Annotation of imach/src/ChangeLog, revision 1.51
1.51 ! brouard 1: 2022-05-24 Nicolas Brouard <brouard@ined.fr>
! 2:
! 3: * imach.c (Module): Some attempts to find a bug of wrong estimates
! 4: of confidencce intervals with product in the equation modelC
! 5:
! 6: 2022-05-15 Nicolas Brouard <brouard@ined.fr>
! 7:
! 8: * imach.c (Module): Some minor improvements
! 9:
1.50 brouard 10: 2022-04-13 Brouard Nicolas <brouard@brouard.name>
11:
12: * imach.c (Module): Adding link to text data files
13:
1.49 brouard 14: 2022-04-11 Nicolas Brouard <brouard@ined.fr>
15:
16: * imach.c (Module): Error in rewriting the 'r' file with yearsfproj or yearsbproj fixed
17:
1.48 brouard 18: 2022-04-05 Brouard Nicolas <brouard@ined.fr>
19:
20: * imach.c (Module): Fixed covariates (dummy or quantitative)
21: with missing values have never been allowed but are ERRORS and
22: program quits. Standard deviations of fixed covariates were
23: wrongly computed. Mean and standard deviations of time varying
24: covariates are still not computed.
25:
26: 2022-03-17 Brouard Nicolas <brouard@ined.fr>
1.47 brouard 27:
28: * 99r25 Improvements in fixing discrepancies between covariates
29: missing in result line but in model.
30:
1.46 brouard 31: *Wed Mar 31 2021 Nicolas Brouard <brouard@ined.fr>
1.45 brouard 32: * imach.c (Module): Still bugs in the result loop. Thank to Holly Benett
33:
1.46 brouard 34: *2021-03-08 Nicolas Brouard <brouard@ined.fr>
1.45 brouard 35:
36: * ./ (Module): Fixed bug on result:
37:
1.46 brouard 38: *2021-02-20 Nicolas Brouard <brouard@ined.fr>
1.43 brouard 39:
40: * imach.c (Module): Fix bug on quitting after result lines!
1.44 brouard 41: (Module): Version 0.99r21
1.43 brouard 42:
1.42 brouard 43: 2021-02-12 Nicolas Brouard <brouard@ined.fr>
44:
45: * imach.c (Module): The use of a Windows BOM (huge) file is now an error
46:
47:
48: 2021-02-11 Nicolas Brouard <brouard@ined.fr>
1.41 brouard 49:
50: * (Module): imach.c Someone entered 'results:' instead of 'result:'. Now it is an error which is printed.
51:
1.42 brouard 52: 2020-02-22 Brouard Nicolas <brouard@ined.fr>
1.40 brouard 53:
54: * (Module): imach.c Update mle=-3 (for computing Life expectancy
55: and life table from the data without any state)
56:
1.42 brouard 57: 2019-05-20 Brouard Nicolas <brouard@ined.fr>
1.39 brouard 58:
59: * version.h: Summary: version 0.99.r19
60:
61: * imach.c: Summary: Projection syntax simplified
62: We can now start projections, forward or backward, from the mean date
63: of inteviews up to or down to a number of years of projection:
64: prevforecast=1 yearsfproj=15.3 mobil_average=0
65: or
66: prevforecast=1 starting-proj-date=1/1/2007 final-proj-date=12/31/2017 mobil_average=0
67: or
68: prevbackcast=1 yearsbproj=12.3 mobil_average=1
69: or
70: prevbackcast=1 starting-back-date=1/10/1999 final-back-date=1/1/1985 mobil_average=1
71:
1.42 brouard 72: 2019-05-18 Brouard Nicolas <brouard@ined.fr>
1.39 brouard 73:
74: * imach.c: Summary: doxygen tex bug
75:
1.42 brouard 76: 2019-05-16 Brouard Nicolas <brouard@ined.fr>
1.39 brouard 77:
78: * imach.c: Summary: There was some wrong lines added
79:
1.42 brouard 80: 2019-05-09 Brouard Nicolas <brouard@ined.fr>
1.39 brouard 81:
82: * Makefile, imach.c: *** empty log message ***
83:
84: * ChangeLog: Summary: C=
85:
86: * imach.c: Summary: Some updates
87:
88: * imach.c: Summary: Before ncovmax
89:
90: * version.h: *** empty log message ***
91:
92: * imach.c: Summary: 0.99r18 unlimited number of individuals
93: The number n which was limited to 20,000 cases is now unlimited, from firstobs to lastobs. If the number is too for the virtual memory, probably an error will occur.
