Poll Reading 101

[NYcarbineer]

This is also why when it comes to things like approval rating and voter identification, Rasmussen's numbers will show more favorable data in both categories for Republicans than Gallup's will. Rasmussen's data is based on LV while Gallup's is based on RV.

Now does this finally clear it all up for everyone?

So you admit that Rasmussen intentionally uses a peculiar method that he knows will skew the numbers in favor of Republicans.

That is pure bias by definition.

Good God, talk about completely missing the point and twisting the argument. LV is hardly "peculiar". Go read post #68 again, and this time take off your blue glasses.

Likely voters is certainly a peculiar method to use to take a poll that is not an election poll.

 

[NYcarbineer]

So we're talking about party identification, you claim that Rasmussen is more accurate, then suddenly when you're asked to actually substantiate,

then we weren't talking about party identification?

lol

Sweet Jesus. Let me slow this down to accommodate the logically challenged. While there is no way to prove conclusively what the true breakdown of party identification is in the nation, it's logical to conclude that since Rasmussen's data is weighted according to their party identification data (and don't even try...that's common procedure. Gallup does that too and you never hear any whining about them), and since Rasmussen's data in general elections has been notoriously accurate, that their party identification data must be reasonably accurate as well. Do I need to connect the dots between taking a shit and wiping your ass for you too?

Explain it.

 

[BluePhantom]

Since Rasmussen's polls are producing outlying results, then you have to assume that either Rasmussen is wrong,

or the sum total of every other pollster is wrong.

Which is the more logical conclusion?

Ahhhhh but they are not necessarily producing outlying results. There have been five polls taken since Santorum dropped out of the race. Anything before that is irrelevant because with that event the entire political landscape changed and with it the opinion of the voters will change as well. Of those five three are media polls which are notoriously inaccurate. Romney leads in one of them. The two remaining polls (Rasmussen and Gallup) both show Romney ahead by similar margins. Taken as a whole, the outlier would be the CNN poll released today.

RealClearPolitics - Election 2012 - General Election: Romney vs. Obama

 

[BluePhantom]

So we're talking about party identification, you claim that Rasmussen is more accurate, then suddenly when you're asked to actually substantiate,

then we weren't talking about party identification?

lol

Sweet Jesus. Let me slow this down to accommodate the logically challenged. While there is no way to prove conclusively what the true breakdown of party identification is in the nation, it's logical to conclude that since Rasmussen's data is weighted according to their party identification data (and don't even try...that's common procedure. Gallup does that too and you never hear any whining about them), and since Rasmussen's data in general elections has been notoriously accurate, that their party identification data must be reasonably accurate as well. Do I need to connect the dots between taking a shit and wiping your ass for you too?

Explain it.

Try giving me the link to the story so I can look at their data.

 

[BluePhantom]

So you admit that Rasmussen intentionally uses a peculiar method that he knows will skew the numbers in favor of Republicans.

That is pure bias by definition.

Good God, talk about completely missing the point and twisting the argument. LV is hardly "peculiar". Go read post #68 again, and this time take off your blue glasses.

Likely voters is certainly a peculiar method to use to take a poll that is not an election poll.

You are seriously this thick aren't you? If you are gong to weight your election polls on a partisan index you are going to have to use the same method for each data set you collect. You can't weight an LV poll using RV data.

 

[California Girl]

Sweet Jesus. Let me slow this down to accommodate the logically challenged. While there is no way to prove conclusively what the true breakdown of party identification is in the nation, it's logical to conclude that since Rasmussen's data is weighted according to their party identification data (and don't even try...that's common procedure. Gallup does that too and you never hear any whining about them), and since Rasmussen's data in general elections has been notoriously accurate, that their party identification data must be reasonably accurate as well. Do I need to connect the dots between taking a shit and wiping your ass for you too?

Explain it.

Try giving me the link to the story so I can look at their data.

Now you get why you're talking to a wall, right? Take a graph, without context, and tell someone 'explain that'. It's nothing short of moronic... but that's gonna go waaaay over his head.

Link is:

http://www.mysterypollster.com/photos/uncategorized/rasmussencorrected_2.jpg

 

[francoHFW]

Rasmussen suqs. They were close only on the last poll in 2008, after months of propaganda. Like now.

 

[NYcarbineer]

Good God, talk about completely missing the point and twisting the argument. LV is hardly "peculiar". Go read post #68 again, and this time take off your blue glasses.

Likely voters is certainly a peculiar method to use to take a poll that is not an election poll.

You are seriously this thick aren't you? If you are gong to weight your election polls on a partisan index you are going to have to use the same method for each data set you collect. You can't weight an LV poll using RV data.

An presidential approval poll is a measure of the American people's opinion on the JOB the president is doing;

likely voters are a subset of the American people. A subset that skews conservatiive/Republican, so,

if you wanted to take an approval poll that made it appear that the American people were less approving of a Democratic president and more approving of a GOP president,

of course you could use likely voters.

 

[NYcarbineer]

Rasmussen suqs. They were close only on the last poll in 2008, after months of propaganda. Like now.

Rasmussen had GW Bush beating Gore by 9 points.

 

[NYcarbineer]

So we're talking about party identification, you claim that Rasmussen is more accurate, then suddenly when you're asked to actually substantiate,

then we weren't talking about party identification?

lol

Sweet Jesus. Let me slow this down to accommodate the logically challenged. While there is no way to prove conclusively what the true breakdown of party identification is in the nation, it's logical to conclude that since Rasmussen's data is weighted according to their party identification data (and don't even try...that's common procedure. Gallup does that too and you never hear any whining about them), and since Rasmussen's data in general elections has been notoriously accurate, that their party identification data must be reasonably accurate as well. Do I need to connect the dots between taking a shit and wiping your ass for you too?

I've already proven via the Silver research I posted that Rasmussen has absolutely zero claim to any particular talent for accuracy in general elections.

 

[NYcarbineer]

Sweet Jesus. Let me slow this down to accommodate the logically challenged. While there is no way to prove conclusively what the true breakdown of party identification is in the nation, it's logical to conclude that since Rasmussen's data is weighted according to their party identification data (and don't even try...that's common procedure. Gallup does that too and you never hear any whining about them), and since Rasmussen's data in general elections has been notoriously accurate, that their party identification data must be reasonably accurate as well. Do I need to connect the dots between taking a shit and wiping your ass for you too?

Explain it.

Try giving me the link to the story so I can look at their data.

The data is on the chart. Question is, why you need anything more? You're the poll expert, are you unaware of Rasmussen's years of giving Bush above average approval numbers.

I want you to explain why when a REPUBLICAN was president, Rasmussen polls gave him better than average approval, BUT,

when a Democrat became president,

IMMEDIATELY the Rasmussen polls began to produce lower than average approval numbers.

1. Are we in agreement that the only reasonable explanation is that Rasmussen has pro-GOP bias?

2. If we are in agreeement on one, doesn't that categorically eliminate Rasmussen for any consideration as an 'accurate' poll?

Or are pro-GOP bias and accuracy not incompatible in your world?

 

[NYcarbineer]

As the general election heats up between Romney and Obama I am seeing a lot of posts pointing to this poll and that poll and I am noticing an equal amount of misunderstanding from all sides. As I am an admitted "poll geek" (to the point that I have a spreadsheet I wrote to analyze polling data - I know "get a life") I want to take some time to explain how to read polls and get the most from the information they offer. While I imagine there are threads on this topic from 2008 or 2010 it appears it's time for a refresher course at the very least.

Rule #1: Consider the Sample

You will generally see polls sampled in three ways. The first is "adults" (A). Polls that sample "adults" is the least reliable because only about 50%-55% of the eligible population actually turn out to vote. Polls of A might give you an idea of public perception but they don't tell you a lot about who is in the best position to win an election.

The second (and most common) is "registered voters" (RV). This is better than A polls because they disregard anyone who is not eligible and in a position to vote. Still they are not the best because only about 70% of registered voters actually go and cast a ballot. So it's better, but still slightly problematic. Quinnipiac and Gallup are examples of firms that use RV sampling.

