JFern's "Statistics"

[J. J.]

On another thread, our old friend JFRAUD has raised statistal questions unreated to the topic.  Though he has, charateristically, declined to address the topics, and has declined to start a separate thread, despite repeated requests.  So, it falls to me to address them in the appropriate forum.

JFRAUD asked:

https://uselectionatlas.org/FORUM/index.php?topic=20462.195

You must be logged in to read this quote.

There are several problems.  First, if the sample group were the Kerry delegates to the Democratic National Convention, this would indicate that Kerry was in big trouble as he should win all of them.  The "expected value" here woulld be 1000 for Kerry and zero for Bush.  In that case, with the expected value being 1000 Kerry, there would be no statistical correlation.

The second problem is trying to tie these factors to another event.  Is it because the economy is perceived to be bad, the war in Iraq, voters don't trust Dick Cheney, or that the X-Files are not in first run any more?

The significance here is not how well this describes the population, but how far off the expected value is this number.

[J. J.]

Or if we want a less precise and more common sense wording, let's say a good polling firm like SUSA comes out with a poll with Kerry at 94% and Bush 6%.  Would that be a statistically significant lead by Kerry?

The lead itself would not be statically valid, as you would have to look at the poll itself.  You are equating the result with the validity of the poll. 

Let me put it this way, if I flicked a light switch 100 times (and after each test, checked the bulb to make sure that it worked), we would expect, if the switch controlled the bulb, to it work 100 time out of 100.  Likewise, I would expect the bulb not to light whan I did not flick the switch.  If the bulb goes on when don't flick the switch, or doesn't go on when I do flick and it does it enough times, I better stop thinking that the switch controls the light.

[J. J.]

Random forum poster: "Holy, sh**t look at this new SUSA poll showing Kerry up 94-6 nationwide!"

J.J: "Who cares, that's not a statistically signifcant lead."

No, but I might say, "That's Zogby."

In answer to your question, you would be looking at the results of the poll directly.  The statistics question is not what are results of the poll, but what is likelthood that the poll is wrong.  Even if the pollster do does everything right in poll construction, and impliments it perfectly, there is still a chance that a certain percentage that the poll itself is going to be statistically invalid. 

In other words, let's that this was a series of 100 polls, all conducted at the same time, and all with the same implimentation and construction.  Also assume that we know the actual result is 51% Bush, 49% Kerry.  Would we expect to get a really bad poll like this one as one of those 100?  Yes.

I think that happened during the 2004 campaign the day that the Vorlon changed his name to "The Shadows."

I think we can add a bit to one rule to Silent Hunter's list:

https://uselectionatlas.org/FORUM/index.php?topic=20676.msg442894#msg442894


"6. Remember a little thing called 'margin of error,' " and never trust just one poll.

[J. J.]

The thing is, even if the pollster does everything right, he's still going to get one absolutely wrong result out of the margin of error in X amount of polls.  Now, with a sample size of 1000, X will be lower than if the sample size is 300, but it's still going to happen.

[J. J.]

The thing is, even if the pollster does everything right, he's still going to get one absolutely wrong result out of the margin of error in X amount of polls.  Now, with a sample size of 1000, X will be lower than if the sample size is 300, but it's still going to happen.

Yeah, well he's never going to get 94-6 with a sample of 1000 when it was really a tie, and that's why 94-6 is a very statistically significant lead.

That you cannot say, statistically.

We are not referring to margin of error directly, but a problem that the poll will just be wrong.   When at a poll, statistically, it is accurate to say, this is the corect number, within the margin of error, X number of times out of 100.  X is usually 95 to 99.

[J. J.]

The thing is, even if the pollster does everything right, he's still going to get one absolutely wrong result out of the margin of error in X amount of polls.  Now, with a sample size of 1000, X will be lower than if the sample size is 300, but it's still going to happen.

Yeah, well he's never going to get 94-6 with a sample of 1000 when it was really a tie, and that's why 94-6 is a very statistically significant lead.

