On Tuesday, February 14, 2012 at 9:32 AM, Prashant wrote:
I'm sorry for sending another e-mail -- one correction to my previouspost is that the hometown01 variable is categorical -- and thecategories are in Chinese characters -- perhaps this is a reason whyimb is having difficulty.thank you again,PrashantOn Tue, Feb 14, 2012 at 10:29 PM, Prashant <presearchwork@gmail.com> wrote:Hi Matt,Thank you kindly for the quick reply -- I later tried with differentcombinations of variables and found that the imb command works aftertaking out the binary variable "hometown01". The cem command workseven when it (or any combination of variables) is included. Does ithave to do with the ~15% missing values in hometown01 perhaps?Thank you for all of your help!PrashantOn Tue, Feb 14, 2012 at 10:18 PM, Matt Blackwell<blackwel@fas.harvard.edu> wrote:Hi Prashant,Have you tried running the imb function on a smaller set of the variables?The `cem` command calls imbalance at some point, so this should work.Another quick potential solution is to reinstall the CEM package and see ifthat fixes the issue.Hope that helps!Cheers,matt.~~~~~~~~~~~Matthew BlackwellPhD CandidateInstitute for Quantitative Social ScienceDepartment of GovernmentHarvard UniversityOn Tuesday, February 14, 2012 at 5:59 AM, Prashant wrote:Hi,I'm get an error message when I run imb in Stata (cem runs fine):L1meas(): 3301 subscript invalidimbalance(): - function returned error<istmt>: - function returned errorr(3301);My code is something like:imb new_age borninbeijing female hometown01 BJ_hukou Rural_hukoutypefatheredu motheredu ifpreschooling schoolingathome,treatment(public_yn)Any help would be most appreciated!Thanks,Prashant---cem Mailing List, served by HUITSend messages: cem@lists.gking.harvard.edu[un]subscribe Options: http://lists.gking.harvard.edu/?info=cemMore information on cem: http://gking.harvard.edu/cemCem mailing list