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