That you cannot say, statistically.

We are not referring to margin of error directly, but a problem that the poll will just be wrong.   When at a poll, statistically, it is accurate to say, this is the corect number, within the margin of error, X number of times out of 100.  X is usually 95 to 99.

With a 1000 sample poll, the margin of error is always less than 1.582%.
We have 96-4, which is a z-score of 27.8.

If you know anything about z-scores you'll realize there's no way you'll ever get that.

The problem is, you cannot say that the 94% is significant or not.  What the result is not going to determine if the poll itself is statistically significant. 

[J. J.]

The problem is, you cannot say that the 94% is significant or not.  What the result is not going to determine if the poll itself is statistically significant. 

The error on a sample of 1000 is a bit over 3%. That determines statistical significance. If you don't understand that, sign up for freshman statistics.

You seem to be talking about the margin of error within the sample size, the maxim percetage that the numbers within the poll will vary.  I'm addressing the possibility that the sample was outside the second or third standard deviation (95% and 99%, respectively).

[J. J.]

The problem is, you cannot say that the 94% is significant or not.  What the result is not going to determine if the poll itself is statistically significant. 

The error on a sample of 1000 is a bit over 3%. That determines statistical significance. If you don't understand that, sign up for freshman statistics.

You seem to be talking about the margin of error within the sample size, the maxim percetage that the numbers within the poll will vary.  I'm addressing the possibility that the sample was outside the second or third standard deviation (95% and 99%, respectively).

You're hopelessly confused. Time for you to read some Statistics 101 like this:
http://www.measuringusability.com/sample_old.htm

Of course, knowing you, you'll miss the point, again.

Here is a link from the site you posted:

http://www.surveysystem.com/sscalc.htm

Assuming 120,000,000 million voters, you could get a result within 3% of the actual amount, 95% of the time, with a sample size of 1067.  To illustrate the difference, to get a result within 1% of the actual amount, 99% of the time, you would need a sample size of 16639.

Here is the actual explanation from the site:

You must be logged in to read this quote.

That's pretty much what I've been talking about and what Tedrick has been talking about.  It's from the link on the site that you quoted.  Why can't you understand it?

[J. J.]

Yep, I had a good feeling that you'd miss the point.

If we have a sample of 1000, the 95% confidence interval is around +-3%. That means if Kerry has a lead of 6 or fewer points, it's not a statistically significant lead. If Kerry has a lead of 88 points (94-6), then it's quite statistically significant.

I know a lot more statistics than you, you are a fraud for blaming your lack of knowledge of statistics on my supposedly being wrong.

JFRAUD,  I assigned the confidence interval of 3%, the confidence level has nothing to do with it.  You can set both.  I can set the confidence interval at 0.1%, which requires a sample size 952775.

Even with tha virtually No margin of error (0.1%) and that sample size, the confidence level would still be 95%.  In other words, if I took 20 polls with a sample size of 952775, it is probable that at least one would not show the "actual" results within 0.1%

Likewise, I could be looking for numbers within +/-10% of the actual number and only poll 96 people, 20 different times.  The would still be the probability that one poll in those 20 wouldn't match the actual results. 

The response does affect the confidence interval, but not the confidence level.

[J. J.]

Yep, I had a good feeling that you'd miss the point.

If we have a sample of 1000, the 95% confidence interval is around +-3%. That means if Kerry has a lead of 6 or fewer points, it's not a statistically significant lead. If Kerry has a lead of 88 points (94-6), then it's quite statistically significant.

I know a lot more statistics than you, you are a fraud for blaming your lack of knowledge of statistics on my supposedly being wrong.

JFRAUD,  I assigned the confidence interval of 3%, the confidence level has nothing to do with it.  You can set both.  I can set the confidence interval at 0.1%, which requires a sample size 952775.

