You are viewing an obsolete version of the DU website which is no longer supported by the Administrators. Visit The New DU.
Democratic Underground Latest Greatest Lobby Journals Search Options Help Login

Reply #29: you just aren't very good at analysis, apparently [View All]

Printer-friendly format Printer-friendly format
Printer-friendly format Email this thread to a friend
Printer-friendly format Bookmark this thread
Home » Discuss » Topic Forums » Election Reform Donate to DU
OnTheOtherHand Donating Member (1000+ posts) Send PM | Profile | Ignore Tue Aug-18-09 01:51 PM
Response to Reply #28
29. you just aren't very good at analysis, apparently
Edited on Tue Aug-18-09 01:56 PM by OnTheOtherHand
I don't think it's nasty or unprofessional to call crap crappy; even if it is, the crap remains crappy regardless. If you want to depict a relationship between "county size and vote change" (whatever exactly those variables are), a standard and reasonable way to do it is a scatterplot -- not a sorted bar chart with a diagonal dotted line through it. The latter raises questions about the intentions and/or competence of the analyst.

You didn't directly answer my question, but your own urban legend scatterplot bar chart from hell indicates that Bush did better in 2004 than in 2000 in all but one New York county. So much for Bush "breaking even or losing share in Republican rural areas and small towns."* If that's what you meant by the urban legend being a myth, then I guess we agree, and I appreciate your concession.

* Of course, this chart doesn't display "share" at all, which in my opinion is a weakness. But in this case the answer is the same: Bush's vote share increased in all but one New York county.

The bar chart from hell does also indicate that Bush did relatively better in some downstate counties (but not in other cities such as Albany, Buffalo, and Syracuse). It hypes that finding by displaying ratios from low bases. For instance, in Brooklyn, Bush increased his vote share by about 8.6 points; it looks very impressive in this chart because Bush's vote share in 2000 was under 16%, but an 8.6-point swing is an 8.6-point swing no matter what the previous percentage was.

To look at it another way, altogether Bush got about 190,000 more votes in the five boroughs in 2004 than in 2000 -- and there were about 7.4 million votes cast. Even if we assume -- for no particular reason -- that all those votes are stolen, we're nowhere near the exit poll result. (Go ahead, throw in some more counties. No point in my trying to do all your work for you.)

I actually can't replicate your correlations; you claim to have lever-only returns, but you've posted neither the data nor the evidence. So, for now, I'll file that alongside the claims that Oregon is the only 100% paper state (whatever that even means) and the only 2004 battleground or strong Democratic state within the margin of error. At any rate, you may sincerely believe that it is impossible for Bush to have done so 'well' in the NY metro area without fraud, but your sincere belief doesn't constitute evidence. Sorry.
Printer Friendly | Permalink | Reply | Top

Home » Discuss » Topic Forums » Election Reform Donate to DU

Powered by DCForum+ Version 1.1 Copyright 1997-2002
Software has been extensively modified by the DU administrators

Important Notices: By participating on this discussion board, visitors agree to abide by the rules outlined on our Rules page. Messages posted on the Democratic Underground Discussion Forums are the opinions of the individuals who post them, and do not necessarily represent the opinions of Democratic Underground, LLC.

Home  |  Discussion Forums  |  Journals |  Store  |  Donate

About DU  |  Contact Us  |  Privacy Policy

Got a message for Democratic Underground? Click here to send us a message.

© 2001 - 2011 Democratic Underground, LLC