[BACK]Return to ChangeLog CVS log [TXT] [DIR] Up to [Local Repository] / imach / src

Diff for /imach/src/ChangeLog between versions 1.51 and 1.58

version 1.51, 2022/05/24 08:09:48 version 1.58, 2022/08/31 09:52:08
Line 1 Line 1
   2022-08-31  Nicolas Brouard   <brouard@ined.fr>
   
           * imach.c (Module): Some improvments in fichtm and many verifications 0.99r34
   
   2022-08-21  Nicolas Brouard   <brouard@ined.fr>
   
           * imach.c (Module): Version 0.99r33 A lot of changes in
           reassigning covariates: my first idea was that people will always
           use the first covariate V1 into the model but in fact they are
           producing data with many covariates and can use an equation model
           with some of the covariate; it means that in a model V2+V3 instead
           of codtabm(k,Tvaraff[j]) which calculates for combination k, for
           three covariates (V1, V2, V3) the value of Tvaraff[j], but in fact
           the equation model is restricted to two variables only (V2, V3)
           and the combination for V2 should be codtabm(k,1) instead of
           (codtabm(k,2), and the code should be
           codtabm(k,TnsdVar[Tvaraff[j]]. Many many changes have been
           made. All of these should be simplified once a day like we did in
           hpxij() for example by using precov[nres] which is computed in
           decoderesult for each nres of each resultline. Loop should be done
           on the equation model globally by distinguishing only product with
           age (which are changing with age) and no more on type of
           covariates, single dummies, single covariates. 
   
   2022-08-06  Nicolas Brouard   <brouard@ined.fr>
   
           *  imach.c (Module): Version of imach using partly decoderesult to rebuild xpxij function
   
   2022-08-03  Nicolas Brouard   <brouard@ined.fr>
   
           *  imach.c (Module): Many errors in graphs fixed with Vn*age covariates.
   
   2022-07-25  Brouard Nicolas  <brouard@brouard.name>
   
           * imach.c (Module): Error cptcovn instead of nsd in bmij (was
           coredumped, revealed by Feiuno, thank you.
   
   2022-07-23  Nicolas Brouard   <brouard@ined.fr>
   
           * r29 W and not sqrt(Wald)
   
   2022-07-22  Nicolas Brouard   <brouard@ined.fr>
   
           *  imach.c (Module): Output of Wald test in the htm file and not only in the log. 
   
   2022-06-02  Brouard Nicolas  <brouard@brouard.name>
   
           * imach.c (Module): Adding the Wald tests from the log to the main
           htm for better display of the maximum likelihood estimators.
   
   2022-05-30  Brouard Nicolas  <brouard@brouard.name>
   
           * imach.c: With products of covariates (age or dummies or
           quantitatives), estimates of parameters were good but when
           estimating variances the positions of newly created covariates
           were wrongly assigned and results were wrong. Thank to Feinua_Sun!
   
 2022-05-24  Nicolas Brouard   <brouard@ined.fr>  2022-05-24  Nicolas Brouard   <brouard@ined.fr>
   
         * imach.c (Module): Some attempts to find a bug of wrong estimates          * imach.c (Module): Some attempts to find a bug of wrong estimates
Line 752 Line 809
         lower mortality.          lower mortality.
   
 2002-05-30    <brouard@BROUARD>  2002-05-30    <brouard@BROUARD>
         *  
         * imach.c (Module): Add correlation matrix of one-step          * imach.c (Module): Add correlation matrix of one-step
         probabilities and covariance matrix          probabilities and covariance matrix
   
   
   
   
   
Removed from v.1.51  
changed lines
  Added in v.1.58

FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>