Annotation of imach/src/ChangeLog, revision 1.30
1.30 ! brouard 1: 2006-04-28 Brouard Nicolas <brouard@localhost>
! 2:
! 3: * imach.c (Module): Yes the sum of survivors was wrong since
! 4: imach-114 because nhstepm was no more computed in the age
! 5: loop. Now we define nhstepma in the age loop.
! 6:
1.29 lievre 7: 2006-04-04 LIEVRE Agnes <lievre@PC_00697.ined.fr>
8:
9: * imach.iss (Module):
10:
11: * imach.c (Module): bugs in evsi + population file added in htm output file
12:
13: 2006-03-22 LIEVRE Agnes <lievre@PC_00697.ined.fr>
14:
15: * imach.c (Module):
16:
1.27 brouard 17: 2006-03-20 Brouard Nicolas <brouard@localhost>
18:
1.28 brouard 19: * imach.c (Module): <title> changed, corresponds to .htm file
20: name. <head> headers where missing.
21:
1.27 brouard 22: * Makefile (Module): 0.98g
23:
24: * imach.c (Module): Weights can have a decimal point as for
25: English (a comma might work with a correct LC_NUMERIC environment,
26: otherwise the weight is truncated).
27: Modification of warning when the covariates values are not 0 or
28: 1.
29: Version 0.98g
30:
1.24 lievre 31: 2006-03-16 LIEVRE Agnes <lievre@PC_00697.ined.fr>
32:
1.26 lievre 33: * imach.c (Module): Comments concerning covariates added
34:
1.25 lievre 35: * noreg-setup.iss (Module): Version 0.98f
36:
1.24 lievre 37: * Makefile (Module): Version 0.98f make _windows=1 imachcyg-setup
38:
39: * imach.c (Module): refinements in the computation of lli if
40: status=-2 in order to have more reliable computation if stepm is
41: not 1 month. Version 0.98f
42:
1.22 brouard 43: 2006-03-15 Brouard Nicolas <brouard@localhost>
44:
45: * imach.c (Module): Bug if status = -2, the loglikelihood was
46: computed as likelihood omitting the logarithm. Version O.98e
47:
1.21 brouard 48: 2006-03-14 Brouard Nicolas <brouard@localhost>
49:
50: * imach.c (Module): varevsij Comments added explaining the second
51: table of variances if popbased=1 .
52: (Module): Covariances of eij, ekl added, graphs fixed, new html link.
53: (Module): Function pstamp added
54: (Module): Version 0.98d
55:
1.20 brouard 56: 2006-03-06 Brouard Nicolas <brouard@localhost>
57:
58: * imach.c (Module): Variance-covariance wrong links and
59: varian-covariance of ej. is needed (Saito).
60:
1.19 brouard 61: 2006-02-27 Brouard Nicolas <brouard@localhost>
62:
63: * imach.c (Module): One freematrix added in mlikeli!
64:
65: 2006-02-26 Brouard Nicolas <brouard@localhost>
66:
67: * imach.c (Module): Some improvements in processing parameter
68: filename with strsep.
69:
70: 2006-02-24 Brouard Nicolas <brouard@localhost>
71:
72: * imach.c (Module): Memory leaks checks with valgrind and:
73: datafile was not closed, some imatrix were not freed and on matrix
74: allocation too.
75:
1.16 lievre 76: 2006-02-09 LIEVRE Agnes <lievre@PC_00697.ined.fr>
77:
1.18 lievre 78: * strsep.c (Module): Inclusion because not in mingw32!!!
79:
1.17 lievre 80: * setup.iss.in (Module): IMACHSETUPVERSION added
81:
82: * noreg-setup.iss (Module): added to cvs tree
83:
1.16 lievre 84: * Makefile (Module): IMACHSETUPVERSION added
85:
1.15 brouard 86: 2006-01-30 BROUARD Nicolas <brouard@localhost>
87:
1.23 brouard 88: * Makefile (Module, Module): Latest Makefile
89:
1.15 brouard 90: * imach.c (Module): Back to gnuplot.exe instead of wgnuplot.exe
91:
92: 2006-01-27 BROUARD Nicolas <brouard@localhost>
93:
94: * noreg-setup.iss (Module): ADDED
95:
96: 2006-01-24 BROUARD Nicolas <brouard@localhost>
97:
98: * imach.c (Module): Comments (lines starting with a #) are allowed in data.
99:
1.14 brouard 100: 2005-10-25 Nicolas Brouard <brouard@dhcp171.recherche.ined.fr>
101:
102: * Makefile (Module): Added Imach98.pmsp and howto crete a dmg
103:
104: * createdmg.sh (Module): Creates a dmg disk for MaC OS/X
105:
1.12 lievre 106: 2005-09-30 <lievre@PC_00595>
107:
108: * imach.c (Module): sump fixed, loop imx fixed, and simplifications.