Even with tha virtually No margin of error (0.1%) and that sample size, the confidence level would still be 95%.  In other words, if I took 20 polls with a sample size of 952775, it is probable that at least one would not show the "actual" results within 0.1%

Likewise, I could be looking for numbers within +/-10% of the actual number and only poll 96 people, 20 different times.  The would still be the probability that one poll in those 20 wouldn't match the actual results. 

The response does affect the confidence interval, but not the confidence level.

Of course if it's really a dead heat, 1 in 20 polls, will, by definition, show a statistically significant different at the 95% confidence level.  If you don't like that, then choose a widen confidence interval, like a 99.999999999% confidence interval, which still doesn't include Kerry leading Bush 94%-6%.

I can't believe you're still confused about this.

You seem to be confusing the sample confidence interval with the confidence level.  What ever the result, there is still the chance that it's wrong; from a statistical standpoint, results that are below 95% are not statistically significant.

Let's say that there is another poll, conducted randomly with the same sample size at the same time.  Could that show Bush 94%, Kerry 6%?  Yes. 

One of two polls is obviously wrong, but it's wrong because of the nature of statistics.  The pollster randomly polled in a bad sample.  About one in twenty will be those bad samples; this probably accounts for some wide swings in the tracking polls.  When the sample passes through, the numbers drop back to where they were.  We really couldn't tell which of these polls.

What the poll result really says is that the poll, in 19 out of 20 cases, shows that the result is +/- 3 points of the reported result, if we poll 1067 people.  The problem is, we don't know it the 20th case or not.

That statement is true if the result 50/50 or 99/1.  What it does is change the confidence interval, known to most of us as the margin of error.  A 50/50 result of polling 1067 people would yield a MOE of +/- 3 points.  A 99/1 result of polling 1067 people would yield a MOE of +/- 0.6 points.  Both of those results would still be accurate 19 out of 20 times.

All that is does is change the MOE; it doesn't reflect on the possiblity that the sample size is the 20th case.

You don't seem to understand the difference between MOE and the accuracy of the poll.

BTW:  Any one interested in reading about it can go to the web site http://www.surveysystem.com/sscalc.htm  They can run the numbers themselves.

I'm more than happy to let anyone interested to read it and make their own judgment.

[J. J.]

Read a statistics book so you'll stop telling me I'm wrong when I right. If it's outside the 95% confidence interval, it's statistically significant at the p=5% level. In this case, it really doesn't matter what sort of confidence interval you choose, it's even outside of the 1 - 10^-200 confidence interval, so i't statistically significant at the p=10^-200 level.

If Kerry's support is really 50%, his polled support will be outside of that 95% confidence range range 1/20th of the time, and it'll be statistically significant at the 5% level. I'm not sure how many more times I have to say the same thing before you understand.

JFRAUD, I'll stop telling you that your wrong the decade that stop being wrong.  You are saying, in effect, that because the poll numbers show a certain thing, that means the poll is accurate. 

You are looking at one poll and assuming that the poll is one of the 19 that is correct, and your basing that on the numbers within that poll.  The results of the poll have no effect on if the sample was an "accurate" sample.  The results do effect MOE, but the only conclusion that can be reached is that Kerry is 95% likely to have support within the MOE.

Now that said, the MOE will be smaller as the support for one cadidate moves away from 50%, but that has nothing to do with if the 95% likelihood that the poll is correct.  For example, if 100 people were polled, we could say that we are 95% confident that Kerry has 94% +/- 4.65%.  Likewise, if 100,000 were polled we could say that we are 95% that Kerry has 94 +/- 0.47%.

If the numbers change the MOE changes.  Assume that Kerry has 40% of the vote, according to the poll.  If 100 people were polled we could say that we are 95% confident that Kerry has 40% +/- 9.6%.  If 100,000 were polled we could say that we are 95% confident that Kerry has 40% +/- 0.3%.

You'll note that in all cases the confidence level stays the same.  None of this affects the confidence level, only makes the MOE shrink or grow.

