multiple imputation procedure within spss

[msherman]

Dear list:  First time user of SPSS’s multiple imputation procedure.  After running this procedure the output generate provides data sets for each imputation. Thus, if I requested 10 imputations I obtained 10 different data sets with imputation values for those that were missing data points. Although It seems like one could simply get the average of all of the imputed values for those folks with missing values SPSS does not create a new data set with the average values or any measures of error associated with the imputed values. I would be curious to know what other folks have done using spss after they have run the multiple imputation procedure.    martin

 

Martin F. Sherman, Ph.D.

Professor of Psychology

Director of  Masters Education in Psychology: Thesis Track

 

Loyola University Maryland

Department of Psychology

222 B Beatty Hall

4501 North Charles Street

Baltimore, MD 21210

 

410-617-2417

[hidden email]

 

[Jon K Peck]

The point of multiple imputation is to avoid collapsing the data so that the procedures can handle the uncertainty correctly.  The enabled procedures will give you the corrected summaries.

Jon Peck (no "h")
Senior Software Engineer, IBM
[hidden email]
new phone: [phone]




From:        Martin Sherman <[hidden email]>
To:        [hidden email]
Date:        08/24/2011 09:41 AM
Subject:        [SPSSX-L] multiple imputation procedure within spss
Sent by:        "SPSSX(r) Discussion" <[hidden email]>

---

Dear list:  First time user of SPSS’s multiple imputation procedure.  After running this procedure the output generate provides data sets for each imputation. Thus, if I requested 10 imputations I obtained 10 different data sets with imputation values for those that were missing data points. Although It seems like one could simply get the average of all of the imputed values for those folks with missing values SPSS does not create a new data set with the average values or any measures of error associated with the imputed values. I would be curious to know what other folks have done using spss after they have run the multiple imputation procedure.    martin
 
Martin F. Sherman, Ph.D.
Professor of Psychology
Director of  Masters Education in Psychology: Thesis Track
 
Loyola University Maryland
Department of Psychology
222 B Beatty Hall
4501 North Charles Street
Baltimore, MD 21210
 
410-617-2417
msherman@...
 

[Alex Reutter]

Hi Martin,

Certain procedures recognize when you are working with multiply imputed data and produce output appropriate to that fact.  There is a list of procedures that work with multiply imputed data in the documentation.  You definitely don't want a simple average of the imputed values.

Alex




From:        Martin Sherman <[hidden email]>
To:        [hidden email]
Date:        08/24/2011 10:36 AM
Subject:        multiple imputation procedure within spss
Sent by:        "SPSSX(r) Discussion" <[hidden email]>

---

Dear list:  First time user of SPSS’s multiple imputation procedure.  After running this procedure the output generate provides data sets for each imputation. Thus, if I requested 10 imputations I obtained 10 different data sets with imputation values for those that were missing data points. Although It seems like one could simply get the average of all of the imputed values for those folks with missing values SPSS does not create a new data set with the average values or any measures of error associated with the imputed values. I would be curious to know what other folks have done using spss after they have run the multiple imputation procedure.    martin
 
Martin F. Sherman, Ph.D.
Professor of Psychology
Director of  Masters Education in Psychology: Thesis Track
 
Loyola University Maryland
Department of Psychology
222 B Beatty Hall
4501 North Charles Street
Baltimore, MD 21210
 
410-617-2417
msherman@...
 

[Bruce Weaver]

Martin, you might want to read some of the following good articles that explain how pooled estimates are computed (using a method due to Rubin).  The "fine manual" might also be instructive.

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/ 

Rubin, D. B. (1987). Multiple imputation for survey nonresponse. New York: Wiley.

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. Psychological Methods, 7(2), 147-177.

msherman wrote

Dear list:  First time user of SPSS's multiple imputation procedure.  After running this procedure the output generate provides data sets for each imputation. Thus, if I requested 10 imputations I obtained 10 different data sets with imputation values for those that were missing data points. Although It seems like one could simply get the average of all of the imputed values for those folks with missing values SPSS does not create a new data set with the average values or any measures of error associated with the imputed values. I would be curious to know what other folks have done using spss after they have run the multiple imputation procedure.    martin

Martin F. Sherman, Ph.D.
Professor of Psychology
Director of  Masters Education in Psychology: Thesis Track

Loyola University Maryland
Department of Psychology
222 B Beatty Hall
4501 North Charles Street
Baltimore, MD 21210

410-617-2417
[hidden email]<mailto:[hidden email]>