2
$\begingroup$

I am looking for applied references to data augmentation (preferably with some written code). Either online references are books would be great.

I found this book online:

http://www.amazon.com/Bayesian-Missing-Data-Problems-Biostatistics/dp/142007749X/ref=sr_1_1?ie=UTF8&s=books&qid=1291905761&sr=1-1

But with no reviews I am hesitant on purchasing it.

Thanks!

Edit: I have two variables X and Y. Let's say X follows a mixture of normals and there is a logistic relationship between X and Y. There is measurement error when observing X. We observe 100 X Y pairs and need to estimate the function between the two.

In a book on measurement error (John P. Buonaccorsi) the author recommends data augmentation (I believe the introduced variables are the true X means) for estimation. However no details are given. I am looking for simple examples (R code but doesn't really matter) to get started.

$\endgroup$
  • 3
    $\begingroup$ The Art of Data Augmentation, by van Dyk and Meng may be a good start. I also quickly found some R examples on Bayesian statistics on Peter M. Lee and Brian Neelon's websites. But I guess you can find other good tutorials with Google, or a more experienced user will have some good recommendations to offer. $\endgroup$ – chl Dec 9 '10 at 15:25
  • $\begingroup$ Great thanks. Anyone know of a good book/textbook reference? $\endgroup$ – Glen Dec 9 '10 at 16:35
  • $\begingroup$ Maybe you could add some info about its intended use and the target language . $\endgroup$ – chl Dec 9 '10 at 22:12
5
$\begingroup$

The Art of Data Augmentation, by van Dyk and Meng may be a good start. I also quickly found some R examples on Bayesian statistics on Peter M. Lee and Brian Neelon's websites. But I guess you can find other good tutorials with Google, or a more experienced user will have some good recommendations to offer.

Originally an upvoted comment by chl

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.