94:
1.42 brouard 95: 2018-12-13 Brouard Nicolas <brouard@ined.fr>
1.39 brouard 96:
97: * imach.c: Summary: Bug for young ages (<-30) will be in r17
98:
1.42 brouard 99: 2018-12-05 Brouard Nicolas <brouard@ined.fr>
1.39 brouard 100:
101: * Makefile: Summary: 0.99r16
102:
1.42 brouard 103: 2018-05-02 Brouard Nicolas <brouard@ined.fr>
1.39 brouard 104:
105: * imach.c: Summary: Some bugs fixed
106:
1.42 brouard 107: 2018-05-02 Brouard Nicolas <brouard@ined.fr>
1.39 brouard 108:
109: * imach.c: Summary: Bug for young ages (<-30) will be in r17
110:
1.42 brouard 111: 2018-05-02 Brouard Nicolas <brouard@ined.fr>
1.38 brouard 112:
113: * imach.c: Summary: Some bugs fixed
114:
1.42 brouard 115: 2018-05-01 Brouard Nicolas <brouard@ined.fr>
1.38 brouard 116:
117: * imach.c:
118: Summary: Bug fixed by providing frequencies only for non missing covariates
119:
1.42 brouard 120: 2018-04-27 Brouard Nicolas <brouard@ined.fr>
1.38 brouard 121:
122: * imach.c: Summary: some minor bugs
123:
1.42 brouard 124: 2018-04-21 Brouard Nicolas <brouard@ined.fr>
1.38 brouard 125:
126: * README.txt: *** empty log message ***
127:
128: * imach.c: Summary: Some bugs fixed, valgrind tested
129:
1.42 brouard 130: 2018-04-20 Brouard Nicolas <brouard@ined.fr>
1.38 brouard 131:
132: * Makefile, README.txt, setup.iss: Summary: imach 0.99r16
133:
134: * imach.c:
135: Summary: Computing mean and stdeviation of fixed quantitative variables
136:
1.42 brouard 137: 2018-04-19 Brouard Nicolas <brouard@ined.fr>
1.38 brouard 138:
139: * imach.c: Summary: Some minor bugs fixed
140:
141: * version.h: *** empty log message ***
142:
1.42 brouard 143: 2018-02-27 Brouard Nicolas <brouard@ined.fr>
1.38 brouard 144:
145: * imach.c: *** empty log message ***
146:
147: * imach.c: Summary: Adding second argument for quitting
148:
1.42 brouard 149: 2018-02-21 Brouard Nicolas <brouard@ined.fr>
1.38 brouard 150:
151: * Makefile, README.txt, imach.c: Summary: 0.99r15
152: New Makefile with recent VirtualBox 5.26. Bug in sqrt negatve in imach.c
153:
1.42 brouard 154: 2017-07-20 Brouard Nicolas <brouard@ined.fr>
1.38 brouard 155:
156: * imach.c: Summary: temporary working
157:
1.42 brouard 158: 2017-07-19 Brouard Nicolas <brouard@ined.fr>
1.38 brouard 159:
160: * imach.c: Summary: Bug for mobil_average=0 and prevforecast fixed(?)
