Return to ChangeLog CVS log

Up to [Local Repository] / imach / src

*** empty log message ***

    1: 2003-06-25  Brouard Nicolas  <brouard@homebrou>
    2: 
    3: 	* imach.c (Repository): Duplicated warning errors corrected.
    4: 	(Repository): Elapsed time after each iteration is now output. It
    5: 	helps to forecast when convergence will be reached. Elapsed time
    6: 	is stamped in powell.  We created a new html file for the graphs
    7: 	concerning matrix of covariance. It has extension -cov.htm.
    8: 
    9: 2003-06-23  Brouard Nicolas  <brouard@homebrou>
   10: 
   11: 	* 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.
   12: 
   13: 2003-06-18  Brouard Nicolas  <brouard@homebrou>
   14: 
   15: 	* imach.c (Repository): Suppress abusive calls to append to file html (solution was to put fichtm as a global variable. Version 0.96
   16: 
   17: 2003-06-17  Brouard Nicolas  <brouard@homebrou>
   18: 
   19: 
   20: 	* imach.c (Repository): Check when date of death was earlier that
   21: 	current date of interview. It may happen when the death was just
   22: 	prior to the death. In this case, dh was negative and likelihood
   23: 	was wrong (infinity). We still send an "Error" but patch by
   24: 	assuming that the date of death was just one stepm after the
   25: 	interview.
   26: 	(Repository): Because some people have very long ID (first column)
   27: 	we changed int to long in num[] and we added a new lvector for
   28: 	memory allocation. But we also truncated to 8 characters (left
   29: 	truncation)
   30: 
   31: 	(Repository): No more line truncation errors.
   32: 
   33: 2003-06-14  Brouard Nicolas  <brouard@homebrou>
   34: 
   35: 	* imach.c (Repository): Add of a routine likelione (likelihood
   36: 	only once) which prints on a text file
   37: 	(ilk) the contributions to the likelihood for each
   38: 	individual/wave.
   39: 
   40: 2003-06-13  Brouard Nicolas  <brouard@homebrou>
   41: 	* imach.c (Repository): Replace "freqsummary" at a correct
   42: 	place. It differs from routine "prevalence" which may be called
   43: 	many times. Probs is memory consuming and must be used with
   44: 	parcimony.
   45: 
   46: 2003-06-17    <brouard@BROUARD>
   47: 
   48: 	* timeval.h (Module): Added included file to make use of
   49: 	gettimeofday working on win32 with cygwin.
   50: 
   51: 2003-05-16  Brouard Nicolas  <brouard@brouard>
   52: 	* imach.c (Module): Insert of a warning if the delay between two
   53: 	waves is negative.
   54: 
   55: 	* imach.c (Module): 
   56: 
   57: 2003-05-03    <brouard@BROUARD>
   58: 
   59: 	* imach.c: Some cleaning
   60: 
   61: 2003-03-28    <brouard@BROUARD>
   62: 	* imach.c (Module): In version up to 0.92 likelihood was computed
   63: 	as if date of death was unknown. Death was treated as any other
   64: 	health state: the date of the interview describes the actual state
   65: 	and not the date of a change in health state. The former idea was
   66: 	to consider that at each interview the state was recorded
   67: 	(healthy, disable or death) and IMaCh was corrected; but when we
   68: 	introduced the exact date of death then we should have modified
   69: 	the contribution of an exact death to the likelihood. This new
   70: 	contribution is smaller and very dependent of the step unit
   71: 	stepm. It is no more the probability to die between last interview
   72: 	and month of death but the probability to survive from last
   73: 	interview up to one month before death multiplied by the
   74: 	probability to die within a month. Thanks to Chris
   75: 	Jackson for correcting this bug.  Former versions increased
   76: 	mortality artificially. The bad side is that we add another loop
   77: 
   78: 
   79: 	which slows down the processing. The difference can be up to 10%
   80: 
   81: 
   82: 	lower mortality.
   83: 
   84: 
   85: 
   86: 
   87: 
   88: 2002-05-30    <brouard@BROUARD>
   89: 
   90: 
   91: 
   92: 
   93: 
   94: 	* 
   95: 
   96: 
   97: 
   98: 
   99: 
  100: 	* imach.c (Module): Add correlation matrix of one-step
  101: 
  102: 
  103: 	probabilities and covariance matrix
  104: 
  105: 
  106: 
  107: 
  108: