[Toro]

DerbyX DerbyX:

Toro Toro:

Reverend Blair Reverend Blair:

Ah, Harris Decima has the Cons at 34% too.
http://ca.news.yahoo.com/s/capress/0810 ... delxn_main

There were a couple of sites that tracked accuracy in the last election, Toro. Nanos was less than one percent off in his predictions, if I remember correctly. I'm sure if you spend more than 2 minutes, you'll be able to find them.

Well, since you're the one who keeps repeating it, and it will only take 2 minutes, why don't you back up your claim?

Bottom left

Less then a minute!

Now, do you have it for the other polls? What was happening to the trend?

How did Nanos do in the prior elections?

Blair says that

Reverend Blair Reverend Blair:

Nanos has a reputation for being right though, Ryan. That reputation comes from a long record of accuracy.

post1338156#p1338156

Well, if they have a "long record of accuracy," show it.

Truly, I'm interested if this is true.

[DerbyX]

Toro Toro:

Now, do you have it for the other polls? What was happening to the trend?

How did Nanos do in the prior elections?

You asked for proof of nanos accuracy and I provided it.

Do your own reseach instead of holding your opinion as fact until proven other wise and post data to support it. Nanos has the reputation for accuracy. If you say the others have it then provide proof.

[Toro]

DerbyX DerbyX:

Toro Toro:

Now, do you have it for the other polls? What was happening to the trend?

How did Nanos do in the prior elections?

You asked for proof of nanos accuracy and I provided it.

Do your own reseach instead of holding your opinion as fact until proven other wise and post data to support it. Nanos has the reputation for accuracy. If you say the others have it then provide proof.

Show me other examples of Nanos superior accuracy then. I'm more than willing to listen. You might be right. Show me that they are better than the other pollsters.

But if you've taken a single class of statistics you know that one example does not make a population.

[Toro]

BTW, Nanos had the Tories polling above 40 a few weeks ago when the other polls had them below. Was Nanos wrong then? Or were all the other polls wrong.

Look here

http://www.nodice.ca/elections/canada/polls.php

Nanos had the Tories at 40 on Sept 24. None of the other pollsters did.

[ryan29]

DerbyX DerbyX:

Toro Toro:

Now, do you have it for the other polls? What was happening to the trend?

How did Nanos do in the prior elections?

You asked for proof of nanos accuracy and I provided it.

Do your own reseach instead of holding your opinion as fact until proven other wise and post data to support it. Nanos has the reputation for accuracy. If you say the others have it then provide proof.

but nanos polls have also been all over the place , so i guess one of them is right but which one of the half dozen different possibilites put forward by this polling company ?

i also suspect in the very end he will be closer but were still a ways from the end so i suspect his numbers will change alot in final weeks . i bet his final poll will have the cpc higher and liberals lower so he doesn't get things wrong and risk being way off .

[DerbyX]

Toro Toro:

Show me other examples of Nanos superior accuracy then. I'm more than willing to listen. You might be right. Show me that they are better than the other pollsters.

But if you've taken a single class of statistics you know that one example does not make a population.

Not how it works. I showed Nanos numbers last election and pointed you to their webpage where if you look bottom right you can vet their credentials.

You seem to think that unless Nanos is proven beyond any doubt by hardcore evidence you accept then you are perfectly OK stating that HD is the correct poll.

http://www.harrisdecima.ca/en/

Here is HDs site. I don't see them vetting their credentials do you? Where are they pointing to their election results as proof of their accuracy?

YOU post evidence supporting the accuracy of the polling group you support not tell me to keep posting more and more support of Nanos.

[DerbyX]

ryan29 ryan29:

DerbyX DerbyX:

Toro Toro:

Now, do you have it for the other polls? What was happening to the trend?

How did Nanos do in the prior elections?

You asked for proof of nanos accuracy and I provided it.

Do your own reseach instead of holding your opinion as fact until proven other wise and post data to support it. Nanos has the reputation for accuracy. If you say the others have it then provide proof.

but nanos polls have also been all over the place , so i guess one of them is right but which one of the half dozen different possibilites put forward by this polling company ?

i also suspect in the very end he will be closer but were still a ways from the end so i suspect his numbers will change alot in final weeks . i bet his final poll will have the cpc higher and liberals lower so he doesn't get things wrong and risk being way off .

All the polls have. All you are doing is claiming that the pollsters that give the CPC the greatest level of support must therefore be correct because thats what you believe.