161:
1.42 brouard 162: 2017-07-17 Brouard Nicolas <brouard@ined.fr>
1.38 brouard 163:
164: * imach.c: Summary: BOM files can be read now
165:
1.42 brouard 166: 2017-06-30 Brouard Nicolas <brouard@ined.fr>
1.38 brouard 167:
168: * imach.c: Summary: Graphs improvements
169:
170: * imach.c: Summary: Saito's color
171:
1.42 brouard 172: 2017-06-29 Brouard Nicolas <brouard@ined.fr>
1.38 brouard 173:
174: * imach.c: Summary: Version 0.99r14
175:
1.42 brouard 176: 2017-06-27 Brouard Nicolas <brouard@ined.fr>
1.38 brouard 177:
178: * imach.c: Summary: More documentation on projections
179:
180: * imach.c: Summary: Color of backprojection changed from 6 to 5(yellow)
181:
182: * imach.c: Summary: Some bug with rint
183:
1.42 brouard 184: 2017-05-24 Brouard Nicolas <brouard@ined.fr>
1.38 brouard 185:
186: * imach.c: *** empty log message ***
187:
1.42 brouard 188: 2017-05-23 Brouard Nicolas <brouard@ined.fr>
1.38 brouard 189:
190: * imach.c: Summary: Code into subroutine, cleanings
191:
1.42 brouard 192: 2017-05-18 Brouard Nicolas <brouard@ined.fr>
1.38 brouard 193:
194: * imach.c:
195: Summary: backprojection and confidence intervals of backprevalence
196:
1.42 brouard 197: 2017-05-13 Brouard Nicolas <brouard@ined.fr>
1.38 brouard 198:
199: * imach.c: Summary: temporary save for backprojection
200:
201: * imach.c: Summary: Version 0.99r13 (improvements and bugs fixed)
202:
1.42 brouard 203: 2017-04-26 Brouard Nicolas <brouard@ined.fr>
1.38 brouard 204:
205: * imach.c: Summary: imach 0.99r13 Some bugs fixed
206:
207: * imach.c: Summary: Labels in graphs
208:
1.42 brouard 209: 2017-04-24 Brouard Nicolas <brouard@ined.fr>
1.38 brouard 210:
211: * imach.c: Summary: to save
212:
1.42 brouard 213: 2017-04-18 Brouard Nicolas <brouard@ined.fr>
1.38 brouard 214:
215: * imach.c: *** empty log message ***
216:
1.42 brouard 217: 2017-04-05 Brouard Nicolas <brouard@ined.fr>
1.38 brouard 218:
219: * imach.c: Summary: Bug in E_ as well as in T_ fixed nres-1 vs k1-1
220:
1.42 brouard 221: 2017-04-04 Brouard Nicolas <brouard@ined.fr>
1.38 brouard 222:
223: * imach.c: Summary: Gnuplot indexations fixed (humm)
224:
225: * imach.c:
226: Summary: Some errors to warnings only if date of death is unknown but status is death we could set to pi3
227:
1.42 brouard 228: 2017-04-03 Brouard Nicolas <brouard@ined.fr>
1.38 brouard 229:
230: * imach.c: Summary: Version 0.99r12
231: Some cleanings, conformed with updated documentation.
232:
1.42 brouard 233: 2017-03-30 Brouard Nicolas <brouard@ined.fr>
1.38 brouard 234:
235: * version.h: *** empty log message ***
236:
237: * version.h: Summary:0.99r11
238:
1.42 brouard 239: 2017-03-29 Brouard Nicolas <brouard@ined.fr>
1.38 brouard 240:
241: * imach.c: Summary: Temp
242:
1.42 brouard 243: 2017-03-27 Brouard Nicolas <brouard@ined.fr>
1.38 brouard 244:
245: * imach.c: Summary: Temporary
246:
1.42 brouard 247: 2017-03-08 Brouard Nicolas <brouard@ined.fr>
1.38 brouard 248:
249: * imach.c: Summary: IMaCh version 0.99r10 bugs in gnuplot fixed
250:
251: * imach.c: Summary: Fixing data parameter line
252:
1.42 brouard 253: 2016-12-15 Brouard Nicolas <brouard@ined.fr>
1.38 brouard 254:
255: * imach.c: Summary: 0.99 in progress
256:
1.42 brouard 257: 2016-09-15 Brouard Nicolas <brouard@ined.fr>
1.38 brouard 258:
259: * imach.c: *** empty log message ***
260:
261: * imach.c: Summary: not working
262:
1.42 brouard 263: 2016-09-08 Brouard Nicolas <brouard@ined.fr>
1.38 brouard 264:
265: * imach.c: Summary: continue
266:
