Return to ChangeLog CVS log

Up to [Local Repository] / imach / src

Annotation of imach/src/ChangeLog, revision 1.13

1.12      lievre      1: 2005-09-30    <lievre@PC_00595>
                      2: 
                      3:        * imach.c (Module): sump fixed, loop imx fixed, and simplifications.
1.13    ! lievre      4:        (Module): If the status is missing at the last wave but we know
        !             5:        that the person is alive, then we can code his/her status as -2
        !             6:        (instead of missing=-1 in earlier versions) and his/her
        !             7:        contributions to the likelihood is 1 - Prob of dying from last
        !             8:        health status (= 1-p13= p11+p12 in the easiest case of somebody in
        !             9:        the healthy state at last known wave). Version is 0.98 
1.12      lievre     10: 
1.11      brouard    11: 2004-05-20  Brouard Nicolas  <brouard@localhost>
                     12: 
                     13:        * imach.c (Repository): 
                     14:        Agnes added a direct estimation of mortality (without the need of
                     15:        computing period prevalence and differential mortality). Thus here
                     16:        is version 0.97a which has been distributed to some people at
                     17:        REVES 16 in Brugge using an Inno setup.exe for PCs. Estimates of
                     18:        mortality using covariates is not done today. Estimating direct
                     19:        mortality is a very different process because it doesn't need
                     20:        interpolation because it is easy to get the lx from the force of
                     21:        the mortality mux in the simplest case as for a Gompertz (log mux
                     22:        = a + b*x . But we have been able to incorporate the new code
                     23:        within former imach program (0.96d) without deteriorating too much
                     24:        the understanding of the program. 
                     25: 
1.10      brouard    26: 2003-06-25    <brouard@BROUARD>
                     27: 
                     28:        * imach.c (Module): On windows (cygwin) function asctime_r doesn't
                     29:        exist so I changed back to asctime which exists.
                     30:        (Module): Version 0.96b
                     31: 
                     32: 2003-06-24    <brouard@BROUARD>
                     33: 
                     34:        * imach.c (Module): Some bugs corrected for windows. Also, when
                     35:        mle=-1 a template is output in file "or"mypar.txt with the design
                     36:        of the covariance matrix to be input.
                     37: 
1.9       brouard    38: 2003-06-25  Brouard Nicolas  <brouard@homebrou>
                     39: 
                     40:        * imach.c (Repository): Duplicated warning errors corrected.
                     41:        (Repository): Elapsed time after each iteration is now output. It
                     42:        helps to forecast when convergence will be reached. Elapsed time
                     43:        is stamped in powell.  We created a new html file for the graphs
                     44:        concerning matrix of covariance. It has extension -cov.htm.
                     45: 
1.8       brouard    46: 2003-06-23  Brouard Nicolas  <brouard@homebrou>
                     47: 
                     48:        * 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.
                     49: 
                     50: 2003-06-18  Brouard Nicolas  <brouard@homebrou>
                     51: 
                     52:        * imach.c (Repository): Suppress abusive calls to append to file html (solution was to put fichtm as a global variable. Version 0.96
                     53: 
1.7       brouard    54: 2003-06-17  Brouard Nicolas  <brouard@homebrou>
                     55: 
                     56: 
                     57:        * imach.c (Repository): Check when date of death was earlier that
                     58:        current date of interview. It may happen when the death was just
                     59:        prior to the death. In this case, dh was negative and likelihood
                     60:        was wrong (infinity). We still send an "Error" but patch by
                     61:        assuming that the date of death was just one stepm after the
                     62:        interview.
                     63:        (Repository): Because some people have very long ID (first column)
                     64:        we changed int to long in num[] and we added a new lvector for
                     65:        memory allocation. But we also truncated to 8 characters (left
                     66:        truncation)
                     67: 
                     68:        (Repository): No more line truncation errors.
                     69: 
                     70: 2003-06-14  Brouard Nicolas  <brouard@homebrou>
                     71: 
                     72:        * imach.c (Repository): Add of a routine likelione (likelihood
                     73:        only once) which prints on a text file
                     74:        (ilk) the contributions to the likelihood for each
                     75:        individual/wave.
                     76: 
                     77: 2003-06-13  Brouard Nicolas  <brouard@homebrou>
                     78:        * imach.c (Repository): Replace "freqsummary" at a correct
                     79:        place. It differs from routine "prevalence" which may be called
                     80:        many times. Probs is memory consuming and must be used with
                     81:        parcimony.
                     82: 
                     83: 2003-06-17    <brouard@BROUARD>
                     84: 
                     85:        * timeval.h (Module): Added included file to make use of
                     86:        gettimeofday working on win32 with cygwin.
                     87: 
                     88: 2003-05-16  Brouard Nicolas  <brouard@brouard>
                     89:        * imach.c (Module): Insert of a warning if the delay between two
                     90:        waves is negative.
                     91: 
                     92:        * imach.c (Module): 
                     93: 
                     94: 2003-05-03    <brouard@BROUARD>
                     95: 
                     96:        * imach.c: Some cleaning
                     97: 
                     98: 2003-03-28    <brouard@BROUARD>
                     99:        * imach.c (Module): In version up to 0.92 likelihood was computed
                    100:        as if date of death was unknown. Death was treated as any other
                    101:        health state: the date of the interview describes the actual state
                    102:        and not the date of a change in health state. The former idea was
                    103:        to consider that at each interview the state was recorded
                    104:        (healthy, disable or death) and IMaCh was corrected; but when we
                    105:        introduced the exact date of death then we should have modified
                    106:        the contribution of an exact death to the likelihood. This new
                    107:        contribution is smaller and very dependent of the step unit
                    108:        stepm. It is no more the probability to die between last interview
                    109:        and month of death but the probability to survive from last
                    110:        interview up to one month before death multiplied by the
                    111:        probability to die within a month. Thanks to Chris
                    112:        Jackson for correcting this bug.  Former versions increased
                    113:        mortality artificially. The bad side is that we add another loop
                    114: 
                    115: 
                    116:        which slows down the processing. The difference can be up to 10%
                    117: 
                    118: 
                    119:        lower mortality.
                    120: 
                    121: 
                    122: 
                    123: 
                    124: 
                    125: 2002-05-30    <brouard@BROUARD>
                    126: 
                    127: 
                    128: 
                    129: 
                    130: 
                    131:        * 
                    132: 
                    133: 
                    134: 
                    135: 
                    136: 
                    137:        * imach.c (Module): Add correlation matrix of one-step
                    138: 
                    139: 
                    140:        probabilities and covariance matrix
                    141: 
                    142: 
                    143: 
                    144: 
                    145: