Worst Congress Ever

[KeithE]

[Ed Pettibone]

Ed: Keith have you ever seen a chart on the accuracy of Pollsters?

http://farm4.static.flickr.com/3295/252 ... f95a_o.png

Note where CBS / New York Times & Gallup fall in percentage of pollster induced error

Pollster Ratings v4.0: Results
by Nate Silver @ 6:13 PM


-- These ratings reflect polling for President (general and primary elections), U.S. Senate, U.S. House, and gubernatorial races since 1998. More recent cycles are weighted more heavily. This is a truly massive amount of data: roughly 4,700 polls.

-- The variable called rawscore is the most direct measure of a pollster's track record. However, it is much inferior to PIE -- or Pollster-Introduced Error -- for evaluating the effectiveness of different pollsters on a going-forward basis. Because polling involves a great deal of luck in the near-term, rawscores must be substantially regressed toward the mean. However, different types of pollsters are regressed to different means. In particular, pollsters that have made a commitment to transparency and disclosure have been shown to have superior results over the long-run. The way we measure this is whether the pollster was a member of either the NCPP or the AAPOR Transparency Initiative as of 6/1/10.

-- PIE is expressed as a positive number and reflects the amount of error that a pollster introduces above and beyond that which is unavoidable due to things like sampling variance. The lower a firm's PIE the better.

[William Thornton]

I am thinking that fewer laws passed means we are better off...but I know that deems wanted another porkulus bill.

[KeithE]

[KeithE]

[Ed Pettibone]

[KeithE]

Well Ed, you are correct to say the Popularity data plot was really several polls.

But I still read you as largely negative on the use of polls; am I correct? When you say “quote polls if you must”, what else am I to assume.

As to using good polls,I will attempt to never use the only two polls (Zogby Intetractive[probably sic and differentiated from Zogby], and Columbus Dispatch) that stand a chance of being statistically significantly different than all the others in your posted study (which I still wonder how they can quantify PIE).


Polls tell a more accurate story than our guesses. I do think it wise to look at the wording of any poll if they make that available and judgment made as to whether or not that is “leading the witness” as Perry Mason and HamBurger often say (we’ve been watching re-runs lately).

The case that I was making in this post was that Congress may be the worse ever (not only in terms of “popularity” but 13 other points brought out in the article for you consideration). Making that popularity history point better (than my article did) is a Gallup tracking poll: same question asked over a long period.



Interesting to note the peak coming right after 9/11 and then a smaller peak right when Obama took office with a .

But the real point germane to my thesis- worst congress ever- is that 10% is the lowest ever (the NYT/CBS poll had it as 9%, has only 7% feel congress is doing a good/excellent job). Truth is it has been a long downhill slide for Congress since 9/11 following a strong growth in popularity during the Clinton years and we are at a new low in terms of popularity. My originally posted article had 13 other points that get at more than just Popularity.

[Ed Pettibone]

Ed: And again you are citing the polling company which is the 24th most likely of 32 to have Pollster Introduced Error.

But no Keith I am not negative on the use of polls per se, but I am negative on how they are too often interpreted by amateurs.

And although I can not scientifically explain the processes (despite having seen some of them demonstrated by people I trust) I am aware of that the visual depiction of "Data" can be and is often manipulated to present misleading if not totally false impressions for the significance of said "Data".

[KeithE]

Wrt polls - whatever you want to think, Ed .

Now any more thoughts about Congress?