Shige, One of the priorities of 4.2 is to handle all issues with missing data correctly. These include [1] combining results by Rubin's rules when summarizing the model result [2] creating graphs of quantities of interest by drawing from each imputed dataset [3] handling missing values in setx() [4] not interfering with the Amelia namespace, and integrating correctly with ameliabind(), mi.meld(). The current posted Beta of 4.2 handles issues 1&2, and will address 3&4 shortly. These are all issues that have been brought up on the list repeatedly, and while it's very useful in my present position to be able to read through the examples the list has provided, I'm sure it is frustrating that these issues have been present for several months. (Going over the list, as I have been working on this the last several weeks, I've found your bug reports, Shige, very useful. If I don't close all of the threads you have started, directly, it's because I don't want to overwhelm the list with a flurry of issue resolved reports, rather than because they are ignored.) Thanks, James. -- James Honaker, Senior Research Scientist //// Institute for Quantitative Social Science, Harvard University ________________________________ From: zelig-bounces(a)lists.gking.harvard.edu [zelig-bounces(a)lists.gking.harvard.edu] on behalf of Shige Song [shigesong(a)gmail.com] Sent: Friday, May 31, 2013 3:00 PM To: Zelig mailing list Subject: [zelig] Zelig 4.20 with multiply imputed data I see now Zelig 4.20 is in beta. Does it handle results based on multiply imputed data correctly? That is, does it output the combined results (as in Zelig 3) instead of a set of individual results (as in early version of Zelig 4)? Best, Shige