1.42 brouard 267: 2016-09-07 Brouard Nicolas <brouard@ined.fr>
1.38 brouard 268:
269: * imach.c: Summary: Starting values from frequencies
270:
271: * imach.c: *** empty log message ***
272:
1.42 brouard 273: 2016-09-02 Brouard Nicolas <brouard@ined.fr>
1.38 brouard 274:
275: * imach.c: *** empty log message ***
276:
1.42 brouard 277: 2016-08-30 Brouard Nicolas <brouard@ined.fr>
1.38 brouard 278:
279: * imach.c: Summary: Fixing a lots
280:
1.42 brouard 281: 2016-08-29 Brouard Nicolas <brouard@ined.fr>
1.38 brouard 282:
283: * imach.c: Summary: gnuplot problem in Back projection to fix
284:
285: * imach.c: Summary: Better
286:
1.42 brouard 287: 2016-08-26 Brouard Nicolas <brouard@ined.fr>
1.38 brouard 288:
289: * imach.c:
290: Summary: Improvement in Powell output in order to copy and paste
291:
292: * imach.c: Summary: Starting tests of 0.99
293:
294: * imach.c: Summary: to valgrind
295:
1.42 brouard 296: 2016-08-25 Brouard Nicolas <brouard@ined.fr>
1.38 brouard 297:
298: * imach.c: *** empty log message ***
299:
1.42 brouard 300: 2016-08-23 Brouard Nicolas <brouard@ined.fr>
1.38 brouard 301:
302: * imach.c: *** empty log message ***
303:
304: * imach.c: Summary: not working
305:
1.42 brouard 306: 2016-08-22 Brouard Nicolas <brouard@ined.fr>
1.38 brouard 307:
308: * imach.c: Summary: not working
309:
310: * imach.c: Summary: Not working
311:
1.42 brouard 312: 2016-07-23 Brouard Nicolas <brouard@ined.fr>
1.38 brouard 313:
314: * imach.c: Summary: Completing for func too
315:
1.42 brouard 316: 2016-07-22 Brouard Nicolas <brouard@ined.fr>
1.38 brouard 317:
318: * imach.c: Summary: Fixing some arrays, still debugging
319:
1.42 brouard 320: 2016-07-21 Brouard Nicolas <brouard@ined.fr>
1.38 brouard 321:
322: * imach.c:
323: Summary: 0.99 working (more or less) for Asian Workshop on multitate methods
324:
1.42 brouard 325: 2016-07-12 Brouard Nicolas <brouard@ined.fr>
1.38 brouard 326:
327: * imach.c: Summary: temp
328:
329: * imach.c: Summary: saving but not running
330:
1.42 brouard 331: 2016-07-01 Brouard Nicolas <brouard@ined.fr>
1.38 brouard 332:
333: * imach.c: Summary: Fixes
334:
1.42 brouard 335: 2016-02-19 Brouard Nicolas <brouard@ined.fr>
1.38 brouard 336:
337: * imach-0.98r.c: Summary: Kind of 0.98r? series, starting with r7
338:
339: * setup.iss, Makefile, version.h: *** empty log message ***
340:
341: * imach.c: Summary: temporary
342:
1.42 brouard 343: 2016-02-17 Brouard Nicolas <brouard@ined.fr>
1.38 brouard 344:
345: * imach.c: Summary: Probably last 0.98 stable version 0.98r6
346:
1.42 brouard 347: 2016-02-16 Brouard Nicolas <brouard@ined.fr>
1.38 brouard 348:
349: * imach.c: Summary: minor bug
350:
351: * imach.c: Summary: 0.99r2
352:
1.42 brouard 353: 2016-02-15 Brouard Nicolas <brouard@ined.fr>
1.38 brouard 354:
355: * imach.c: *** empty log message ***
356:
1.42 brouard 357: 2016-02-12 Brouard Nicolas <brouard@ined.fr>
1.38 brouard 358:
359: * imach.c: Summary: 0.99 Back projections
360:
1.42 brouard 361: 2015-12-23 Brouard Nicolas <brouard@ined.fr>
1.38 brouard 362:
363: * imach.c: Summary: Experimental backcast
364:
1.42 brouard 365: 2015-12-18 Brouard Nicolas <brouard@ined.fr>
1.38 brouard 366:
367: * imach.c: Summary: 0.98r4 Warning and status=-2
368:
369: Version 0.98r4 is now:
370: - displaying an error when status is -1, date of interview unknown and date of death known;
371: - permitting a status -2 when the vital status is unknown at a known date of right truncation.
372: Older changes concerning s=-2, dating from 2005 have been supersed.