The third (and best) is "likely voters" (LV). This considers only people who are registered to vote and meet a statistical criteria that indicates they actually will go vote. LV polls, with only a few rare exceptions (like Quinnipiac, for example) are the ones to pay the most attention to. Rasmussen and SurveyUSA are examples of firms that use a LV sampling method.

Rule #2. Understand Margin of Error

I see people all the time get so excited about a poll that shows their candidate up by 3%. In reality, from a statistical perspective that's a tie. Every poll will have a slightly different margin of error but a good rule of thumb is 4%. If a poll shows a lead of 4% or less, it's a statistical tie and could go either way.

Rule #3. Pay Attention to Timing

A poll in April about an election in November doesn't mean a whole lot. Too much can happen. The economy could dramatically recover or totally tank between those times. A scandal may break. We could get attacked and forced into a military confrontation. A candidate may get a temporary bounce from their party's convention, the selection of a running mate, or even a human interest story that captures the nation's attention. All of these things will influence the polls and voter preference. The closer to the election, the more valuable a poll becomes. This is why we experience the "October Surprise" (the dirty secret that a candidate exposes about their opponent a week or two before the election). Knowing what is happening and when can help you identify the difference between a trend that is likely to stick and a temporary bounce.

Rule #4. Know the Polling Agencies Affiliations and History

Any agency can luck out in a given year. It's important to know which firms show a history of accuracy over multiple election cycles. For example, the Washington Post was great on a few selected state polls in 2010. In 2008 however they were absolutely dreadful. Gallup has a great reputation but over the last several years they have been getting less and less accurate. Rasmussen had a surprisingly weak 2010 but in 2008 and for years prior they were absolutely deadly accurate. What changes? Sometimes their methodology, sometimes nothing....they had a bad year or a good year.

Also keep in mind that some firms are affiliated with a given party. Public Polling Policy (PPP), for example, is funded and affiliated exclusively with the DNC. Magellan Strategies, the RNC. Usually, on RealClearPolitics, thoss agencies are noted (D) or (R) for Democratic affiliated firms or Republican affiliated firms respectively. It's wise to keep in mind who is paying their bills when you consider the validity of their data. That's not to say these firms should be completely disregarded...just that it should be kept in mind.

Rule #5. READ THE FUCKING CROSSTABS

The crosstabs are information about the specifics of the polling demographics in that sample. They are usually at the very beginning or the very end of a polling report. Many liberals might be excited as hell with a poll that shows Obama with an 11% lead until they look more closely and notice that (simply by sheer chance) the polling agency reached a sample where 47% of them identified as Democrats compared to only 23% that identified themselves as Republicans. This creates what is known as the dreaded "outlier". Simply by sheer random chance the agency reached a given demographic that is out of proportion with the United States as a whole and it skewed the results to the point where the data is unreliable.

Rule #6. Trends and Averages are More Important Than Snapshots

A poll is basically a snap shot: "at this precise moment in time and according to the sample we reached, this is what the feeling is". The best way to read polls is to look at a collection of reliable polls and average the results. RealClearPolitics does this with the "RCP average" but that average does not consider all the points I have discussed. If it's a recent poll it gets counted whether it's a good poll or a bad poll.

Tracking the trends associated with the averages shows more than just what the snapshot is but where there is momentum toward one side or the other. It's the trends that matter more when election day is distant. Those snapshots only have real relevance a week or so away from election day because things can happen so fast that even a historically accurate poll can show a dramatic change in their data within a very short period of time depending on what happens to be going on at one point in time compared to the other.

So with all that said let me list in order the common agencies that, through my research and tracking on my spreadsheet, are the most valuable and the most accurate.

