Return to ChangeLog CVS log

Up to [Local Repository] / imach / src

Annotation of imach/src/ChangeLog, revision 1.5

1.5     ! brouard     1: 2003-06-17    <brouard@BROUARD>
        !             2: 
        !             3:        * timeval.h (Module): Added included file to make use of
        !             4:        gettimeofday working on win32 with cygwin.
        !             5: 
1.3       brouard     6: 2003-05-16  Brouard Nicolas  <brouard@brouard>
                      7: 
1.4       brouard     8:        * imach.c (Module): Insert of a warning if the delay between two
                      9:        waves is negative.
                     10: 
1.3       brouard    11:        * imach.c (Module): 
                     12: 
1.2       brouard    13: 2003-05-03    <brouard@BROUARD>
                     14: 
                     15:        * imach.c: Some cleaning
1.1       brouard    16: 2003-03-28    <brouard@BROUARD>
                     17: 
                     18:        * imach.c (Module): In version up to 0.92 likelihood was computed
                     19:        as if date of death was unknown. Death was treated as any other
                     20:        health state: the date of the interview describes the actual state
                     21:        and not the date of a change in health state. The former idea was
                     22:        to consider that at each interview the state was recorded
                     23:        (healthy, disable or death) and IMaCh was corrected; but when we
                     24:        introduced the exact date of death then we should have modified
                     25:        the contribution of an exact death to the likelihood. This new
                     26:        contribution is smaller and very dependent of the step unit
                     27:        stepm. It is no more the probability to die between last interview
                     28:        and month of death but the probability to survive from last
                     29:        interview up to one month before death multiplied by the
                     30:        probability to die within a month. Thanks to Chris
                     31:        Jackson for correcting this bug.  Former versions increased
                     32:        mortality artificially. The bad side is that we add another loop
                     33:        which slows down the processing. The difference can be up to 10%
                     34:        lower mortality.
                     35: 
                     36: 2002-05-30    <brouard@BROUARD>
                     37: 
                     38:        * 
                     39: 
                     40:        * imach.c (Module): Add correlation matrix of one-step
                     41:        probabilities and covariance matrix
                     42: