Hi All,
Can someone please provide me with the equation for
exact matching? For example suppose I have two treatment cases
and 4 control cases and there is one covariate (X), where X=0,1. Suppose
that the treatment and control cases match exactly on X=1, how does
exact matching match the cases?
My reasoning is that it will match treatment case 1 to the 4 control
cases
and treatment case 2 also to the four control cases. Therefore you have
two subclasses with a total of 10 cases. Am I correct?
George
--
MatchIt mailing list served by Harvard-MIT Data Center
List Address: matchit(a)lists.gking.harvard.edu
Subscribe/Unsubscribe: http://lists.gking.harvard.edu/?info=matchit
MatchIt Software and Documentation: http://gking.harvard.edu/matchit/
Browse/Search List Archive: http://lists.hmdc.harvard.edu/lists/matchit/
Thanks. That's a typo. It should be
s.out0 <- sim(z.out, x = x.out0, x1 = x.out1)
We will fix the typo in the next release.
Thanks,
Kosuke
Department of Politics
Princeton University
http://imai.princeton.edu
On Sep 7, 2010, at 1:58 PM, Mcnary, Scot W. wrote:
> Kosuke,
>
> I'm looking at the same pdf:
>
> http://gking.harvard.edu/matchit/docs/matchit.pdf
>
> Sorry about my typing error. I'm confused about the objects z.out1 and x.out1 the top of page 17 in the third line of code on that page that reads:
>
>> s.out0 <- sim(z.out1, x = x.out1)
>
> I don't see where z.out1 and x.out1 were created.
>
> Just a suggestion: if you prefer questions be routed to the mailing list, please indicate this in the package maintainer contact information in:
>
> help(package = "MatchIt")
>
> Scot
>
> -----Original Message-----
> From: Kosuke Imai [mailto:kimai@Princeton.EDU]
> Sent: Sunday, September 05, 2010 7:26 AM
> To: Mcnary, Scot W.
> Cc: matchit(a)lists.gking.harvard.edu
> Subject: Re: matchit.pdf p. 17
>
> Please ask your questions on the mailing list from now on. I'm ccing this message to the mailing list:
>
> Do you have the latest version of MatchIt? I'm looking at http://gking.harvard.edu/matchit/docs/matchit.pdf but I don't see any z.out.1 etc. on page 17.
>
> Kosuke
>
> Department of Politics
> Princeton University
> http://imai.princeton.edu
>
> On Sep 4, 2010, at 11:08 AM, Mcnary, Scot W. wrote:
>
>> Hi,
>>
>> I'm using the MatchIt package for some analyses I'm running and finding it very useful. I have both the matchit.pdf and the cem.pdf references open to work through examples. I'm confused about p. 17 in the matchit.pdf. At the top of the page, there are four lines of code that describe using the Zelig package setx() function and the sim() function. In the third line, the sim() function refers to objects z.out.1 and x.out.1, but I don't see where those were generated. Should the line instead read:
>>
>> s.out0 <- sim(z.out0, x = x.out0)
>>
>> for the control group? The bottom of page 17 looks as though that might be the intent.
>>
>> Thanks,
>>
>> Scot McNary
>>
>> Scot W. McNary Ph.D.
>> Assistant Professor EDLT/COE
>> Towson University, Towson MD 21252
>> smcnary(a)towson.edu 410 704 4835
>>
>>
>
>
>
--
MatchIt mailing list served by Harvard-MIT Data Center
List Address: matchit(a)lists.gking.harvard.edu
Subscribe/Unsubscribe: http://lists.gking.harvard.edu/?info=matchit
MatchIt Software and Documentation: http://gking.harvard.edu/matchit/
Browse/Search List Archive: http://lists.hmdc.harvard.edu/lists/matchit/
Please ask your questions on the mailing list from now on. I'm ccing this message to the mailing list:
Do you have the latest version of MatchIt? I'm looking at http://gking.harvard.edu/matchit/docs/matchit.pdf but I don't see any z.out.1 etc. on page 17.
Kosuke
Department of Politics
Princeton University
http://imai.princeton.edu
On Sep 4, 2010, at 11:08 AM, Mcnary, Scot W. wrote:
> Hi,
>
> I’m using the MatchIt package for some analyses I’m running and finding it very useful. I have both the matchit.pdf and the cem.pdf references open to work through examples. I’m confused about p. 17 in the matchit.pdf. At the top of the page, there are four lines of code that describe using the Zelig package setx() function and the sim() function. In the third line, the sim() function refers to objects z.out.1 and x.out.1, but I don’t see where those were generated. Should the line instead read:
>
> s.out0 <- sim(z.out0, x = x.out0)
>
> for the control group? The bottom of page 17 looks as though that might be the intent.
>
> Thanks,
>
> Scot McNary
>
> Scot W. McNary Ph.D.
> Assistant Professor EDLT/COE
> Towson University, Towson MD 21252
> smcnary(a)towson.edu 410 704 4835
>
>
--
MatchIt mailing list served by Harvard-MIT Data Center
List Address: matchit(a)lists.gking.harvard.edu
Subscribe/Unsubscribe: http://lists.gking.harvard.edu/?info=matchit
MatchIt Software and Documentation: http://gking.harvard.edu/matchit/
Browse/Search List Archive: http://lists.hmdc.harvard.edu/lists/matchit/