You are going to be able to determine the confidence level from the results of the single pole.  That is why your basic question illustrates your ignorence of the subject.  You cannot determine if this one of those randomly wrong polls from the internal numbers (though it will effect MOE).

[J. J.]

Damn, you're still calling me Jfraud? That's g pathetic.

At the 1-p confidence level, we have a false statistically significant difference at most p of the time. That's for a two sideded test, so if all we're testing is does Kerry have a statistically significant lead, it drops to p/2. Ok, now let p=5%. Yes, we get a false (statistically significant) positive at most 1 in 20 times.  Now, if you don't like that, fine, let p=10^-200. Kerry leading Bush 94-6 is still outside of that.

The MOE is sqrt(p*(1-p)/n), so the 100,000 MOE should be sqrt(1000) times smalelr than the 100 MOE, not 10. 



Let me repeat why I can be damn sure a 94%-6% poll is a statistically significant lead by Kerry. If it wasn't, the best Kerry could hope for was a 50-50 tie. The 1-10^-200 confidence interval for a 50-50 tied poll does not include Kerry beating Bush 94%-6%. Therefore, it's statistically significant even at the absurdly small level of p=10^-200.

Okay, first, I refer to you as JFRAUD because of "facts" you attempt to use in your posts, and I'm not the only one that has noticed that.

As to the question you asked:

https://uselectionatlas.org/FORUM/index.php?topic=20462.195

You must be logged in to read this quote.

You've asked here, "if there is a poll of 1000 random likely voters, if Kerry leads Bush with 94% of the vote to 6%, that means that Kerry has a statistically significant lead. "  The answer as you just admitted is, " Yes, we get a false (statistically significant) positive at most 1 in 20 times. "  We have no way, within that poll result, of determining it this a bad sample or not.  The only thing that can be legitimitely determined from this that we are, based on the poll results,  95% confident that Kerry is at 94% within the MOE.  If the result showed Kerry at 12%, all we could say is that we 95% confident that Kerry is at 12% within the MOE.  Neither of these results affect the confidence level; if you don't understand that, you don't have a solid grasp on how statistics work.  Why don't you ask one of your teachers.

Now if had two polls, possibly with different sample sizes, taken at the same time, we might be able  reach a conclusion, but we can not with only one poll.

You also move from straight statistical signifigance into probabilities and attempt to relate MOE to this.  Yes, MOE, the range where the 95% certainty score is, shrinks as you move away from 50%, but that has noeffect on the confidence level.  Whatever the result is, it will be a 95% confidence level.  A 50/50 split will have a different MOE, but will still be the same statistical significance.

I'm actually using the link to the site you posted; that is what that description says.

[J. J.]

JFraud, you are confusing validity of the poll, whether the poll is valid and the MOE.  You could poll one person and still make the statement that with 95% certainty that Kerry's result is 100% within the MOE.  The MOE in that case is 99%.  That was actuall SNL "Weekend Update" bit a few elections ago.  The result doesn't effect the confidence level.

You also are not looking at correlation between what causes the result and the result. 

Now, if you wish to ask if the number is outside the MOE, the answer is yes.

[J. J.]

JFraud, you are confusing validity of the poll, whether the poll is valid and the MOE.  You could poll one person and still make the statement that with 95% certainty that Kerry's result is 100% within the MOE.  The MOE in that case is 99%.  That was actuall SNL "Weekend Update" bit a few elections ago.  The result doesn't effect the confidence level.

You also are not looking at correlation between what causes the result and the result. 

Now, if you wish to ask if the number is outside the MOE, the answer is yes.

If I have a random sample of 1 person, then the normal approximation completely fails. I can't really say much. I couldn't even say that I'm 95% sure that Kerry has better than 20% support. I don't see any point in working out example what happens with a sample of 1 or 2, since you definitely can't claim a statistically significant lead based on samples that small.

