Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: st: matrix problem


From   Richard Goldstein <[email protected]>
To   [email protected]
Subject   Re: st: matrix problem
Date   Wed, 15 May 2013 11:16:52 -0400

Roger,

here is an example using the auto data:

. regress mpg price foreign

. predict yhat
(option xb assumed; fitted values)
r; t=0.00 11:15:19

. somersd mpg yhat, transf(c)
Somers' D with variable: mpg
Transformation: Harrell's c
Valid observations: 74

Symmetric 95% CI for Harrell's c
------------------------------------------------------------------------------
             |              Jackknife
         mpg |      Coef.   Std. Err.      z    P>|z|     [95% Conf.
Interval]
-------------+----------------------------------------------------------------
        yhat |   .7759969   .0340637    22.78   0.000     .7092333
.8427604
------------------------------------------------------------------------------
r; t=0.09 11:15:29

. return li

scalars:
              r(level) =  95

matrices:
              r(table) :  9 x 1
r; t=0.00 11:15:35

. mat list r(table)

r(table)[9,1]
             yhat
     b  .77599687
    se  .03406367
     z   22.78078
pvalue  7.11e-115
    ll  .70923332
    ul  .84276043
    df          .
  crit   1.959964
 eform          0
r; t=0.00 11:15:45

. which somersd
/Users/rich/Library/Application Support/Stata/ado/plus/s/somersd.ado
*! Author: Roger Newson
*! Date: 30 May 2012

Rich


On 5/15/13 11:10 AM, Roger B. Newson wrote:
> I do not recall that -somersd- (an -eclass-command) produces a matrix
> result -r(table)-. What program did you use to produce -r(table)-, and
> how did you do this?
> 
> Best wishes
> 
> Roger
> 
> Roger B Newson BSc MSc DPhil
> Lecturer in Medical Statistics
> Respiratory Epidemiology and Public Health Group
> National Heart and Lung Institute
> Imperial College London
> Royal Brompton Campus
> Room 33, Emmanuel Kaye Building
> 1B Manresa Road
> London SW3 6LR
> UNITED KINGDOM
> Tel: +44 (0)20 7352 8121 ext 3381
> Fax: +44 (0)20 7351 8322
> Email: [email protected]
> Web page: http://www.imperial.ac.uk/nhli/r.newson/
> Departmental Web page:
> http://www1.imperial.ac.uk/medicine/about/divisions/nhli/respiration/popgenetics/reph/
> 
> 
> Opinions expressed are those of the author, not of the institution.
> 
> On 15/05/2013 16:04, Richard Goldstein wrote:
>> Hi all,
>>
>> I am using Newson's -somersd- command (from ssc); results, including the
>> piece I want, are saved in a matrix and I can list that matrix:
>>
>> . mat list r(table)
>>
>> r(table)[9,1]
>>              yhat1
>>       b  .62563699
>>      se  .00834334
>>       t  74.986391
>> pvalue  3.73e-257
>>      ll  .60924043
>>      ul  .64203354
>>      df        452
>>    crit  1.9652262
>>   eform          0
>>
>> My problem comes in attempting to use the [1,1] term (.62563699 here);
>> for example, I can't seem to list it:
>>
>> . matrix li r(table)[1,1]
>> [ invalid name
>> matrix [1,1] not found
>> r(111)
>>
>> and I can't do what I want to do - add this value to a scalar:
>>
>> scalar cstat=cstat+r(table)[1,1]
>> invalid syntax
>> r(198)
>>
>> note that cstat is not the problem as it is defined (as 0) prior to
>> entering my loop
>>
>> clearly I am doing something wrong but I have been unable to figure out
>> what it is or how to fix it
>>
>> Rich
>> *
>> *   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/
>>
> *
> *   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/
> 
*
*   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/


© Copyright 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index