Hi Gary,
I've commented out this bit here:
boot.good <- !(any(colMeans(commD0[, -1]) ==
1) || any(colMeans(commD0[, -1]) == 0) ||
any(colMeans(hospD0[,
-1]) == 1) || any(colMeans(hospD0[, -1]) ==
0))
and just set boot.good <- T
and it seems to be running without a hitch now. I'm not sure what that
would say about my data set...
- A
On 05/25/2012 10:14 AM, Gary King wrote:
Hi Alex, I'm not sure what the issue is, but it
works by
bootstrapping. so you can experiment by taking a bootstrapped sample
yourself and then feeding it into readme and the repeating. there
may be something wrong with your data set. but it may well be just
taking a long time, which could definitely be the case. readme
involves simulation for even one run, and then that whole thing is
being bootstrapped many times.
Gary
--
*Gary King*- Albert J. Weatherhead III University Professor -
Director, IQSS <http://iq.harvard.edu>- Harvard University
GKing.Harvard.edu <http://gking.harvard.edu/>-King@Harvard.edu
<mailto:King@Harvard.edu>- @kinggary <http://twitter.com/kinggary>-
617-500-7570 - Asst 495-9271 - Fax 812-8581
On Tue, May 22, 2012 at 6:47 PM, Alex Hanna <ahanna(a)ssc.wisc.edu
<mailto:ahanna@ssc.wisc.edu>> wrote:
Hello,
I'm having some trouble generating bootstrap standard errors for
my dataset. It works fine for the demo, but as soon as I use my
data it sticks and doesn't want to generate them. I think the
offending piece of code is in the VA function, probably this part:
while (!boot.good && boot.se <http://boot.se>) {
index.boot1 <- sample(1:p1, p1, replace = TRUE)
index.boot2 <- sample(1:p2, p2, replace = TRUE)
commD0 <- commD[index.boot1, ]
hospD0 <- hospD[index.boot2, ]
print(commD0)
boot.good <- !(any(colMeans(commD0[, -1]) ==
1) || any(colMeans(commD0[, -1]) == 0) ||
any(colMeans(hospD0[,
-1]) == 1) || any(colMeans(hospD0[, -1]) ==
0))
}
For whatever reason, I don't think it's ever setting boot.good to
TRUE and is stuck in an infinite loop. I'm not sure what
conditions would lead that to happen, especially since
preprocessing takes out all the invariant columns anyhow.
Any advice here would be very appreciated.
TIA,
- A
--
Alexander Hanna
PhD student, Department of Sociology
University of Wisconsin-Madison
http://alex-hanna.com
-
---
readme mailing list served by HUIT
List Address: readme(a)lists.gking.harvard.edu
<mailto:readme@lists.gking.harvard.edu>
Subscribe/Unsubscribe:
http://lists.gking.harvard.edu/mailman/listinfo/readme
More info about the program:
http://gking.harvard.edu/readme
Readme mailing list
Readme(a)lists.gking.harvard.edu <mailto:Readme@lists.gking.harvard.edu>
https://lists.gking.harvard.edu/mailman/listinfo/readme
--
Alexander Hanna
PhD student, Department of Sociology
University of Wisconsin-Madison