The Deadly Accurate Duo (First Tier)
1. SurveyUSA
2. Quinnipiac

Damned Accurate (Second Tier)
3. Rasmussen (slipped from First Tier after a shaky 2010)

Pay Close Attention To (Third Tier)
4. Mason-Dixon
5. PPP

Worth Consideration (Fourth Tier)
6. Gallup
7. Magellan Strategies
8. Strategic Vision

Consider With Care
9. ABC/Washington Post (one good year in a history of disaster does not establish confidence)
10. Fox News (historically getting more and more accurate but not there quite yet)

Best to Ignore
Pretty much everything else

By keeping these above points in mind a true "student of the polls" will be able to get a much more solid understanding of who is winning and losing, how they are winning, why they are winning, and will be able to distinguish between what is important and what is irrelevant. The ability to effectively analyze the polling data can also mean the difference between making a strong argument on a thread or being exposed as a complete tool. These concepts are vital to understand whether you are simply looking for ammo in a debate or you really want a true understanding of the political landscape and your candidate's chances for victory.

Having just bothered to re-read this carefully, I notice that you don't actually provide any DATA to support your rankings of the Pollsters.

 

[Toro]

Excellent thread BluePhantom. I appreciate you going to all the time and effort explaining the mechanics of polling.

 

[NYcarbineer]

Explain it.

Try giving me the link to the story so I can look at their data.

Now you get why you're talking to a wall, right? Take a graph, without context, and tell someone 'explain that'. It's nothing short of moronic... but that's gonna go waaaay over his head.

Link is:

http://www.mysterypollster.com/photos/uncategorized/rasmussencorrected_2.jpg

I'm just curious. Why didn't you ask OP for links or evidence to support the claims he made in his first post?

 

[NYcarbineer]

Apparently, not.

You're gonna need to dumb it down for the slow kids.

I guess so. I mean good Christ, my 18 year old daughter understands this perfectly. I don't see why it's so difficult for NYC

Except let's be honest here. He understands perfectly. He is just engaging in typical debater tactics in an attempt to discredit Rasmussen because he has the typical liberal hard on about them.

In reference to your lapse into namecalling in this thread, once it was clear you were losing the argument...

California Girl has a message for you:

Click here

 

[BluePhantom]

Likely voters is certainly a peculiar method to use to take a poll that is not an election poll.

You are seriously this thick aren't you? If you are gong to weight your election polls on a partisan index you are going to have to use the same method for each data set you collect. You can't weight an LV poll using RV data.

An presidential approval poll is a measure of the American people's opinion on the JOB the president is doing;

likely voters are a subset of the American people. A subset that skews conservatiive/Republican, so,

if you wanted to take an approval poll that made it appear that the American people were less approving of a Democratic president and more approving of a GOP president,

of course you could use likely voters.

Dude.....my God this isn't really that difficult. By around mid-September ALL agencies will switch to a LV model. Most don't do it all year long because LV polls are more expensive than RV polls. But by mid to late September everyone will go to LV models because they are more accurate. Don't believe me? Fine. Look here and see how many LV polls there are vs RV polls. Now look here. Notice anything interesting? Yeah they are all LV polls. Go scroll down the list and you will find that they transitioned in September and with only two exceptions, by October they were all doing LV. At that point the spread between Rasmussen and SurveryUSA's data suddenly began to match the data by everyone else. Why? Because at that point they reverted to Rasmussen and SUSA's methods. The only fucking difference is that Rasmussen and SUSA use the same method no matter how far away the election is.

I mean my GOD....Stimpy you eeediot.

 

[BluePhantom]

Having just bothered to re-read this carefully, I notice that you don't actually provide any DATA to support your rankings of the Pollsters.

Maybe I am resorting to name calling because I simply can't believe how obtuse you are. I mean you are just bound and determined to discredit Rasmussen for whatever damned reason. Probably because you read an OpEd on the Daily Kos whining and crying about Rasmussen and just went with it like a mockingbird.

