Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | "Scott Mist" <scott.mist@comcast.net> |
To | <statalist@hsphsun2.harvard.edu> |
Subject | st: RE: RE: RE: RE: RE: RE: RE: RE: RE: How to do bootstrap of candisc |
Date | Wed, 17 Mar 2010 15:06:07 -0700 |
Martin, I had just figured that out as your email came in. Thank you so much. This is exactly what I am looking for. Scott -----Original Message----- From: owner-statalist@hsphsun2.harvard.edu [mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of Martin Weiss Sent: Wednesday, March 17, 2010 2:56 PM To: statalist@hsphsun2.harvard.edu Subject: st: RE: RE: RE: RE: RE: RE: RE: RE: How to do bootstrap of candisc <> You probably executed the code from the command line? Run it from the dofile editor. Type -doedit- to open it. See [U], 16.1.2 for an explanation of comments in do-files. Or join the lines now held together by "/* */" in one physical line and then you are good to go from the command line :-) HTH Martin -----Original Message----- From: owner-statalist@hsphsun2.harvard.edu [mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of Scott Mist Sent: Mittwoch, 17. März 2010 22:42 To: statalist@hsphsun2.harvard.edu Subject: st: RE: RE: RE: RE: RE: RE: RE: How to do bootstrap of candisc Martin, Thanks so much. When I used your code, I get this error: . cancorone=r(cancorone) command not found . r(111); I have copied the larger output below. Thanks again, Scott . cap pro drop myprog . . webuse rootstock, clear (Table 6.2 Rootstock Data -- Rencher (2002)) . . . . prog myprog, rclass 1. . vers 11 2. . candisc y1 y2 y3 y4, group(rootstock) 3. . mat A= e(candisc_stat) 4. . ret sca cancorone=A[1,1] 5. . ret sca cancortwo=A[2,1] 6. . mat B=e(L_std) 7. . ret sca stdcoeffone=B[1,1] 8. . ret sca stdcoefftwo=B[2,1] 9. . end . . . . bs cancorone=r(cancorone) /* . cancorone=r(cancorone) command not found . r(111); -----Original Message----- From: owner-statalist@hsphsun2.harvard.edu [mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of Martin Weiss Sent: Wednesday, March 17, 2010 2:28 PM To: statalist@hsphsun2.harvard.edu Subject: st: RE: RE: RE: RE: RE: RE: How to do bootstrap of candisc <> Here is a mechanical way to get at these results and -bs- them. But please bear in mind that I have no idea whether this is appropriate or not. I have never used -candisc- myself. I am only providing technical details here... ************* cap pro drop myprog webuse rootstock, clear prog myprog, rclass vers 11 candisc y1 y2 y3 y4, group(rootstock) mat A= e(candisc_stat) ret sca cancorone=A[1,1] ret sca cancortwo=A[2,1] mat B=e(L_std) ret sca stdcoeffone=B[1,1] ret sca stdcoefftwo=B[2,1] end bs cancorone=r(cancorone) /* */ cancortwo=r(cancortwo) /* */ stdcoeffone=r(stdcoeffone) /* */ stdcoefftwo=r(stdcoefftwo), /* */ reps(20): myprog ************* HTH Martin -----Original Message----- From: owner-statalist@hsphsun2.harvard.edu [mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of Scott Mist Sent: Mittwoch, 17. März 2010 21:04 To: statalist@hsphsun2.harvard.edu Subject: st: RE: RE: RE: RE: RE: How to do bootstrap of candisc Sorry, I didn't use the names from the output but the descriptors. Here are the names: e(candisc_stat) e(L_std) Thanks so much. Scott -----Original Message----- From: owner-statalist@hsphsun2.harvard.edu [mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of Martin Weiss Sent: Wednesday, March 17, 2010 12:37 PM To: statalist@hsphsun2.harvard.edu Subject: st: RE: RE: RE: RE: How to do bootstrap of candisc <> Sure, sorry. Just run my example code and tell me the result in the list you get that you want to -bootstrap-... HTH Martin -----Original Message----- From: owner-statalist@hsphsun2.harvard.edu [mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of Scott Mist Sent: Mittwoch, 17. März 2010 19:41 To: statalist@hsphsun2.harvard.edu Subject: st: RE: RE: RE: How to do bootstrap of candisc Martin, I was wondering if you had any other thoughts on how to do this. Thanks, Scott -----Original Message----- From: owner-statalist@hsphsun2.harvard.edu [mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of Scott Mist Sent: Tuesday, March 16, 2010 4:35 PM To: statalist@hsphsun2.harvard.edu Subject: st: RE: RE: How to do bootstrap of candisc I am interested in reproducing the canonical correlation table including the correlation, eigenvalue and p-values. Scott -----Original Message----- From: owner-statalist@hsphsun2.harvard.edu [mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of Martin Weiss Sent: Tuesday, March 16, 2010 4:27 PM To: statalist@hsphsun2.harvard.edu Subject: st: RE: How to do bootstrap of candisc <> Which result returned by -candisc- do you want to -bootstrap-? See this example from the help file: ************* webuse rootstock, clear candisc y1 y2 y3 y4, group(rootstock) eret li ************* HTH Martin -----Original Message----- From: owner-statalist@hsphsun2.harvard.edu [mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of Scott Mist Sent: Dienstag, 16. März 2010 23:47 To: statalist@hsphsun2.harvard.edu Subject: st: How to do bootstrap of candisc Hello all, I am working on doing a bootstrap of a candisc analysis with a small sample size. I am trying to figure out how sensitive the two functions are to the cases in the study. I am hoping to say that this is relatively stable. As such, I am trying to figure out what the distributions of significances are for each of the functions. Does anyone know how to capture this? Thanks, Scott Scott D. Mist, PhD, MAcOM, MS, MA Senior Research Associate & Post Doctoral Fellow Fibromyalgia Research Group Oregon Center for Complementary and Alternative Medicine in Neurological Disorders Schools of Nursing and Medicine Oregon Health & Science University * * For searches and help try: * http://www.stata.com/help.cgi?search * http://www.stata.com/support/statalist/faq * http://www.ats.ucla.edu/stat/stata/ * * For searches and help try: * http://www.stata.com/help.cgi?search * http://www.stata.com/support/statalist/faq * http://www.ats.ucla.edu/stat/stata/ * * For searches and help try: * http://www.stata.com/help.cgi?search * http://www.stata.com/support/statalist/faq * http://www.ats.ucla.edu/stat/stata/ * * For searches and help try: * http://www.stata.com/help.cgi?search * http://www.stata.com/support/statalist/faq * http://www.ats.ucla.edu/stat/stata/ * * For searches and help try: * http://www.stata.com/help.cgi?search * http://www.stata.com/support/statalist/faq * http://www.ats.ucla.edu/stat/stata/ * * For searches and help try: * http://www.stata.com/help.cgi?search * http://www.stata.com/support/statalist/faq * http://www.ats.ucla.edu/stat/stata/ * * For searches and help try: * http://www.stata.com/help.cgi?search * http://www.stata.com/support/statalist/faq * http://www.ats.ucla.edu/stat/stata/ * * For searches and help try: * http://www.stata.com/help.cgi?search * http://www.stata.com/support/statalist/faq * http://www.ats.ucla.edu/stat/stata/ * * For searches and help try: * http://www.stata.com/help.cgi?search * http://www.stata.com/support/statalist/faq * http://www.ats.ucla.edu/stat/stata/ * * For searches and help try: * http://www.stata.com/help.cgi?search * http://www.stata.com/support/statalist/faq * http://www.ats.ucla.edu/stat/stata/