Silicon Investor (SI) -- The First Internet Community

STOCKTALK

We've detected that you're using an ad content blocking browser plug-in or feature. Ads provide a critical source of revenue to the continued operation of Silicon Investor. We ask that you disable ad blocking while on Silicon Investor in the best interests of our community. If you are not using an ad blocker but are still receiving this message, make sure your browser's tracking protection is set to the 'standard' level.

Politics : Formerly About Advanced Micro Devices -- Ignore unavailable to you. Want to Upgrade?

To: koan who wrote (986972)	12/11/2016 3:29:53 PM
From: Bilow	1 Recommendation Recommended By FJB Read Replies (1) \| Respond to of 1570833

Hi koan; Re: "No, it didn't hurt at all [by Hillary losing]."; BWAHAHAHAHAHA!!! LOL!!! BWAHAHAHAHAHA!!! This is really rich! I've got plenty of lefty friends and relatives and I know exactly how the election effected them. They're just now getting over it, LOL. And I know your friends (well, if any) and relatives are the same. Or at least your co-workers, LOL. But somehow, all that sadness had no effect on you! What you're claiming is that you're psychologically abnormal. You're claiming that you don't feel empathy, LOL. You're claiming to be a sociopath, LOL! This is truly hilarious; of course I don't believe it for a minute. Nope, you cried like a baby over the election and I don't need to go back through the SI archives to prove this. I mean really, I call your exaggerations lies just to annoy you, not because I'm psychologically abnormal. And if I didn't? If I only called lies the things you say that are demonstrably untrue? You wouldn't respond and it would decrease my entertainment. ---------------------------------------------------------------------------------------------------------------------- Re: "When Poll says something that turns out to be different than what happened, that is not a lie. You really need to find out what in the hell a lie is. That is just a statistical mistake. And that is why the couch polls in terms of PROBABILITY. They say right up front it is a matter of probability."; No, the lie is when the pollsters use methods that are statistically invalid. And that's what they did. It was very simple, really. They assumed that the turnout would be the same in 2016 as it was in 2012. So they adjusted their polling results to match the 2012 turnout and that moved things about 4 or 5% in favor of the democrats. But the whole problem with Hillary was not support, it was whether or not her supporters would actually turn out to vote for her. That was the big issue and most of the pollsters simply ignored it. Facing that problem would have required that they give results that were more favorable to Trump and they didn't do that. Instead, most of them used a "likely voter model" that assumed that the various voters turn out at levels equal to what they did in previous elections. The right wing press was all over this for months before the election. Trump was getting huge rallies of enthusiastic people while Hillary was having trouble filling small bars. The right wing press reported the polling results and corrected them for the inaccurate assumptions on turnout. But this was not what the leftists wanted to believe so they swallowed the lie. -------------------------------------------------------------------- The correct polling method for turnout is to simply ask the voters how likely they'll turn out. And when that was taken into account, Trump was easily ahead. Here's the LA Times polling results: And here's the explanation for why the LA Times poll was different: Does the poll use a likely voter model? No. However, more weight is given to voters who express a greater degree of certainty that they will vote in November. Rather than assume that every voter is equally sure of his or her allegiance to one candidate or the other and is just as certain to vote, the Daybreak Poll asks participants to rate their likelihood of voting and voting for each candidate. To estimate the vote, we calculate the ratio of a participant’s likelihood of voting to his or her likelihood to vote for a candidate. cesrusc.org cesrusc.org -------------------------------------------------------------------- Re: "The probability that she would win was around 90% in most polls. But that still meant that there was a 10% chance that she would not win."; The 10% chances quoted are from individual polls and arise from the limited number of people surveyed. When they come up with these estimates they assume that the poll is unbiased and that the polling errors are due to the small numbers of voters asked. My claim is that these statistics were in error (a lie) and that, in fact, the polls were biased in favor of Hillary. You can see bias by simply noting that too many polls all made the same error. That is, the polls were biased and so were not independent estimates. If the polls had been truly unbiased estimates, statisticians could combine them into a bigger poll and that way reduce the uncertainty in the polls. The Huntington Post statisticians made exactly that assumption. That's why they said that Clinton had a 98.5% chance of winning (IIRC). So it's not an issue of the polls were wrong that 10% of the time. According to the laws of statistics, the probability that the polls were unbiased was around 2%. For most social scientists, that would be enough to prove that the polls were biased. The FiveThirtyEight website did best at giving Trump a 30% chance of winning but Trump didn't just "win". He slaughtered Hillary with 306 electoral votes. FiveThirtyEight gave an exceedingly small chance that the election could be that lopsided in Trump's favor. I can't find it on their website but it's probably recorded somewhere on SI. -- Carl P.S. I've got to get some important gaming done, as well as typing up the unified field theory, so I'm going to have to say goodbye perhaps for a day or two...