.  That may make it more desirable than declining to re-weigh.

Demographic weighting is industry-standard, not undesirable. Even in the days of 25% response rates, (good) pollsters weighted because of differential turnout among RV subsamples, and unequal selection probabilities within households.

To be clear, I didn't mean to indicate weighting is a bad practice -- it's a necessary one.  I just meant polls would be even better if the phenomena that necessitate weighting didn't exist.  It's undesirable that poll respondents are so unrepresentative (and it's getting worse!). While weighting is the best solution to fixing that problem, it would be better if the problem didn't exist.

For instance, we can weigh up the sample of 18-to-24 year old white females, but that assumes that we're getting a representative sample of 18-to-24 year old white females, and whatever causes a low proportion of those to respond isn't also causing an unrepresentative sample of those to respond.  Weighting is the right thing to do in that case, but it can't fix every underlying problem.

edit: A more obvious example - weighting up the Hispanic respondent % will get you a misleading result if you don't give a poll in Spanish, because English-only interviews will result in an unrepresentative sample of Hispanics, and re-weighting on race alone won't fix that.

[Torie]

The thing is Seriously?, 2012 exit polls and actual polls of likely/registered voters showed there to be more Democrats than Republican in Ohio. Why would Monmouth find there to be more Republicans?

They got a crap underlying sample here. That's my point. There was a lot of massaging to make this thing even workable. I am well aware that the exit poll numbers were in the D+7 or so range. They massaged this poll to D+4. The raw sample was R+4.

Did they massage this poll so that it ended up D+4, or did they do other demographic weights that happened to bring the sample to D+4?  There is a huge, huge methodological difference between those two things.  Obviously, neither is desirable, but with polling response rates what they are these days, demographic weighting is probably becoming more and more pronounced in polls.  That may make it more desirable than declining to re-weigh.

Demographic weighting is industry-standard, not undesirable. Even in the days of 25% response rates, (good) pollsters weighted because of differential turnout among RV subsamples, and unequal selection probabilities within households.

To be clear, I didn't mean to indicate weighting is a bad practice -- it's a necessary one.  I just meant polls would be even better if the phenomena that necessitate weighting didn't exist.  It's undesirable that poll respondents are so unrepresentative, and while weighting is the best solution to fixing that problem, it would be better if the problem didn't exist.

For instance, we can weigh up the sample of 18-to-24 year old white females, but that assumes that we're getting a representative sample of 18-to-24 year old white females, and whatever causes a low proportion of those to respond isn't also causing an unrepresentative sample of those to respond.  (Weighting is the right thing to do in that case, but it can't fix every underlying problem.

edit: A more obvious example - weighting up the Hispanic respondent % will get you a misleading result if you don't give a poll in Spanish, because English-only interviews will result in an unrepresentative sample of Hispanics, and re-weighting on race alone won't fix that

Given all the problems with polling these days, it is amazing that the polls are as accurate as they are. This year will be a big test for them, since past election models might not be replicated in this election, and that is what in part is relied upon to do the weighting.

[Desroko]

The thing is Seriously?, 2012 exit polls and actual polls of likely/registered voters showed there to be more Democrats than Republican in Ohio. Why would Monmouth find there to be more Republicans?

They got a crap underlying sample here. That's my point. There was a lot of massaging to make this thing even workable. I am well aware that the exit poll numbers were in the D+7 or so range. They massaged this poll to D+4. The raw sample was R+4.

Did they massage this poll so that it ended up D+4, or did they do other demographic weights that happened to bring the sample to D+4?  There is a huge, huge methodological difference between those two things.  Obviously, neither is desirable, but with polling response rates what they are these days, demographic weighting is probably becoming more and more pronounced in polls.  That may make it more desirable than declining to re-weigh.

Demographic weighting is industry-standard, not undesirable. Even in the days of 25% response rates, (good) pollsters weighted because of differential turnout among RV subsamples, and unequal selection probabilities within households.

To be clear, I didn't mean to indicate weighting is a bad practice -- it's a necessary one.  I just meant polls would be even better if the phenomena that necessitate weighting didn't exist.  It's undesirable that poll respondents are so unrepresentative (and it's getting worse!). While weighting is the best solution to fixing that problem, it would be better if the problem didn't exist.

