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 #53: I should learn to save links to a few of my own posts [View All]

Printer-friendly format Printer-friendly format
Printer-friendly format Email this thread to a friend
Printer-friendly format Bookmark this thread
This topic is archived.
Home » Discuss » Topic Forums » Election Reform Donate to DU
OnTheOtherHand Donating Member (1000+ posts) Send PM | Profile | Ignore Wed Jun-29-05 07:31 AM
Response to Reply #45
53. I should learn to save links to a few of my own posts
But I can go through the basics pretty efficiently.

The National Election Study series is AFAIK the oldest "continuous" academic survey series, dating back to 1948 (although at that point they presumably didn't know what they were starting). NES conducts interviews in homes (which allows longer interviews, but also presumably creates different social effects than phone interviews would), and works hard to maximize the response rate (lots of quickie phone polls these days are one-try-and-done). When political scientists want to check out something about U.S. public opinion and political behavior, they tend to reach for the NES and/or the General Social Survey (GSS), which asks a wider range of questions.

In the 2002 NES (pre-election wave -- everyone is supposed to be interviewed twice, before and after the election), among folks who said they had voted in the 2000 election and whom they had voted for, 51.6% said Bush and 44.3% said Gore. That is the unweighted result. When the results are weighted to match the demographics of respondents to census figures (the pre-election post-stratified weight), the gap widens to 52.6%/43.5%. These figures include both (reported) 2002 voters and non-voters -- of course in the pre-election wave no one had voted yet.

In the 2004 NES, the pre-election gap is narrower: 50.1% to 46.5% favoring Bush if no weight is used, or 50.9% to 45.8% if the demographic weight is used. Crosstabulating with the post-election survey, we find that among people who claimed to have voted in the 2004 election and also in the 2000 election, 52.7% recalled having voted for Bush, and 44.0% for Gore.

I mentioned the GSS, so let's chuck that in too. In the 2002 GSS, among people who reported having voted in the 2000 election, 50.6% reported having voted for Bush and 44.7% for Gore.

So you see, a five-, or six-, or maybe even a nine-point gap between recalled Bush voters and Gore voters isn't out of line with what we find in other surveys. No political scientist is gonna look at the weighted 43/37 in the NEP and say, "Ohmigosh, that's bizarre."

Bear in mind that the unweighted gap between recalled Bush and Gore voters in the NEP is much smaller, about 1 point. That is actually "too small" in comparison with all these other surveys, and therefore tends to support -- not refute -- the hypothesis of some sort of participation bias.

I think foo_bar has posted a link to British panel studies that show some percentage(s) of people 'changing their minds' about who they voted for. We could try this with US data -- in fact there is a 2000-02-04 NES panel study -- but I haven't, and won't before I leave the country tomorrow. At any rate, the phenomenon is well known. I dunno where I buried foo_bar's link, but meanwhile, this may be useful:

(foo, if you happen to be reading this -- (1) could you post that other link once more? (2) the link above cites, although does not document, the factoid you PMed me once): "in the USA, for example, where John F Kennedy won the Presidency by a tiny margin, the margin on recalled vote steadily increased during his term, and, after he was killed, some two-thirds recalled that they had voted for him.")

Also well known is false reporting of having voted at all. NES validation studies have shown that 10 or 12 or 14 percent of NES respondents may report voting when a check of the records indicates that they haven't. (But we also know that people who participate in the pre-election NES are more likely to vote afterwards! and it also appears that non-voters are increasingly underrepresented in the survey.)
Printer Friendly | Permalink |  | 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