Again, you try to confuse the situatiion. I made it crystal clear we're talking about samples of 1000, not 1.

I an not trying to confuse the situation.  You didn't raise the MOE point in your initial post.  The statement that, "You could poll one person and still make the statement that with 95% certainty that Kerry's result is 100% within the MOE," is a valid statement. 

Now, is there a relationship between MOE and poll results?  Yes.  Is there a relationship between confidence level and poll results?  No.  Do the results have anything to do with if the poll is statistically significant? No.

To take this to the other end, if we polled 10,000,000 voters , we could get an MOE of between 0.03 to 0.01.  The conclusion would still be that we are 95% confident that Kerry's vote is X +/- MOE, but we're still at the 95% confidence level.  The results of the poll do not effect that.

[J. J.]

Let's make this clear. Our null hypothesis is that Kerry and Bush are statistically tied, so we assume Kerry and Bush are both at 50%. Our confidence interval is 95% ( we could make it larger, if wanted).

For small samples, we have to use the binomial distribution. For samples of size 1-5, we can't conclude a statistically signifant difference, no matter with. If our sample is of size 6, we have a 1/64 chance that all 6 people support Kerry, and another 1/64 change that they all support Bush. The resuling 1/32 is less than our reject p=5%, so it would be statistically significant in that case.

For large samples, we get a standard error or deviation of sqrt(p(1-p)/n) = 0.5/sqrt(n). The radius 95% confidence interval is 1.96 standard deviations, or 0.98/sqrt(n). So basically, we have a statistically significant different if we're outside of
[50% - 1/sqrt(n), 50% + 1/sqrt(n)].  For n=1000, we get about
[46.9%, 53.1%].

The null hypothesis is not a 50/50 split; that is where you are making a mistake. 

You asked a question about this would be statistically signifigant.  The numbers that poll genenerates will always be with 95% confidence, each candidates numbers are within the MOE of the result.  If you are asking if the 95% is outside of the MOE (or "confidence interval"), yes it is.  That does not effect the "confidence level."  Unless you arbitrarily decide to move it to 99% confidence level (or the third Standad Deviation), it will always be a 95% confidence level.

[J. J.]

Let's make this clear. Our null hypothesis is that Kerry and Bush are statistically tied, so we assume Kerry and Bush are both at 50%. Our confidence interval is 95% ( we could make it larger, if wanted).

For small samples, we have to use the binomial distribution. For samples of size 1-5, we can't conclude a statistically signifant difference, no matter with. If our sample is of size 6, we have a 1/64 chance that all 6 people support Kerry, and another 1/64 change that they all support Bush. The resuling 1/32 is less than our reject p=5%, so it would be statistically significant in that case.

For large samples, we get a standard error or deviation of sqrt(p(1-p)/n) = 0.5/sqrt(n). The radius 95% confidence interval is 1.96 standard deviations, or 0.98/sqrt(n). So basically, we have a statistically significant different if we're outside of
[50% - 1/sqrt(n), 50% + 1/sqrt(n)].  For n=1000, we get about
[46.9%, 53.1%].

The null hypothesis is not a 50/50 split; that is where you are making a mistake. 

You asked a question about this would be statistically signifigant.  The numbers that poll genenerates will always be with 95% confidence, each candidates numbers are within the MOE of the result.  If you are asking if the 95% is outside of the MOE (or "confidence interval"), yes it is.  That does not effect the "confidence level."  Unless you arbitrarily decide to move it to 99% confidence level (or the third Standad Deviation), it will always be a 95% confidence level.

Again, you're wrong. If you're testing to see if there's a statiscally significant difference, the null hypothesis is that there is a 50-50 tie. Re-read what I said carefully, you seem to lack basic understanding of this.

The null hypothesis, where you reject the validity of the poll, is that the result is less than the second standard deviation from the median.  The internal numbers of the poll have no effect on that.

[J. J.]