Now perhaps you missed the part where I said:

a) that data is based upon my personal polling spreadsheet. Sorry, I can't upload the entire damned spreadsheet onto the thread and breakdown all the mathematical formulas I used to determine who I trust and who I don't among every single one of them. Sorry can't do it.

b) don't focus on a single poll. Look at those with a history of accuracy and average them out. This means "don't take any single poll as gospel (that includes Rasmussen). Compare it to the other polls that you find to be reliable and average them out."

c) If you don't want to go by which polls I find most valuable....fine. Figure it out for yourself. Do your own damned research. Write your own damned spreadsheet and research the historical accuracy of them all yourself. I hope you have a lot of time on your hands 'cause it's gonna take a while.

What specific rank they hold between those I listed is somewhat irrelevant. It really doesn't matter whether you rank Rasmussen ahead of Gallup or below Gallup because by October they will both be saying pretty much the same thing and if you are averaging the results as I said to do it will make no difference whatsoever who the hell you personally rank 1st, 5th, or 10th.

Unfuckingbelievable

 

[BluePhantom]

The data is on the chart. Question is, why you need anything more?

Well the exact data set for the points on the scatter chart might be nice. How was the trend line calculated? Linear? Regression? Rolling? What fucking year are we talking about? Was it an election year? Is the data for Rasmussen their individual daily results or the results of their three day rolling average? You starting to get it now?

You're the poll expert, are you unaware of Rasmussen's years of giving Bush above average approval numbers.

I want you to explain why when a REPUBLICAN was president, Rasmussen polls gave him better than average approval, BUT,

when a Democrat became president,

IMMEDIATELY the Rasmussen polls began to produce lower than average approval numbers.

LV vs. RV is why for the 3rd or 4th damned time.

1. Are we in agreement that the only reasonable explanation is that Rasmussen has pro-GOP bias?

No.

2. If we are in agreeement on one, doesn't that categorically eliminate Rasmussen for any consideration as an 'accurate' poll?

We're not.

Or are pro-GOP bias and accuracy not incompatible in your world?

I think what is incompatible is your brain and statistical realities.

 

[NYcarbineer]

Having just bothered to re-read this carefully, I notice that you don't actually provide any DATA to support your rankings of the Pollsters.

Maybe I am resorting to name calling because I simply can't believe how obtuse you are. I mean you are just bound and determined to discredit Rasmussen for whatever damned reason. Probably because you read an OpEd on the Daily Kos whining and crying about Rasmussen and just went with it like a mockingbird.

Now perhaps you missed the part where I said:

a) that data is based upon my personal polling spreadsheet. Sorry, I can't upload the entire damned spreadsheet onto the thread and breakdown all the mathematical formulas I used to determine who I trust and who I don't among every single one of them. Sorry can't do it.

I didn't bring it up until you started bobbing and weaving and giving me shit because the chart I posted didn't have enough SUBSTANTIATION with it to satisfy you.

Well your original claims in your original post have NO SUBSTANTIATION accompanying them,
so why don't you just apply your own standards to your own posting?

 

[NYcarbineer]

You are seriously this thick aren't you? If you are gong to weight your election polls on a partisan index you are going to have to use the same method for each data set you collect. You can't weight an LV poll using RV data.

An presidential approval poll is a measure of the American people's opinion on the JOB the president is doing;

likely voters are a subset of the American people. A subset that skews conservatiive/Republican, so,

if you wanted to take an approval poll that made it appear that the American people were less approving of a Democratic president and more approving of a GOP president,

of course you could use likely voters.

Dude.....my God this isn't really that difficult. By around mid-September ALL agencies will switch to a LV model. Most don't do it all year long because LV polls are more expensive than RV polls. But by mid to late September everyone will go to LV models because they are more accurate. Don't believe me? Fine. Look here and see how many LV polls there are vs RV polls. Now look here. Notice anything interesting? Yeah they are all LV polls. Go scroll down the list and you will find that they transitioned in September and with only two exceptions, by October they were all doing LV. At that point the spread between Rasmussen and SurveryUSA's data suddenly began to match the data by everyone else. Why? Because at that point they reverted to Rasmussen and SUSA's methods. The only fucking difference is that Rasmussen and SUSA use the same method no matter how far away the election is.

I mean my GOD....Stimpy you eeediot.

A job approval poll is not an election poll. Why is that so difficult for you to understand?