Forum Settings
       
1 26 27 28 29 30 31 32 Next »
Reply To Thread

LBGT TerrorismFollow

#777 Nov 09 2012 at 1:12 AM Rating: Good
****
4,135 posts
Almalieque wrote:
Besides, as I was watched on Tuesday


Ha ha, you're watched! Smiley: lol
____________________________
Dandruffshampoo wrote:
Curses, beaten by Professor stupidopo-opo.
Annabella, Goblin in Disguise wrote:
Stupidmonkey is more organized than a bag of raccoons.
#778 Nov 09 2012 at 8:23 AM Rating: Good
*******
50,767 posts
Sir Xsarus wrote:
I find it interesting
Do you? Do you really?
____________________________
George Carlin wrote:
I think it’s the duty of the comedian to find out where the line is drawn and cross it deliberately.
#779 Nov 09 2012 at 8:35 AM Rating: Excellent
Liberal Conspiracy
*******
TILT
Sir Xsarus wrote:
No one has been saying all the polls were 100% right...

Except for that Scott Rasmussen fellow. He was the bestest pollster in the universe in 2008!
____________________________
Belkira wrote:
Wow. Regular ol' Joph fan club in here.
#780 Nov 09 2012 at 8:53 AM Rating: Default
The All Knowing
Avatar
*****
10,265 posts
stupid wrote:
Almalieque wrote:
Besides, as I was watched on Tuesday


Ha ha, you're watched! Smiley: lol


That is the number one sign of weakness on an online forum.
#781 Nov 09 2012 at 8:54 AM Rating: Good
Repressed Memories
******
21,027 posts
Does Alla even lift?
#782 Nov 09 2012 at 9:36 AM Rating: Good
GBATE!! Never saw it coming
Avatar
****
9,957 posts
Professor stupidmonkey wrote:
Almalieque wrote:
Besides, as I was watched on Tuesday


Ha ha, you're watched! Smiley: lol


Forgot his NoHomoTM shorts?
____________________________
remorajunbao wrote:
One day I'm going to fly to Canada and open the curtains in your office.

#783 Nov 09 2012 at 10:21 AM Rating: Excellent
Meat Popsicle
*****
13,666 posts
Almalieque wrote:
The first point is that polling isn't a mathematical proof for a conclusion, because there is a difference between statistics and mathematics. Statistics use mathematics, but it doesn't make it a mathematical proof.


The difference between a mathematical proof and a statistical correlation is lost on most scientists I work with, much less anyone else. You're probably not going to make any headway with this. Smiley: rolleyes

Almalieque wrote:
However, polling the nation on their opinion on something that is heavily divided will never mathematically guarantee results with the same sample size.


Well if you make the assumption your poll is an accurate reflection of reality you have a margin of error, you don't seem to be making that assumption though.

In my field at least, an algorithm is usually tested and trained on old data, then used to predict results. If the predicted and actual results vary too much going forward, the algorithm is refined and the process repeats. Likewise one poll matching election results more closely suggests that its algorithm is more likely working properly at this time, and doesn't need tweaking. Realistically any poll that has the results within its margin of error is doing a fine job. If this isn't the case, the poll is more likely to be making a fundamental error in its assumptions, and should be looked at more carefully.

Almalieque wrote:
The third point is that political polls are snapshots at that day and time that could change immediately upon their release.


This is where I'd point to gbaji's previous post about watching the trends over a period of time. Of course there's no guarantee things won't change drastically going forward, but there some solace to be found in the fact it usually doesn't.


Edited, Nov 9th 2012 8:55am by someproteinguy
____________________________
That monster in the mirror, he just might be you. -Grover
#784 Nov 09 2012 at 11:00 AM Rating: Excellent
*******
50,767 posts
Heh. "It isn't accurate! Except all the times where it was!"
____________________________
George Carlin wrote:
I think it’s the duty of the comedian to find out where the line is drawn and cross it deliberately.
#785 Nov 09 2012 at 11:11 AM Rating: Excellent
Meat Popsicle
*****
13,666 posts
They we're just lucky their faulty assumptions lined up with the unusual nature of this election. Smiley: nod
____________________________
That monster in the mirror, he just might be you. -Grover
#786Almalieque, Posted: Nov 09 2012 at 11:13 AM, Rating: Sub-Default, (Expand Post) Yes, you're absolutely right. What I left off was due to a catalyst. People for Romney isn't likely to just change over night; but if he were caught in sex scandal, I'm sure that he would have lost the majority of the "swing votes". The fact that those snapshots typically wont change is how you are able to predict a state in the first place. There is no reason to believe that Washington DC would vote for Romney or Georgia vote for Obama. So, instead of using hours polling those places, you can focus on the swing states down to the city/county level. That's how you get your accuracy.
#787 Nov 09 2012 at 11:38 AM Rating: Excellent
Meat Popsicle
*****
13,666 posts
Almalieque wrote:
However, if you were to ask "Do you support abortion" or any other hot topic that is so heavily divided, it becomes increasingly more difficult to be that accurate with the same amount of numbers due to the increased weight of other factors such as the demographics, how the question was worded, how the people were contacted cell vs email vs land line, time of day of the contact, etc. It's not impossible, but it becomes much more about being attentive to details at that point.


Absolutely. You reach a point where there are too many factors to accurately model in a complex environment such as the real world. Nearly every algorithm from mass spectra alignment software, to climate prediction software, to market analysis, to election polling all suffer from this same flaw. In the end you're never going to be able to get a perfect approximation of reality.

So what do you do? Well, you make assumptions, you simplify, condense and ignore certain variables you think will have a minor affect, or that you don't have data on, etc.

In a laboratory setting this would be something like removing (or I suppose simply not adding?) part of an equation, varying a parameter, or changing its weighting through a range of reasonable values and observing how the accuracy of your algorithm changed. For polling I'd reiterate what I said above, the more closely the results match the predicted ones, the less likely it is the poll needs to be altered. Assuming you've been testing the methods on previous data as well of course. Also, throwing out that the more complex algorithm (the one with more values for more more possible factors) is not necessarily the more accurate one. People tend to ***** up more complicated things, and some factors may be best ignored if they prove difficult to model accurately.
____________________________
That monster in the mirror, he just might be you. -Grover
#788 Nov 09 2012 at 12:37 PM Rating: Default
The All Knowing
Avatar
*****
10,265 posts
SomeProteinGuy wrote:
In a laboratory setting this would be something like removing (or I suppose simply not adding?) part of an equation, varying a parameter, or changing its weighting through a range of reasonable values and observing how the accuracy of your algorithm changed. For polling I'd reiterate what I said above, the more closely the results match the predicted ones, the less likely it is the poll needs to be altered. Assuming you've been testing the methods on previous data as well of course. Also, throwing out that the more complex algorithm (the one with more values for more more possible factors) is not necessarily the more accurate one. People tend to ***** up more complicated things, and some factors may be best ignored if they prove difficult to model accurately.


That was what I was referring to when people are given poll results that they don't agree with, they tend to find "errors" or "bias" in the polling, i.e. "democrat/republican heavy".
#789 Nov 09 2012 at 12:50 PM Rating: Excellent
Meat Popsicle
*****
13,666 posts
Ahhh, gotya.

Anyway, I'd say lets get back on topic, but I have no idea what the heck we were talking about in the first place. Still trying to figure out how a thread on gay terrorists got derailed into one about polling statistics. Smiley: confused

Seriously people, you have done enough! Have you no sense of decency!!? Smiley: motz

Or something... Smiley: um
____________________________
That monster in the mirror, he just might be you. -Grover
#790 Nov 10 2012 at 2:11 PM Rating: Default
The All Knowing
Avatar
*****
10,265 posts
Just as I was going to complain about never being apart of these polls, I got two calls from the Gallop poll, but wasn't able to participate because of driving and being in a meeting. They said that they will call back. I can't wait to have my views represent millions of the nation! Smiley: yippee
#791 Nov 11 2012 at 10:09 AM Rating: Good
Soulless Internet Tiger
******
35,474 posts
You answered your phone while driving and again later, while in a meeting?
____________________________
Donate. One day it could be your family.


An invasion of armies can be resisted, but not an idea whose time has come. Victor Hugo

#792 Nov 11 2012 at 10:17 AM Rating: Excellent
Liberal Conspiracy
*******
TILT
It was Gallup!
____________________________
Belkira wrote:
Wow. Regular ol' Joph fan club in here.
#793 Nov 11 2012 at 10:41 AM Rating: Good
*******
50,767 posts
Uglysasquatch wrote:
You answered your phone while driving and again later, while in a meeting?
The kind of luxury one gets when they're not important.
____________________________
George Carlin wrote:
I think it’s the duty of the comedian to find out where the line is drawn and cross it deliberately.
#794 Nov 11 2012 at 12:08 PM Rating: Default
The All Knowing
Avatar
*****
10,265 posts
Uglysasquatch wrote:
You answered your phone while driving and again later, while in a meeting?


I almost always answer my phone while driving, unless I'm on post. And for the meeting, it was during a break.
#795 Nov 11 2012 at 12:49 PM Rating: Good
Uglysasquatch wrote:
You answered your phone while driving and again later, while in a meeting?


Never done that? It's like unzipping your fly and going around the table, smacking everyone in the face with your ****, only legal, faster and slightly less impolite.
#796 Nov 11 2012 at 1:57 PM Rating: Good
Soulless Internet Tiger
******
35,474 posts
Kavekk wrote:
Uglysasquatch wrote:
You answered your phone while driving and again later, while in a meeting?


Never done that? It's like unzipping your fly and going around the table, smacking everyone in the face with your ****, only legal, faster and slightly less impolite.
I've done both, but never used them as the excuse as to why I can't continue to talk. If I answered the phone, I had time to talk. If I didn't answer, it's because I didn't have time.
____________________________
Donate. One day it could be your family.


An invasion of armies can be resisted, but not an idea whose time has come. Victor Hugo

#797 Nov 11 2012 at 2:48 PM Rating: Decent
The All Knowing
Avatar
*****
10,265 posts
Uglysasquatch wrote:
Kavekk wrote:
Uglysasquatch wrote:
You answered your phone while driving and again later, while in a meeting?


Never done that? It's like unzipping your fly and going around the table, smacking everyone in the face with your ****, only legal, faster and slightly less impolite.
I've done both, but never used them as the excuse as to why I can't continue to talk. If I answered the phone, I had time to talk. If I didn't answer, it's because I didn't have time.


The Gallop said that they couldn't talk to me while I was driving. I was thinking your rational, "If I answered the phone then I am able to talk to you'. I assume that they don't want to be linked to a vehicular accident.

For the meeting, I had time to talk, just only about 2 minutes. I had time to answer or hear some statements, but not enough time to complete a survey.

Anyways, they just called back and everything is good.
1 26 27 28 29 30 31 32 Next »
Reply To Thread

Colors Smileys Quote OriginalQuote Checked Help

 

Recent Visitors: 343 All times are in CST
Anonymous Guests (343)