For instance, we can weigh up the sample of 18-to-24 year old white females, but that assumes that we're getting a representative sample of 18-to-24 year old white females, and whatever causes a low proportion of those to respond isn't also causing an unrepresentative sample of those to respond.  Weighting is the right thing to do in that case, but it can't fix every underlying problem.

edit: A more obvious example - weighting up the Hispanic respondent % will get you a misleading result if you don't give a poll in Spanish, because English-only interviews will result in an unrepresentative sample of Hispanics, and re-weighting on race alone won't fix that.

Okay, good reply.

[Alcon]

Seriously?, I think your post raises good questions, although I tend to defer to competent pollsters on matters like this.  I just have one thing to add:

One would think "voter reg history," would be taken into account in the LV screen.

Not necessarily.  Most likely voter screens entail asking questions about self-reported voting history, self-reported intention to vote, self-reported interest in the election, and sometimes, screening questions that determine if the voter has a plan to vote, e.g., knows when and where to do it.

The thing is, these self-reports are more likely to be accurate if they correspond to past behavior than if they don't.  At the end of the day, a 0/4 voter could express high intention to vote, high interest, and even high voting history ('cause people are big ol' liars).  A 4/4 voter could give the same information.  Which voter would really be likelier to vote?  Obviously the 4/4 voter, not the 0/4 voter.  So it makes sense to weigh down the 0/4 voter's response, just because we know that 0/4 voters who give the same answers as 4/4 voters are still less likely to vote.

Also keep in mind that meeting the LV screen does not mean all respondents score equally highly on it.  If the screen determines one voter has a 99% chance to vote, and another 75%, it makes sense to allow both through the LV screen.  But it also makes sense to weigh down the 75% person's response to reflect the fact that their "predicted vote" for their preferred candidate is 0.75 votes, as opposed to 0.99.

Make sense?

[Desroko]

Seriously?, I think your post raises good questions, although I tend to defer to competent pollsters on matters like this.  I just have one thing to add:

One would think "voter reg history," would be taken into account in the LV screen.

Not necessarily.  Most likely voter screens entail asking questions about self-reported voting history, self-reported intention to vote, self-reported interest in the election, and sometimes, screening questions that determine if the voter has a plan to vote, e.g., knows when and where to do it.

The thing is, these self-reports are more likely to be accurate if they correspond to past behavior than if they don't.  At the end of the day, a 0/4 voter could express high intention to vote, high interest, and even high voting history ('cause people are big ol' liars).  A 4/4 voter could give the same information.  Which voter would really be likelier to vote?  Obviously the 4/4 voter, not the 0/4 voter.  So it makes sense to weigh down the 0/4 voter's response, just because we know that 0/4 voters who give the same answers as 4/4 voters are still less likely to vote.

Also keep in mind that meeting the LV screen does not mean all respondents score equally highly on it.  If the screen determines one voter has a 99% chance to vote, and another 75%, it makes sense to allow both through the LV screen.  But it also makes sense to weigh down the 75% person's response to reflect the fact that their "predicted vote" for their preferred candidate is 0.75 votes, as opposed to 0.99.

Make sense?

There's also some confusion about terms here: Seriously appears to be referring to party ID and party registration interchangeably. They're not the same thing at all.

[Seriously?]

I am well aware that it is industry standard, but when you get to this pronounced of a shift, it becomes a question whether the entire sample should be thrown out (aka the 1 of 20 polls that is unreliable as a matter of science). I don't think I've seen a poll that when accounting for demographics shifted the D/R/I by 8% before.

What people like you don't understand is: PARTY ID DOESN'T MATTER THAT MUCH.

Party ID is merely a state of mind question, not a concrete demographic. Party registration is, but that's rarely asked in polls.

Didn't you learn anything from 2012? Unskewing by Party ID has never made any sense.

When you massage a poll that has a result of changing people's preferences by 8%, it does matter. Notice I am not attacking any other poll on this basis, just this one. It looks to me like it's a crap sample. When the rest of these Monmouth their reweighs, it ends up being off a few points, not this significant of a shift.

No one is unskewing a damn thing here. I am suggesting that this underlying sample may be the 1 in 20 that is not reliable. And honestly, a true read would probably be more favorable to Clinton if they got things right the first time.