Main Page | Report this Page
 
Loading..
   
Science Forum Index  »  Statistics - Education Forum  »  Missing Data
Page 1 of 1    
Author Message
Gary
Posted: Wed Feb 06, 2008 3:17 am
Guest
A general question. How should stats software be programmed to
implement routines for missing data? Ideally the user should know what
the routines are doing so they shouldn't be automatic. But perhaps the
user ought to be advised, offered various options? In other words, if
you were writing a new program for general statistical analysis how
would you implement routines for handling missing data? What routines
would you include? And why?

There are some rather nice sources for treating missing data:

http://www.lcgceurope.com/lcgceurope/data/articlestandard/lcgceurope/502001/4509/article.pdf

http://www.uvm.edu/~dhowell/StatPages/More_Stuff/Missing_Data/Missing.html

Perhaps there are other good ones out there.

Lance
Back to top
Bruce Weaver
Posted: Wed Feb 06, 2008 4:57 am
Guest
On Feb 6, 8:17 am, Gary <LanceG...@gmail.com> wrote:
Quote:
A general question. How should stats software be programmed to
implement routines for missing data? Ideally the user should know what
the routines are doing so they shouldn't be automatic. But perhaps the
user ought to be advised, offered various options? In other words, if
you were writing a new program for general statistical analysis how
would you implement routines for handling missing data? What routines
would you include? And why?

There are some rather nice sources for treating missing data:

http://www.lcgceurope.com/lcgceurope/data/articlestandard/lcgceurope/...

http://www.uvm.edu/~dhowell/StatPages/More_Stuff/Missing_Data/Missing...

Perhaps there are other good ones out there.

Lance


Here are some articles (and a website) that I've found useful.

Acock, A. C. (2005). Working with missing values. Journal of Marriage
and Family, 67, 1012-1028.

Donders, A. Rogier T., van der Heijden, Geert J.M.G., Stijnen, T., &
Moons, K. G. M. (2006). Review: A gentle introduction to imputation of
missing values. Journal of Clinical Epidemiology, 59, 1087-1091.

Multiple Imputation Online. http://www.multiple-imputation.com/

Schafer, J. L. (1999). Multiple imputation: A primer. Statistical
Methods in Medical Research, 8, 3-15.

Schafer, J. L., & Graham, J. W. (2002). Missing data: Our view of the
state of the art. Psychosomatic Medicine, 7(2), 147-177.

von Hippel, Paul T. (2004). Biases in SPSS 12.0 missing value
analysis. The American Statistician, 58(2), 160-164.

--
Bruce Weaver
bweaver@lakeheadu.ca
www.angelfire.com/wv/bwhomedir
"When all else fails, RTFM."
Back to top
Ray Koopman
Posted: Wed Feb 06, 2008 5:23 am
Guest
On Feb 6, 5:17 am, Gary <LanceG...@gmail.com> wrote:
Quote:
A general question. How should stats software be programmed to
implement routines for missing data? Ideally the user should know what
the routines are doing so they shouldn't be automatic. But perhaps the
user ought to be advised, offered various options? In other words, if
you were writing a new program for general statistical analysis how
would you implement routines for handling missing data? What routines
would you include? And why?

There are some rather nice sources for treating missing data:

http://www.lcgceurope.com/lcgceurope/data/articlestandard/lcgceurope/...

http://www.uvm.edu/~dhowell/StatPages/More_Stuff/Missing_Data/Missing...

Perhaps there are other good ones out there.

Lance

http://division.aomonline.org/rm/1999_RMD_Forum_Missing_Data.htm
is a little dated now but makes a distinction that is still worth
recognizing.
Back to top
Guest
Posted: Wed Feb 06, 2008 5:23 am
In article <88328f01-747f-4693-9bd5-ac8bd56e8415@e10g2000prf.googlegroups.com>,
Bruce Weaver <bweaver@lakeheadu.ca> writes:
Quote:
...
Here are some articles (and a website) that I've found useful.
...
Schafer, J. L., & Graham, J. W. (2002). Missing data: Our view of the
state of the art. Psychosomatic Medicine, 7(2), 147-177.

