Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | Bobby Jo otto <bobbyjootto@gmail.com> |
To | statalist@hsphsun2.harvard.edu |
Subject | st: Multiple Imputation |
Date | Thu, 15 Aug 2013 14:53:08 -0400 |
Hello, I have a question regarding multiple imputation. I conducted multiple imputation in SPSS and then transferred the data back to Stata. After the imputation, my n=88,800, which includes the original data set plus the 5 imputations. When I delete the original values (drop in 1/14,800) I'm left with a sample size of 74,000. My problem however, is that when I set Stata to recognize that my data is imputed (mi set flong; mi set M=5), it multiplies 74,000 by 6 which then gives me a sample size of 444,000 (each imputed data set is multiplied by 6). Thus, each specific respondent has data 30 different times. Example of data set: (up to 30) imputation_ aid 1 111111 1 111111 5 111111 4 111111 4 111111 3 111111 4 111111 1 111111 2 111111 Can anyone tell me exactly what I am doing wrong? Thanks in advance! * * For searches and help try: * http://www.stata.com/help.cgi?search * http://www.stata.com/support/faqs/resources/statalist-faq/ * http://www.ats.ucla.edu/stat/stata/