If you stick to the solely aggregate analysis, you can avoid ecological
inference altogether. This won't work (for good reasons) with your
reviewers, but here's how it would work: you'd say that %indigenous
causes %voting. you'd then be indifferent between (a) the indigenous
people voting for the indigenous candidate and (b) and the nonindigenous
people who happen to live in areas with lots of indigenous people are the
ones voting for the indigenous candidate (controlling for the other
variables in your regression). This would be fine, but the different
stories here are pretty massive in most applications. So what you might
do is to first do your analysis and explicitly say that, since you're not
doing ecological inference, you can't distinguish between (a) and (b).
And so you would then move to a method of ecological inference to
distinguish between the two.
Best of luck with your research,
Gary
: Gary King, King(a)Harvard.Edu http://GKing.Harvard.Edu :
: Center for Basic Research Direct (617) 495-2027 :
: in the Social Sciences Assistant (617) 495-9271 :
: 34 Kirkland Street, Rm. 2 HU-MIT DC (617) 495-4734 :
: Harvard U, Cambridge, MA 02138 eFax (928) 832-7022 :
I think the way I'd present it if I were you
On Wed, 20 Nov 2002, Beck, Scott H. wrote:
> Professor King:
>
> My colleague, Ken Mijeski (a political scientist) and I (sociology)
> have been analyzing election data from Ecuador the past few years. This
> is aggregate data in that the voting results and other variables are
> only available at the level of the county (in Spanish, canton). One
> primary issue we have dealt with in our analyses concerns whether
> indigenous voters (Indians) in Ecuador more often vote for candidates
> sponsored by the indigenous political party. Using the aggregate data,
> we ran correlations and regressions and not surprisingly found that in
> almost all cases there is a substantial positive correlation between the
> %Indigenous in a county and the %Voting for Indigenous Party Candidate.
> So, the possibility of the ecological fallacy raises its very ugly head
> and journal reviewers are quick to jump on the conclusion that
> indigenous voters much more often vote for those candidates (since we
> know quite a lot about Ecuador and its politics we don't feel that the
> alternative hypothesis, i.e., non-indigenous voters in counties with
> higher proportions of indigenous people much more often vote for
> indigenous party candidates). So, we have been told to learn and then
> use your innovative method of estimating and then inferring the
> proportions of indigenous (black) and non-indigenous (white) who vote
> for candidate x. Though our aging brains struggled through your book
> (despite your clear exegesis) and we have downloaded EZi and used it, we
> think, successfully (at least we can understand most of the output).
> That output backs up our original conclusion - a higher proportion of
> indigenous voters voted for indigenous party candidates than did
> non-indigenous voters.
>
> Our question is this: can we properly use the results of your
> method as a verification technique of the hypothesis, and once verified,
> go back to our previous line of analysis where we are more interested in
> the size of the correlation (standardized beta) between %Indigenous and
> %Voting for Indigenous Party candidate, including OLS multiple
> regression where we introduce "control variables" to determine whether
> the net effect of %Indigenous remains intact? That is, our interest
> ultimately is more of a causal analysis at the aggregate level where
> competing factors, such as poverty rate and illiteracy rate at the
> county level, can be taken into account.
>
> Your answer to this issue would be greatly appreciated and we thank
> you in advance.
>
> Scott Beck
>
>
-
EI mailing list served by Harvard-MIT Data Center
Subscribe/Unsubscribe: http://lists.hmdc.harvard.edu/?info=ei
We offer you e-mail addresses databases for advertisement
mailing; we sell databases also carry out mailing and hosting
for the advertising projects.
We can work on a turnkey project create a site with original design,
program and subject contents. Our databases updates constantly
with the e-mail addresses from all over the world.
Their validity and originality are verified. Today they contains over
than 50 million addresses.
We use our own mailing soft which can be ideally adjusted for every
customer. We have a high-speed channel and a high power server.
The constant of our service demand allows us to keep low prices.
http://www.e-mailpromo.net
Please don't hesitate to contact us anytime!
We'll be happy to answer every your question!
HTTP: www.e-mailpromo.net
E-mail: info(a)e-mailpromo.net
We received your address from a public area.
We apologize if this letter has reached you by mistake.
We'll not disturb you any more.
NB. This message is sent in compliance with the new e-mail bill section
301. Under Bill S. 1618 TITLE III passed by the 105th US Congress.
This message can not be considered as Spam as long as we include the way
to be Removed, Paragraph (a)(c) of S. 1618.
TO REMOVE YOUR ADDRESS FROM YOUR MAILING LIST: you can send message to
info(a)e-mailpromo.net with Subject "Remove".
-
EI mailing list served by Harvard-MIT Data Center
Subscribe/Unsubscribe: http://lists.hmdc.harvard.edu/?info=ei
_EisFac=-2 is not normally harmful, so the first message is ok.
but what do you mean that they didn't work? What was the error message?
Gary King
: Gary King, King(a)Harvard.Edu http://GKing.Harvard.Edu :
: Center for Basic Research Direct (617) 495-2027 :
: in the Social Sciences Assistant (617) 495-9271 :
: 34 Kirkland Street, Rm. 2 HU-MIT DC (617) 495-4734 :
: Harvard U, Cambridge, MA 02138 eFax (928) 832-7022 :
On Sun, 10 Nov 2002, Liu wrote:
> Hi Dr. King,
>
> My name is Baodong Liu, and I work at the University of Wisconsin-Oshkosh
> as an assistant professor of political science. I have used your Ezi for
> more than four years, with four publications by using your method of
> ecological inference. I would like to thank you for your continuing effort
> in furthering research by using aggregate data.
>
> I also would also like to ask you a question about the operation of Ezi. I
> was using Memphis 1991 mayoral election data today and ran Ezi on my Window
> 2000 Profession platform. The file has 245 observations (precincts). I was
> able to run Ei1, but whenever I tried Ei2, the screen bombed and
> disappeared. I tried to read through your manual and the book to find a
> solution, but I failed except that I saw the following message on the
> screen before the program was stopped:
>
> "...
> Importance sampling failed! Using maximum posterior estimates
> <equivalent to _EisFac=-2>.
> Simulating fundamental variability..."
>
> After I saw this, I went to configuration function and changed the _EisFac
> to -2, but it didn't work. As a matter of fact, I tried -1, 0, and 2. None
> of them worked.
>
> Is there any solution to this? If you want, I can send you the datafile.
>
> Thank you for your time.
>
> Sincerely,
>
> Baodong Liu
>
-
EI mailing list served by Harvard-MIT Data Center
Subscribe/Unsubscribe: http://lists.hmdc.harvard.edu/?info=ei
Further to my previous post re priors, I wonder if any one has further
advice on setting priors, specifically the priors on phi. King
pp.136-139/_EdoML etc
I have used reported values for phi from a default run, but have not
found that this improves my estimates.
I am also uncertain as to how _Erho and _Esigma differ from the values
for variance and rho in _EdoML.
Any advice or tips would be much appreciated.
Linda
Linda Moore
Graduate Student
University of Canterbury
Christchurch
New Zealand
lmm72(a)student.canterbury.ac.nz
-
EI mailing list served by Harvard-MIT Data Center
Subscribe/Unsubscribe: http://lists.hmdc.harvard.edu/?info=ei