1.13 lievre 109: (Module): If the status is missing at the last wave but we know
110: that the person is alive, then we can code his/her status as -2
111: (instead of missing=-1 in earlier versions) and his/her
112: contributions to the likelihood is 1 - Prob of dying from last
113: health status (= 1-p13= p11+p12 in the easiest case of somebody in
114: the healthy state at last known wave). Version is 0.98
1.12 lievre 115:
1.11 brouard 116: 2004-05-20 Brouard Nicolas <brouard@localhost>
117:
118: * imach.c (Repository):
119: Agnes added a direct estimation of mortality (without the need of
120: computing period prevalence and differential mortality). Thus here
121: is version 0.97a which has been distributed to some people at
122: REVES 16 in Brugge using an Inno setup.exe for PCs. Estimates of
123: mortality using covariates is not done today. Estimating direct
124: mortality is a very different process because it doesn't need
125: interpolation because it is easy to get the lx from the force of
126: the mortality mux in the simplest case as for a Gompertz (log mux
127: = a + b*x . But we have been able to incorporate the new code
128: within former imach program (0.96d) without deteriorating too much
129: the understanding of the program.
130:
1.10 brouard 131: 2003-06-25 <brouard@BROUARD>
132:
133: * imach.c (Module): On windows (cygwin) function asctime_r doesn't
134: exist so I changed back to asctime which exists.
135: (Module): Version 0.96b
136:
137: 2003-06-24 <brouard@BROUARD>
138:
139: * imach.c (Module): Some bugs corrected for windows. Also, when
140: mle=-1 a template is output in file "or"mypar.txt with the design
141: of the covariance matrix to be input.
142:
1.9 brouard 143: 2003-06-25 Brouard Nicolas <brouard@homebrou>
144:
145: * imach.c (Repository): Duplicated warning errors corrected.
146: (Repository): Elapsed time after each iteration is now output. It
147: helps to forecast when convergence will be reached. Elapsed time
148: is stamped in powell. We created a new html file for the graphs
149: concerning matrix of covariance. It has extension -cov.htm.
150:
1.8 brouard 151: 2003-06-23 Brouard Nicolas <brouard@homebrou>
152:
153: * 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.
154:
155: 2003-06-18 Brouard Nicolas <brouard@homebrou>
156:
157: * imach.c (Repository): Suppress abusive calls to append to file html (solution was to put fichtm as a global variable. Version 0.96
158:
1.7 brouard 159: 2003-06-17 Brouard Nicolas <brouard@homebrou>
160:
161:
162: * imach.c (Repository): Check when date of death was earlier that
163: current date of interview. It may happen when the death was just
164: prior to the death. In this case, dh was negative and likelihood
165: was wrong (infinity). We still send an "Error" but patch by
166: assuming that the date of death was just one stepm after the
167: interview.
168: (Repository): Because some people have very long ID (first column)
169: we changed int to long in num[] and we added a new lvector for
170: memory allocation. But we also truncated to 8 characters (left
171: truncation)
172:
173: (Repository): No more line truncation errors.
174:
175: 2003-06-14 Brouard Nicolas <brouard@homebrou>
176:
177: * imach.c (Repository): Add of a routine likelione (likelihood
178: only once) which prints on a text file
179: (ilk) the contributions to the likelihood for each
180: individual/wave.
181:
182: 2003-06-13 Brouard Nicolas <brouard@homebrou>
183: * imach.c (Repository): Replace "freqsummary" at a correct
184: place. It differs from routine "prevalence" which may be called
185: many times. Probs is memory consuming and must be used with
186: parcimony.
187:
188: 2003-06-17 <brouard@BROUARD>
189:
190: * timeval.h (Module): Added included file to make use of
191: gettimeofday working on win32 with cygwin.
192:
193: 2003-05-16 Brouard Nicolas <brouard@brouard>
194: * imach.c (Module): Insert of a warning if the delay between two
195: waves is negative.
196:
197: * imach.c (Module):
198:
199: 2003-05-03 <brouard@BROUARD>
200:
201: * imach.c: Some cleaning
202:
203: 2003-03-28 <brouard@BROUARD>
204: * imach.c (Module): In version up to 0.92 likelihood was computed
205: as if date of death was unknown. Death was treated as any other
206: health state: the date of the interview describes the actual state
207: and not the date of a change in health state. The former idea was
208: to consider that at each interview the state was recorded
209: (healthy, disable or death) and IMaCh was corrected; but when we
210: introduced the exact date of death then we should have modified
211: the contribution of an exact death to the likelihood. This new
212: contribution is smaller and very dependent of the step unit
213: stepm. It is no more the probability to die between last interview
214: and month of death but the probability to survive from last
215: interview up to one month before death multiplied by the
216: probability to die within a month. Thanks to Chris
217: Jackson for correcting this bug. Former versions increased
218: mortality artificially. The bad side is that we add another loop
219:
220:
221: which slows down the processing. The difference can be up to 10%
222:
223:
224: lower mortality.
225:
226:
227:
228:
229:
230: 2002-05-30 <brouard@BROUARD>
231:
232:
233:
234:
235:
236: *
237:
238:
239:
240:
241:
242: * imach.c (Module): Add correlation matrix of one-step
243:
244:
245: probabilities and covariance matrix
246:
247:
248:
249:
250:
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