Annotation of imach/src/ChangeLog, revision 1.21
1.21 ! brouard 1: 2006-03-14 Brouard Nicolas <brouard@localhost>
! 2:
! 3: * imach.c (Module): varevsij Comments added explaining the second
! 4: table of variances if popbased=1 .
! 5: (Module): Covariances of eij, ekl added, graphs fixed, new html link.
! 6: (Module): Function pstamp added
! 7: (Module): Version 0.98d
! 8:
1.20 brouard 9: 2006-03-06 Brouard Nicolas <brouard@localhost>
10:
11: * imach.c (Module): Variance-covariance wrong links and
12: varian-covariance of ej. is needed (Saito).
13:
1.19 brouard 14: 2006-02-27 Brouard Nicolas <brouard@localhost>
15:
16: * imach.c (Module): One freematrix added in mlikeli!
17:
18: 2006-02-26 Brouard Nicolas <brouard@localhost>
19:
20: * imach.c (Module): Some improvements in processing parameter
21: filename with strsep.
22:
23: 2006-02-24 Brouard Nicolas <brouard@localhost>
24:
25: * imach.c (Module): Memory leaks checks with valgrind and:
26: datafile was not closed, some imatrix were not freed and on matrix
27: allocation too.
28:
1.16 lievre 29: 2006-02-09 LIEVRE Agnes <lievre@PC_00697.ined.fr>
30:
1.18 lievre 31: * strsep.c (Module): Inclusion because not in mingw32!!!
32:
1.17 lievre 33: * setup.iss.in (Module): IMACHSETUPVERSION added
34:
35: * noreg-setup.iss (Module): added to cvs tree
36:
1.16 lievre 37: * Makefile (Module): IMACHSETUPVERSION added
38:
1.15 brouard 39: 2006-01-30 BROUARD Nicolas <brouard@localhost>
40:
41: * imach.c (Module): Back to gnuplot.exe instead of wgnuplot.exe
42:
43: 2006-01-27 BROUARD Nicolas <brouard@localhost>
44:
45: * noreg-setup.iss (Module): ADDED
46:
47: 2006-01-24 BROUARD Nicolas <brouard@localhost>
48:
49: * imach.c (Module): Comments (lines starting with a #) are allowed in data.
50:
1.14 brouard 51: 2005-10-25 Nicolas Brouard <brouard@dhcp171.recherche.ined.fr>
52:
53: * Makefile (Module): Added Imach98.pmsp and howto crete a dmg
54:
55: * createdmg.sh (Module): Creates a dmg disk for MaC OS/X
56:
1.12 lievre 57: 2005-09-30 <lievre@PC_00595>
58:
59: * imach.c (Module): sump fixed, loop imx fixed, and simplifications.
1.13 lievre 60: (Module): If the status is missing at the last wave but we know
61: that the person is alive, then we can code his/her status as -2
62: (instead of missing=-1 in earlier versions) and his/her
63: contributions to the likelihood is 1 - Prob of dying from last
64: health status (= 1-p13= p11+p12 in the easiest case of somebody in
65: the healthy state at last known wave). Version is 0.98
1.12 lievre 66:
1.11 brouard 67: 2004-05-20 Brouard Nicolas <brouard@localhost>
68:
69: * imach.c (Repository):
70: Agnes added a direct estimation of mortality (without the need of
71: computing period prevalence and differential mortality). Thus here
72: is version 0.97a which has been distributed to some people at
73: REVES 16 in Brugge using an Inno setup.exe for PCs. Estimates of
74: mortality using covariates is not done today. Estimating direct
75: mortality is a very different process because it doesn't need
76: interpolation because it is easy to get the lx from the force of
77: the mortality mux in the simplest case as for a Gompertz (log mux
78: = a + b*x . But we have been able to incorporate the new code
79: within former imach program (0.96d) without deteriorating too much
80: the understanding of the program.
81:
1.10 brouard 82: 2003-06-25 <brouard@BROUARD>
83:
84: * imach.c (Module): On windows (cygwin) function asctime_r doesn't
85: exist so I changed back to asctime which exists.
