First, boy, was I stupid to think that the polling organizations don't know what they're doing. Yes, it didn't make sense to me why they were adjusting their samples like they were (and it still doesn't make sense), but whatever "secret sauce" they were adding, they got it about right. In my biz, we refer to doing things based on "engineering judgement"; it's the summation of all your experience with similar systems. I guess their adjustments were "pollsters' judgement" - although I did hear Scott Rasmussen say he had no idea how it would really turn out.
It was a bad day all the way around. Here in Florida, conservative star Alan West is deep in recount (they jerry-mandered his district to engineer this). We were unable to dump Senator Bill Nelson, a dependable rubber stamp for Obama. I'll never forget the first time I sent him a letter about about something - he answered it about four months later with a curt brushoff. An Orlando democrat known for insane histrionics, Alan Grayson, voted out in 2010, engineered a way back into the house. There are local stories that the Orange County Democrats contributed big bucks to his eventual opponent during the Republican primary because they thought the guy Grayson eventually faced was more beatable. Alcee Hastings, a Democratic representative from south Florida was re-elected by something like 85 to 15% over an NPA opponent. So what? He was a judge convicted of soliciting bribes in 1989, impeached, kicked out of his office. After some time (presumably learning better criminal skills) he ran again and has been a fixture in office ever since. He has a constant barrage of allegations of criminal or unethical behavior against him, but he keeps getting re-elected.
At some point, you have to say, "South Florida, if you keep electing criminals, don't be surprised when they rob you".
Elsewhere, my personal favorite Mia Love was defeated in her bid for the House of Representatives - black Republican women get even less respect than white Republican women - in the same way black conservatives are attacked more than whites.
So what can we expect? As Obama told Russian President Dmitry Medvedev,
"This is my last election," Obama said. "After my election I have more flexibility."Expect more flexibility. More executive orders. Expect a carbon tax, if not outright carbon trading (cap and trade) because Sandy was caused by Global Warmening, doncha know (H/T to Tam). Of course you'll get more taxes and less economic growth. It appears that's not a bug, it's intended.
Hauser's Law demonstrated.
Obamacare, of course, becomes the law of the land. They can pass a few more bills to repeal it with no effect like the 30 or so they've done already, but they can't stop it. More companies will drop their employees' health insurance, as intended - so the Fed.gov can ride to the rescue. As planned. This will, as sure as the sun rises in the east, hurt seniors, poor people, young kids with disabilities - anyone not on the peak of the "whole lives" healthcare system curve. Gun control? Sure. Assault Weapons Ban? Already on the table. Smith and Wesson (SWHC) was up 9.6% today and Sturm Ruger (RGR) was up 6.8%. Already, reports of black rifles being sold out are coming in.
THESE are the times that try men's souls. The summer soldier and the sunshine patriot will, in this crisis, shrink from the service of their country; but he that stands by it now, deserves the love and thanks of man and woman. Tyranny, like hell, is not easily conquered; yet we have this consolation with us, that the harder the conflict, the more glorious the triumph. What we obtain too cheap, we esteem too lightly: it is dearness only that gives every thing its value. Heaven knows how to put a proper price upon its goods; and it would be strange indeed if so celestial an article as FREEDOM should not be highly rated.
Or in other words, "It's a great big shit sandwich, and we just got it forced down our throats".ReplyDelete
‘Yes, it didn't make sense to me why they were adjusting their samples like they were’ReplyDelete
But they were not adjusting their samples. Samples are determined randomly by any reputable polling organization.
But they all were saying they sampled more Ds than Rs. 6, 8 or 10% or even more. That doesn't sound like a random sample to me. Not in a 51/49 country.Delete
No, the polls were conducted by random sampling. That’s how they work. They were saying that in a random sample; 6, 8 or 10 % more people said they were democrats, than republicans. (Way out of whack I agree, but a pollster does not have the luxury of ignoring his data)Delete
Not all of the polls indicated this though; some said the D and R were about even. Why the polls were so divergent is still a mystery. My guess is that there was a lot of uncertainty out there, and even possibly some dishonesty in the responders. Or people may have changed their minds at the last minute. Who knows?
The weighted poll averages gave a slight advantage to Obama and exactly as predicted, he won by a fairly narrow margin. The final two polls put Romney up by 1 point plus or minus 4 and he lost by about 2, well within the margin of error.
Given the variation in the polls, I expected the undecided to break for Romney in the end, pushing him over the top. That and his one point lead suggested he had momentum on the last day. If he did, it wasn’t enough.
Another interesting point is that the short term daily tracking polls often found more people indicating they were democrats by a considerable margin but in the long term polls which asked only about party affiliation, the split was about even. I have no idea why that would be.
This was an interesting election. I learned a lot about polling and its limitations of which there are legion.
BTW, you have a nice blog. I’ve been following it for a while.
Thanks. I find the problem interesting from a lot of perspectives. They place random phone calls? Who answers random calls? I look at caller ID and either ignore it, or have the phone set to block repeat numbers. I'd assume, if it's random, they have to call cell phones because some folks don't keep landlines anymore (I do).Delete
It's a tough measurement problem. Compounded by the fact that polls have morphed from being research for the campaigns to being the news. I think they're really misused.
‘Who answers random calls?’Delete
Well exactly. There are tremendous biases built into polls with no real way to remove them. For example, I’m on a no call list and so they can’t call me. In many states there are laws against calling people on their cell phones etc.
What about something as simple as the time of day – depending upon when you call you might get a completely different set of people and from what I understand they get answers from less than 10% of the people they call. People also may lie or change their minds at the last minute.
I agree the polls are a distraction. Most people probably do not understand their limitations. Not only that but I’m betting they contribute to voter fatigue. What can we do about them though, other than educate ourselves and others about what they mean? The other option is to ignore them altogether, although in the general they seemed correct this time. They predicted a close election and it was.
The last two polls put Romney up by one percentage point accurate within 4 percentage points. He lost by two percentage points so both polls were correct 1 – (-2) = 3 < 4.ReplyDelete
So does this mean Ann Margaret is not coming Sir?ReplyDelete
Yes it is going to be crap, but I must retain some levity to keep my sanity.