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

Diff for /imach/src/ChangeLog between versions 1.6 and 1.13

version 1.6, 2003/06/17 20:16:05 version 1.13, 2005/09/30 18:01:43
Line 1 Line 1
 2003-06-17  Brouard Nicolas  <brouard@homebrou>  2005-09-30    <lievre@PC_00595>
   
         * imach.c (Repository): Check when date of death was earlier that          * imach.c (Module): sump fixed, loop imx fixed, and simplifications.
         current date of interview. It may happen when the death was just          (Module): If the status is missing at the last wave but we know
         prior to the death. In this case, dh was negative and likelihood          that the person is alive, then we can code his/her status as -2
         was wrong (infinity). We still send an "Error" but patch by          (instead of missing=-1 in earlier versions) and his/her
         assuming that the date of death was just one stepm after the          contributions to the likelihood is 1 - Prob of dying from last
         interview.          health status (= 1-p13= p11+p12 in the easiest case of somebody in
         (Repository): Because some people have very long ID (first column)          the healthy state at last known wave). Version is 0.98
         we changed int to long in num[] and we added a new lvector for  
         memory allocation. But we also truncated to 8 characters (left  2004-05-20  Brouard Nicolas  <brouard@localhost>
         truncation)  
         (Repository): No more line truncation errors.          * imach.c (Repository):
           Agnes added a direct estimation of mortality (without the need of
 2003-06-14  Brouard Nicolas  <brouard@homebrou>          computing period prevalence and differential mortality). Thus here
           is version 0.97a which has been distributed to some people at
         * imach.c (Repository): Add of a routine likelione (likelihood          REVES 16 in Brugge using an Inno setup.exe for PCs. Estimates of
         only once) which prints on a text file          mortality using covariates is not done today. Estimating direct
         (ilk) the contributions to the likelihood for each          mortality is a very different process because it doesn't need
         individual/wave.          interpolation because it is easy to get the lx from the force of
           the mortality mux in the simplest case as for a Gompertz (log mux
 2003-06-13  Brouard Nicolas  <brouard@homebrou>          = a + b*x . But we have been able to incorporate the new code
           within former imach program (0.96d) without deteriorating too much
         * imach.c (Repository): Replace "freqsummary" at a correct          the understanding of the program.
         place. It differs from routine "prevalence" which may be called  
         many times. Probs is memory consuming and must be used with  2003-06-25    <brouard@BROUARD>
         parcimony.  
           * imach.c (Module): On windows (cygwin) function asctime_r doesn't
 2003-06-17    <brouard@BROUARD>          exist so I changed back to asctime which exists.
           (Module): Version 0.96b
         * timeval.h (Module): Added included file to make use of  
         gettimeofday working on win32 with cygwin.  2003-06-24    <brouard@BROUARD>
   
 2003-05-16  Brouard Nicolas  <brouard@brouard>          * imach.c (Module): Some bugs corrected for windows. Also, when
           mle=-1 a template is output in file "or"mypar.txt with the design
         * imach.c (Module): Insert of a warning if the delay between two          of the covariance matrix to be input.
         waves is negative.  
   2003-06-25  Brouard Nicolas  <brouard@homebrou>
         * imach.c (Module):  
           * imach.c (Repository): Duplicated warning errors corrected.
 2003-05-03    <brouard@BROUARD>          (Repository): Elapsed time after each iteration is now output. It
           helps to forecast when convergence will be reached. Elapsed time
         * imach.c: Some cleaning          is stamped in powell.  We created a new html file for the graphs
 2003-03-28    <brouard@BROUARD>          concerning matrix of covariance. It has extension -cov.htm.
   
         * imach.c (Module): In version up to 0.92 likelihood was computed  2003-06-23  Brouard Nicolas  <brouard@homebrou>
         as if date of death was unknown. Death was treated as any other  
         health state: the date of the interview describes the actual state          * imach.c (Repository): Create a sub-directory where all the secondary files are. Only imach, htm, gp and r(imach) are on the main directory. Correct time and other things.
         and not the date of a change in health state. The former idea was  
         to consider that at each interview the state was recorded  2003-06-18  Brouard Nicolas  <brouard@homebrou>
         (healthy, disable or death) and IMaCh was corrected; but when we  
         introduced the exact date of death then we should have modified          * imach.c (Repository): Suppress abusive calls to append to file html (solution was to put fichtm as a global variable. Version 0.96
         the contribution of an exact death to the likelihood. This new  
         contribution is smaller and very dependent of the step unit  2003-06-17  Brouard Nicolas  <brouard@homebrou>
         stepm. It is no more the probability to die between last interview  
         and month of death but the probability to survive from last  
         interview up to one month before death multiplied by the          * imach.c (Repository): Check when date of death was earlier that
         probability to die within a month. Thanks to Chris          current date of interview. It may happen when the death was just
         Jackson for correcting this bug.  Former versions increased          prior to the death. In this case, dh was negative and likelihood
         mortality artificially. The bad side is that we add another loop          was wrong (infinity). We still send an "Error" but patch by
         which slows down the processing. The difference can be up to 10%          assuming that the date of death was just one stepm after the
         lower mortality.          interview.
           (Repository): Because some people have very long ID (first column)
 2002-05-30    <brouard@BROUARD>          we changed int to long in num[] and we added a new lvector for
           memory allocation. But we also truncated to 8 characters (left
         *          truncation)
   
         * imach.c (Module): Add correlation matrix of one-step          (Repository): No more line truncation errors.
         probabilities and covariance matrix  
   2003-06-14  Brouard Nicolas  <brouard@homebrou>
   
           * imach.c (Repository): Add of a routine likelione (likelihood
           only once) which prints on a text file
           (ilk) the contributions to the likelihood for each
           individual/wave.
   
   2003-06-13  Brouard Nicolas  <brouard@homebrou>
           * imach.c (Repository): Replace "freqsummary" at a correct
           place. It differs from routine "prevalence" which may be called
           many times. Probs is memory consuming and must be used with
           parcimony.
   
   2003-06-17    <brouard@BROUARD>
   
           * timeval.h (Module): Added included file to make use of
           gettimeofday working on win32 with cygwin.
   
   2003-05-16  Brouard Nicolas  <brouard@brouard>
           * imach.c (Module): Insert of a warning if the delay between two
           waves is negative.
   
           * imach.c (Module):
   
   2003-05-03    <brouard@BROUARD>
   
           * imach.c: Some cleaning
   
   2003-03-28    <brouard@BROUARD>
           * imach.c (Module): In version up to 0.92 likelihood was computed
           as if date of death was unknown. Death was treated as any other
           health state: the date of the interview describes the actual state
           and not the date of a change in health state. The former idea was
           to consider that at each interview the state was recorded
           (healthy, disable or death) and IMaCh was corrected; but when we
           introduced the exact date of death then we should have modified
           the contribution of an exact death to the likelihood. This new
           contribution is smaller and very dependent of the step unit
           stepm. It is no more the probability to die between last interview
           and month of death but the probability to survive from last
           interview up to one month before death multiplied by the
           probability to die within a month. Thanks to Chris
           Jackson for correcting this bug.  Former versions increased
           mortality artificially. The bad side is that we add another loop
   
   
           which slows down the processing. The difference can be up to 10%
   
   
           lower mortality.
   
   
   
   
   
   2002-05-30    <brouard@BROUARD>
   
   
   
   
   
           *
   
   
   
   
   
           * imach.c (Module): Add correlation matrix of one-step
   
   
           probabilities and covariance matrix
   
   
   
   
   
Removed from v.1.6  
changed lines
  Added in v.1.13

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