If the sample is large, and the level of statistical signifiance we are using is 95%, then it's about 1.96 standard deviations. When we are outside of that range, we conclude that there's a statistically significant difference. You can choose 3 standard deviations or 99.7%, and so on.

Actually it exceptionally close to two standard deviations; a full description can be seen here:


http://www.robertniles.com/stats/stdev.shtml

You must be logged in to read this quote.

This, however, is NOT the MOE.  The sample is always assumed to be accurate at, but it is not 5% of the time.  Even a 50/50 result will still not represent the population (even withing the MOE) 5% of the time.  The result of the poll, who has what percentage, will not change that.  A poll that shows 50% for each candidate will be just as statistically valid as a poll that shows 96% for one candidate; the MOE will be different.

[J. J.]

I'll ad that that if you had the entire population, i.e. all voters, you could make different assumptions.

[J. J.]

Again you're wrong, 3 standard deviations is more than 99%.You'tre hopeless confused about the MOE. If I have 1000 people polled, and 94% or 96% support one candidate, that's well outside the margin of error at the 95% level, the 99% level or the 99.9999999999999% level.

JFRAUD, now you are disagreeing with the website I quoted.  That is quote from it.  E-mail the author and tell him he's wrong.  I should warn you that before you do, my of stats textbook says the same thing.

So does the website you quoted:

You must be logged in to read this quote.

http://www.surveysystem.com/sscalc.htm


You reading comprehension skills are the problem. 

When you say something is statistically significant, you do that based upon on poll, typically a sample of 1000 or so. You completely fail to understand statistics if you don't realize that a reasonably sized sample gives statistically significant information. Go ask your statistics 101 teacher about statistical significance of opinion polls.

I can't beleive you haven't admitted that you're wrong yet. This is g pathetic, and a good example of why I hate Republicans. No matter how obvious I made it, they insist I'm wrong. f**ck you all.

What actually is pathetic is that you cannot comprehend what you are reading, even when you link to it as supportive to you postion.  That's why you have earned the name JFRAUD.  It hasn't been limited to this discussion, but it is common to the bulk of your posts, on various subjects.  The positions that you hold don't may you pathetic; that you can't support them is way does.

As both the recently quoted sites state, there is a level certainty, or "confidence level" is not effected by the results.  That you cannot comprehend that, in the face of evidence posted, only illustrates you lack of understanding, and gives increased reasons to doubt anything you say.

[J. J.]

Specifically are you saying that Marist polling is wrong? They had a sample of 1009, and they say

The results of the entire survey are statistically significant at ±3%.

http://www.maristpoll.marist.edu/usapolls/hc050308.htm

You've got a lot of explaining to do.

JFraud, you moron, that entire poll is based on a confidence level.  I just e-mailed Marist to see what it is.  They also refer to this as "Margin of Error." 

You have a lot of explaining to do.  There are various citations on this thread quoting the difference between confidence level and confidence interval/MOE, including one from a site that you linked to.  They are all saying the same thing.

Why can you not comprehend it?  You are actually disagreeing not with my comments, but the quotes from the sites.  Are you really that stupid?  Do you really think that anyone will believe you over those sites, especially since you said, go to one of them for an explanation?  Is this a matter of your problems with reading comprehension or something else?

[J. J.]

Umm, that's exactly what I said. You have a 95% confidence interval, which has a radius of about 3% for your standard sample of 1000 or so.  If that confidence interval doesn't include a tie, then the lead is  statistically significant. What part of that don't you understand?

I think a brick wall would have understood this by now.

You still have it wrong JFRAUD.  I'm going to go back and quote something I said previously.

You are looking at one poll and assuming that the poll is one of the 19 that is correct, and your basing that on the numbers within that poll.  The results of the poll have no effect on if the sample was an "accurate" sample.  The results do effect MOE, but the only conclusion that can be reached is that Kerry is 95% likely to have support within the MOE.

Now that said, the MOE will be smaller as the support for one cadidate moves away from 50%, but that has nothing to do with if the 95% likelihood that the poll is correct.  For example, if 100 people were polled, we could say that we are 95% confident that Kerry has 94% +/- 4.65%.  Likewise, if 100,000 were polled we could say that we are 95% that Kerry has 94 +/- 0.47%.

If the numbers change the MOE changes.  Assume that Kerry has 40% of the vote, according to the poll.  If 100 people were polled we could say that we are 95% confident that Kerry has 40% +/- 9.6%.  If 100,000 were polled we could say that we are 95% confident that Kerry has 40% +/- 0.3%.

You'll note that in all cases the confidence level stays the same.  None of this affects the confidence level, only makes the MOE shrink or grow.

You are going to be able to determine the confidence level from the results of the single pole.  That is why your basic question illustrates your ignorence of the subject.  You cannot determine if this one of those randomly wrong polls from the internal numbers (though it will effect MOE).

The MOE can change because of the result; that however does not change the confidence level.  It is possible that both candidates will be within the MOE on a given poll, but even in that case there is still a "bad" sample.  The MOE has no effect on determining if the sample is bad.  A 3% MOE does not mean that the sample has a 3% chance of being wrong; it means that if the sample is an accurate representation of the population the candidates score is +/- 3% of the number predicted in the poll.

Example:  Poll #1  Sample size of 1000.  The confidence level is 95%, and the MOE +/- 3.1%, and  Candidate A scores 50%.  The poll (or more accurately the pollster) can say that he is 95% sure that Candidate A has between 46.9% and 53.1% of the vote.  

Poll #2 Now, as stated (and this is hypothetical) that a second poll is conducted, using the same methods, sample size, and at the same time (SMST)  and Candidate A has 90%.  The MOE will drop to +/- 1.86%.  The same pollster can say that he is 95% sure that Candidate A has between 88.14% and 91.86% of the vote.  Nothing has changed in the pollsters methods, it's just a different sample.

Now let's that he takes a total of 20 polls (SMST):

Poll Numbers 1, 3, 4, 5,  Candidate A at 50%  MOE 3.1
Poll Number  2 Candidate A at 90%  MOE 1.86
Poll Numbers 8, 9, 10, 11, Candidate A at 49% MOE 3.1
Poll Numbers 6, 12, 13, 14, Candidate A at 51% MOE 3.1
Poll Numbers 15, 16, 17, Candidate A at 52%   MOE 3.1
Poll Numbers 18, 19, 20 Candidate A at 48%  MOE 3.1

Even though Poll #2 has a lower MOE, it is not an accurate desciption of the electorate.  The pollster could still say that, based on Poll # 2, that he is is 95% sure that Candidate A has between 88.14% and 91.86% of the vote.

Based on your example, there is nothing internal to the poll to show that this isn't a bad poll, like Poll #2; there isn't any way to do that, based on just one poll.  MOE does not come into play in determining this.

[J. J.]

I noticed you ignored my comment pointing out that you are yet again a lying hypocrite for telling me that the 95% confidence interval radius is 2, not 1.96 standard deviations.

Not that you being a lying hypocrite is anything new.  When will you ever admit that you're wrong?

Actually because, as pointed out, you were referring to a statistics website that I quoted.  I pointed that out earlier

You've said quite a lot that bears little resemblence to fact, the earliest one that I recall being your call for a "civil war" and most recent claim that something that happend in July of 1933 triggered something that happened March of 1933 (I'm still wondering where the Vatican keeps it time machine).  You've said so little that is accurate, very little of what you say will be believed.  Of course, when you post links, people do read them, and unlike you, they do understand them.

That's possibly why more and more people are calling you JFRAUD.  It doesn't descibe your politics by qualities of the mental processes as illustrated in your post.

[J. J.]

OK, now you're trying a new strategy, say some stuff that is actually right, and then say something wrong and claim that's what I said. when did I say there was ever a 3% probability of something with a 3% MOE?

I see you now know what a confidence interval is. Now, if you have one poll, with a MOE of 3.1% at at the 95% confidence level, and it has Kerry out of that [46.9%, 53.1%] confidence interval, then you can conclude that Kerry has a statistically significant lead (or Bush does), assuming Bush+Kerry=100%. It's statistically significant at that 95% cofidence level. Your probability of falsely rejecting the null hypothesis of a tie is at most p=5%.

You really do have a problem with reading comprehension.  Here is what was posted two days ago:

The thing is, even if the pollster does everything right, he's still going to get one absolutely wrong result out of the margin of error in X amount of polls.  Now, with a sample size of 1000, X will be lower than if the sample size is 300, but it's still going to happen.

Yeah, well he's never going to get 94-6 with a sample of 1000 when it was really a tie, and that's why 94-6 is a very statistically significant lead.

That you cannot say, statistically.

We are not referring to margin of error directly, but a problem that the poll will just be wrong.   When at a poll, statistically, it is accurate to say, this is the corect number, within the margin of error, X number of times out of 100.  X is usually 95 to 99.

With a 1000 sample poll, the margin of error is always less than 1.582%.
We have 96-4, which is a z-score of 27.8.

If you know anything about z-scores you'll realize there's no way you'll ever get that.

You'll note that I was saying thing then as now.  Now I know you have problems with calendars, but April 24 comes before April 26. (Well, GHW Bush thought September was December in 1988.)  Also note that the just contradicted yourself on that last statement about MOE.

You cannot tell if a poll represents the population from the internal numbers of the poll.  If the example was 50/50, 60/40, or 99/1, you'd still have the same problem.  The only thing the first example you posted showed was that the results were outside of the MOE; that alone does not determine statistical validity. If there more central tendency in the population than in the poll, you will actually get a smaller MOE the more inaccurate the poll is.

[J. J.]

So I meant standard deviation. It would have been the MOE for a 68.27% confidence interval. I didn't say anything about the level of confidence there. You have yet to respond to the following:
I pointed out you were wrong about saying I was wrong about MOE=1.96 standard deviations - no reply
I asked you why they say that a poll of 1000 says

You must be logged in to read this quote.

- no reply

Are you ever going to admit you're wrong?

MOE does not = 1.96 SD.  MOE, also known as confidence interval, is function of sample size confidence Level (which is standard deviation), sample size, and poll results.  Here is the description, again, not you have the mentality to comprehend it:

You must be logged in to read this quote.

http://www.surveysystem.com/sscalc.htm

BTW:  This is from the site you used as your source.

As pointed out befor the +/- 3 does not have any bearing on the validity of the poll, as has been pointed out.

You just illustrated your ignorance again. 

Jfern, this is not sarcasm, but you obviously have a reading comprehesion problem at the very least.  I'm not the only one who has noticed it.  You need help.

[J. J.]

If the sample is large, we do the normal approximation. If we want a 95% confidence level, we get a MOE of 1.96 standard deviations. I've gone over this a zillion times. Do you understand now?

I understand that you have no understanding of statistics.

Here is a relatively straight forward explanation of where standard deviation comes into play in determining the confidence level:

You must be logged in to read this quote.

http://encyclopedia.learnthis.info/s/st/standard_deviation_1.html

You've made the claim that "If we want a 95% confidence level, we get a MOE of 1.96 standard deviations. "  Instead of posting this nonsense, why don't you link to a site that says this, and post this statement.

Now the site you just linked to says this:

You must be logged in to read this quote.

As has been explained, the confidence interval is another name for the MOE.  This calculates the MOE.  As has been shown, the MOE does not determine the validity of the poll.  A candidate can have a lead over his opponent well beyond the MOE and the poll can still be invalid.

The statement that a poll shows that cadidate A has a given within the MOE, at a particular Confidence Level, is an accurate statement without regard to what the score is.