The journal is "Psychological Methods" (very good survey article!)
--
J.E.H.Shaw [Ewart Shaw] strgh@uk.ac.warwick TEL: +44 2476 523069
Department of Statistics, University of Warwick, Coventry CV4 7AL, UK
http://www.warwick.ac.uk/statsdept http://www.ewartshaw.co.uk
3 ((4&({*.(=+/))++/=3Smile@([:,/0&,^Sadi.3)@|:"2^:2))&.>@]^Sadi.@[) <#:3 6 2
Back to top
Bruce Weaver
Posted: Wed Feb 06, 2008 5:51 am
Guest
On Feb 6, 10:23 am, st...@mimosa.csv.warwick.ac.uk () wrote:
Quote:
In article <88328f01-747f-4693-9bd5-ac8bd56e8...@e10g2000prf.googlegroups.com>,
Bruce Weaver <bwea...@lakeheadu.ca> writes:

...
Here are some articles (and a website) that I've found useful.
...
Schafer, J. L., & Graham, J. W. (2002). Missing data: Our view of the
state of the art. Psychosomatic Medicine, 7(2), 147-177.

The journal is "Psychological Methods" (very good survey article!)


Indeed it is! Good catch, Ewart. Thanks.

--
Bruce Weaver
bweaver@lakeheadu.ca
www.angelfire.com/wv/bwhomedir
"When all else fails, RTFM."
Back to top
Gary
Posted: Wed Feb 06, 2008 10:52 pm
Guest
On Feb 6, 5:51 pm, Bruce Weaver <bwea...@lakeheadu.ca> wrote:
Quote:
On Feb 6, 10:23 am, st...@mimosa.csv.warwick.ac.uk () wrote:

In article <88328f01-747f-4693-9bd5-ac8bd56e8...@e10g2000prf.googlegroups.com>,
        Bruce Weaver <bwea...@lakeheadu.ca> writes:

...
Here are some articles (and a website) that I've found useful.
...
Schafer, J. L., & Graham, J. W. (2002). Missing data: Our view of the
state of the art. Psychosomatic Medicine, 7(2), 147-177.

The journal is "Psychological Methods" (very good survey article!)

Indeed it is!  Good catch, Ewart.  Thanks.

--
Bruce Weaver
bwea...@lakeheadu.cawww.angelfire.com/wv/bwhomedir
"When all else fails, RTFM."

Thanks for the references and web sites. Much appreciated.

Anyone got any suggestions as to how missing data procedures should be
implemented?

Lance
Back to top
Richard Ulrich
Posted: Sat Feb 09, 2008 12:03 am
Guest
On Thu, 7 Feb 2008 00:52:49 -0800 (PST), Gary <LanceGary@gmail.com>
wrote:

[snip, previous]
Quote:

Thanks for the references and web sites. Much appreciated.

Anyone got any suggestions as to how missing data procedures should be
implemented?

- with plenty of options for the user, so that the user
*knows* that there were plenty of options that were not used?

"With humility"?

What kind of answer did you expect?

--
Rich Ulrich

http://www.pitt.edu/~wpilib/index.html
Back to top
Gary
Posted: Sat Feb 09, 2008 12:06 am
Guest
On Feb 9, 6:03 am, Richard Ulrich <Rich.Ulr...@comcast.net> wrote:
Quote:
On Thu, 7 Feb 2008 00:52:49 -0800 (PST), Gary <LanceG...@gmail.com
wrote:

[snip, previous]



Thanks for the references and web sites. Much appreciated.

Anyone got any suggestions as to how missing data procedures should be
implemented?

 - with plenty of options for the user, so that the user
*knows*  that there were plenty of options that were not used?

"With humility"?

What kind of answer did you expect?

--
Rich Ulrich

http://www.pitt.edu/~wpilib/index.html

Oh I was thinking of a discussion in another forum about how missing
data procedures should be implemented...

Thanks

lance
Back to top
 
Page 1 of 1       All times are GMT - 5 Hours
The time now is Mon Oct 13, 2008 2:07 am
Science Forum Index

Powered by phpBB & ML | Disclaimer



Contact Us