A few months ago, I wrote that, based on the so-called generic ballot (surveys that as, “If the elections for Congress were being held today, which party’s candidate would you vote for in your Congressional district?”) and some research by Bafumi, Erikson, and Wlezien, the Republican Party looked to be in good shape in 2010.
Recently, Harry Joe (who took a statistics course from Joe Bafumi at Dartmouth!) crunched the early poll numbers, does the adjustment based on the Bafumi/Erikson/Wlezien regression, and comes up with a forecast that the Republicans will win by 8 percentage points (that’s 54%-46%); that is, 1994 all over again, but this time without the benefit (yet) of any Newt Gingrich-like figure (although I’m sure there will be many proto-Gingriches around to claim the credit if this all happens). Here’s Harry Joe’s plot:
As John, Jamie, and I have discussed (see also here), the translation from votes to seats is not trivial. Still, if the Republicans really get 54% of the two-party vote or anything close to that, they’re in excellent shape.
Which would not mean that Obama is a lame duck by any means. Recall Reagan in 1982 and 1984.
Not going to happen. I'm willing to put real money behind my view. The electorate has changed and these polls are now as useful as presidential polls this far out (totally useless). The House Democrats will end up about where they were after the 2006 election (plus or minus 5 seats).
Another fun side note is that Professor Gelman came and gave a students only lecture when I took Bafumi's intro stats course.
Good stuff.
If I have the time, I might re-run the model using some of the "alternative" models that take into account different factors such as likely voters. I doubt we see much of a difference.
The democrats definitely are going to have an uphill battle this mid-term. I doubt that these results are to far off, and possibly understate the problem. Research 2000's polls show a serious enthusiasm gap, with the Republican Tea Party movement MUCH more motivated than the liberal base.
There are only really two things that can ameliorate the losses (and there are going to be losses):
1. Pass health care reform and/or other policies that the liberal base wants. This will help close the enthusiasm gap, and fight the perception that the Dems are incapable of getting anything done.
2. Hope the economy gets better. It will get at least somewhat better, but nothing the government does at this point will have any significant effect in time for the elections. All signs point to a slow climb out of a deep hole.
On the other hand, the Iowa Electronic Markets are quite bullish for a Democrat-controlled Congress…
Market Quotes: Congress10
2010 Congressional Control Market.
Quotes current as of 06:00:02 CST, Tuesday, February 23, 2010.
Symbol Bid Ask Last Low High Average
DH_DS10 0.523 0.567 0.580 — — —
DH_RS10 0.031 0.039 0.033 — — —
RH_DS10 0.185 0.242 0.243 — — —
RH_RS10 0.185 0.259 0.241 — — —
DH_DS=Dem House, Dem Senate
DH_RS=Dem House, Rep Senate
RH_DS=Rep House, Dem Senate
RH_RS=Rep House, Rep Senate
"Hope the economy gets better. It will get at least somewhat better, but nothing the government does at this point will have any significant effect in time for the elections. All signs point to a slow climb out of a deep hole."
Ain't gonna happen – there are 8 months, for all practical purposes.
Now, voter enthusiasm is something in the Democratic leadership's power. If Obama is smart, he'll put out a 100% effort over the next 8 months. It's strongly in his interest to minimize GOP gains, unless he'd like to spend the next two years on the defensive.
I guess this is why they hold elections. If we could call the winners using a statistical model and a host of assumptions a couple hundred days out from voting day, we'd save so much time and energy (but miss out on all the fun).