86: (Module): Version 0.96b
87:
88: 2003-06-24 <brouard@BROUARD>
89:
90: * imach.c (Module): Some bugs corrected for windows. Also, when
91: mle=-1 a template is output in file "or"mypar.txt with the design
92: of the covariance matrix to be input.
93:
1.9 brouard 94: 2003-06-25 Brouard Nicolas <brouard@homebrou>
95:
96: * imach.c (Repository): Duplicated warning errors corrected.
97: (Repository): Elapsed time after each iteration is now output. It
98: helps to forecast when convergence will be reached. Elapsed time
99: is stamped in powell. We created a new html file for the graphs
100: concerning matrix of covariance. It has extension -cov.htm.
101:
1.8 brouard 102: 2003-06-23 Brouard Nicolas <brouard@homebrou>
103:
104: * 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.
105:
106: 2003-06-18 Brouard Nicolas <brouard@homebrou>
107:
108: * imach.c (Repository): Suppress abusive calls to append to file html (solution was to put fichtm as a global variable. Version 0.96
109:
1.7 brouard 110: 2003-06-17 Brouard Nicolas <brouard@homebrou>
111:
112:
113: * imach.c (Repository): Check when date of death was earlier that
114: current date of interview. It may happen when the death was just
115: prior to the death. In this case, dh was negative and likelihood
116: was wrong (infinity). We still send an "Error" but patch by
117: assuming that the date of death was just one stepm after the
118: interview.
119: (Repository): Because some people have very long ID (first column)
120: we changed int to long in num[] and we added a new lvector for
121: memory allocation. But we also truncated to 8 characters (left
122: truncation)
123:
124: (Repository): No more line truncation errors.
125:
126: 2003-06-14 Brouard Nicolas <brouard@homebrou>
127:
128: * imach.c (Repository): Add of a routine likelione (likelihood
129: only once) which prints on a text file
130: (ilk) the contributions to the likelihood for each
131: individual/wave.
132:
133: 2003-06-13 Brouard Nicolas <brouard@homebrou>
134: * imach.c (Repository): Replace "freqsummary" at a correct
135: place. It differs from routine "prevalence" which may be called
136: many times. Probs is memory consuming and must be used with
137: parcimony.
138:
139: 2003-06-17 <brouard@BROUARD>
140:
141: * timeval.h (Module): Added included file to make use of
142: gettimeofday working on win32 with cygwin.
143:
144: 2003-05-16 Brouard Nicolas <brouard@brouard>
145: * imach.c (Module): Insert of a warning if the delay between two
146: waves is negative.
147:
148: * imach.c (Module):
149:
150: 2003-05-03 <brouard@BROUARD>
151:
152: * imach.c: Some cleaning
153:
154: 2003-03-28 <brouard@BROUARD>
155: * imach.c (Module): In version up to 0.92 likelihood was computed
156: as if date of death was unknown. Death was treated as any other
157: health state: the date of the interview describes the actual state
158: and not the date of a change in health state. The former idea was
159: to consider that at each interview the state was recorded
160: (healthy, disable or death) and IMaCh was corrected; but when we
161: introduced the exact date of death then we should have modified
162: the contribution of an exact death to the likelihood. This new
163: contribution is smaller and very dependent of the step unit
164: stepm. It is no more the probability to die between last interview
165: and month of death but the probability to survive from last
166: interview up to one month before death multiplied by the
167: probability to die within a month. Thanks to Chris
168: Jackson for correcting this bug. Former versions increased
169: mortality artificially. The bad side is that we add another loop
170:
171:
172: which slows down the processing. The difference can be up to 10%
173:
174:
175: lower mortality.
176:
177:
178:
179:
180:
181: 2002-05-30 <brouard@BROUARD>
182:
183:
184:
185:
186:
187: *
188:
189:
190:
191:
192:
193: * imach.c (Module): Add correlation matrix of one-step
194:
195:
196: probabilities and covariance matrix
197:
198:
199:
200:
201:
FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>
![[BACK]](/icons/small/back.gif){kind=icon}
Return to ChangeLog CVS log ![[TXT]](/icons/small/text.gif){kind=icon}
![[DIR]](/icons/small/dir.gif){kind=icon}
Up to [Local Repository] / imach / src