BTW, the polls have been all over the place because thats the way it goes during elections.

[Toro]

DerbyX DerbyX:

All the polls have. All you are doing is claiming that the pollsters that give the CPC the greatest level of support must therefore be correct because thats what you believe.

BTW, the polls have been all over the place because thats the way it goes during elections.

That's not what I'm saying. What I'm saying is that you cannot take one poll and say this is the most accurate poll. You can't say that about any of them. You can't say that because one nailed the last election that they are the one to believe the most.

I shot a gun once in my life. I killed a squirrel. Never picked a gun up again. It doesn't mean because the last time I hit my target that I'm a great marksman.

BUT ...

I'm more than willing to accept that Nanos MAY be the most accurate. I don't know. But I haven't seen any empirical evidence other than claims by people on CKA.

I look at the trend of all polls. The polls have been moving away from a Harper majority. Polls tell you about trends.

The only one that matters is Oct 14.

[DerbyX]

Toro Toro:

DerbyX DerbyX:

All the polls have. All you are doing is claiming that the pollsters that give the CPC the greatest level of support must therefore be correct because thats what you believe.

BTW, the polls have been all over the place because thats the way it goes during elections.

That's not what I'm saying. What I'm saying is that you cannot take one poll and say this is the most accurate poll. You can't say that about any of them. You can't say that because one nailed the last election that they are the one to believe the most.

I shot a gun once in my life. I killed a squirrel. Never picked a gun up again. It doesn't mean because the last time I hit my target that I'm a great marksman.

BUT ...

I'm more than willing to accept that Nanos MAY be the most accurate. I don't know. But I haven't seen any empirical evidence other than claims by people on CKA.

I look at the trend of all polls. The polls have been moving away from a Harper majority. Polls tell you about trends.

The only one that matters is Oct 14.

Except that we are looking at the empirical evidence. We are referencing their references and professional reputation. Thats the difference. Rev isn't supporting them because they show the NDP at the highest levels, quite the opposite. Polls do show trends yes but the difference between HD and Nanos are stark and accuracy of the pollsters should be factored in.

[Toro]

DerbyX DerbyX:

Except that we are looking at the empirical evidence. We are referencing their references and professional reputation. Thats the difference. Rev isn't supporting them because they show the NDP at the highest levels, quite the opposite. Polls do show trends yes but the difference between HD and Nanos are stark and accuracy of the pollsters should be factored in.

That's fine. Then post the evidence why this is the case.

Posting the last election results does not necessarily mean anything. It might, but by definition, one pollster has to be the closest.

Show me that Nanos was the closest the last five elections (or so) and I'd be more willing to entertain the notion.

[kenmore]

The only polls that count are the voting polls.. so get out and vote... ABC

anything but Tory!

[DerbyX]

Toro Toro:

DerbyX DerbyX:

Except that we are looking at the empirical evidence. We are referencing their references and professional reputation. Thats the difference. Rev isn't supporting them because they show the NDP at the highest levels, quite the opposite. Polls do show trends yes but the difference between HD and Nanos are stark and accuracy of the pollsters should be factored in.

That's fine. Then post the evidence why this is the case.

Posting the last election results does not necessarily mean anything. It might, but by definition, one pollster has to be the closest.

Show me that Nanos was the closest the last five elections (or so) and I'd be more willing to entertain the notion.

You keep demanding that other people do your research.

YOU do it. You determine who is the most accurate or if you simply consider them all innaccurate then you shouldn't even be watching their trends for any information.

[Blue_Nose]

Here's the last two election results along with the last poll results from SES/Nanos and Ipsos-Reid. I just summed the total error across the five parties for each pollster.

I didn't easily find poll results from 2000, so that's as far back as it goes.

Last election was certainly a good one for Nanos, but he's only marginally better than Ipsos-Reid in 2004.

0:

results.PNG [ 13.66 KiB | Viewed 286 times ]

[Toro]

DerbyX DerbyX:

You keep demanding that other people do your research.

YOU do it. You determine who is the most accurate or if you simply consider them all innaccurate then you shouldn't even be watching their trends for any information.

You made the claim. You back it up. Walk the talk.

[DerbyX]

Toro Toro:

DerbyX DerbyX:

You keep demanding that other people do your research.

YOU do it. You determine who is the most accurate or if you simply consider them all innaccurate then you shouldn't even be watching their trends for any information.

You made the claim. You back it up. Walk the talk.

I did. I provided the evidence to back up my claim.