373:
374: * Makefile: *** empty log message ***
375:
1.42 brouard 376: 2015-12-16 Brouard Nicolas <brouard@ined.fr>
1.38 brouard 377:
378: * Makefile: *** empty log message ***
379:
380: * imach.c: Summary: 0.98r4 working
381:
382: * Makefile: Summary: linuxrpm added
383:
384: * Makefile: *** empty log message ***
385:
386: * imach.c: Summary: temporary not working
387:
1.42 brouard 388: 2015-12-11 Brouard Nicolas <brouard@ined.fr>
1.38 brouard 389:
390: * imach.c: Summary: 0.98r4
391:
1.42 brouard 392: 2015-12-08 Brouard Nicolas <brouard@ined.fr>
1.38 brouard 393:
394: * Makefile: *** empty log message ***
395:
1.42 brouard 396: 2015-11-21 Brouard Nicolas <brouard@ined.fr>
1.38 brouard 397:
398: * Makefile:
399: Summary: VBoxManage change from execute --image to run --exe and --wait-exit doesn't exist any more
400:
401: * imach.c: Summary: minor typo
402:
403: * imach.c: Summary: 0.98r3 with some graph of projected cross-sectional
404:
405: Author: Nicolas Brouard
406:
1.42 brouard 407: 2015-11-18 Brouard Nicolas <brouard@ined.fr>
1.38 brouard 408:
409: * imach.c: Summary: Start working on projected prevalences
410:
1.42 brouard 411: 2015-11-17 Brouard Nicolas <brouard@ined.fr>
1.38 brouard 412:
413: * imach.c: Summary: Adding ftolpl parameter
414: Author: N Brouard
415:
416: We had difficulties to get smoothed confidence intervals. It was due
417: to the period prevalence which wasn't computed accurately. The inner
418: parameter ftolpl is now an outer parameter of the .imach parameter
419: file after estepm. If ftolpl is small 1.e-4 and estepm too,
420: computation are long.
421:
422: * version.h: *** empty log message ***
423:
424: * imach.c: Summary: temporary
425:
1.42 brouard 426: 2015-10-27 Brouard Nicolas <brouard@ined.fr>
1.38 brouard 427:
428: * Makefile: *** empty log message ***
429:
430: * setup.iss.in: Summary: some new subdirs
431:
432: * imach.c: *** empty log message ***
433:
434: * setup.iss.in:
435: Summary: Adding gnuplot 5.1 with bin and etc for pango fonts
436:
1.42 brouard 437: 2015-10-24 Brouard Nicolas <brouard@ined.fr>
1.38 brouard 438:
439: * imach.c: *** empty log message ***
440:
1.42 brouard 441: 2015-10-23 Brouard Nicolas <brouard@ined.fr>
1.38 brouard 442:
443: * imach.c:
444: Summary: 0.98r3 some clarification for graphs on likelihood contributions
445:
1.42 brouard 446: 2015-10-01 Brouard Nicolas <brouard@ined.fr>
1.38 brouard 447:
448: * imach.c: Summary: Some new graphs of contribution to likelihood
449:
1.42 brouard 450: 2015-09-30 Brouard Nicolas <brouard@ined.fr>
1.38 brouard 451:
452: * Makefile:
453: Summary: Version read from version.h, itself read with cmake
454:
455: * imach.c: Summary: looking at better estimation of the hessian
456:
457: Also a better criteria for convergence to the period prevalence And
458: therefore adding the number of years needed to converge. (The
459: prevalence in any alive state shold sum to one
460:
461: * Makefile: *** empty log message ***
462:
1.42 brouard 463: 2015-09-22 Brouard Nicolas <brouard@ined.fr>
1.38 brouard 464:
465: * imach.c:
466: Summary: Adding some overall graph on contribution to likelihood. Might change
467:
1.42 brouard 468: 2015-09-15 Brouard Nicolas <brouard@ined.fr>
1.38 brouard 469:
470: * Makefile: *** empty log message ***
471:
472: * imach.c: Summary: 0.98r0
473:
1.46 brouard 474: - Some new graphs like survival functions
1.38 brouard 475: - Some bugs fixed like model=1+age+V2.
476:
477: * ChangeLog, Makefile: Summary: 0.98r0
478:
479: * CMakeLists.txt: Summary: Some tests for setup.iss
480:
1.37 brouard 481: 2015-09-15 Nicolas J Brouard <nbrouard@tugault.ined.fr>
482:
483: * (Module): 0.98r0 Some new graphs, some bugs fixed: model=1+age+V2. etc
484:
1.36 brouard 485: 2015-08-18 Nicolas J Brouard <nbrouard@tugault.local>
486:
487: * (Module): Adding error when the covariance matrix doesn't contain the exact number of lines required by the model line.
488:
1.35 brouard 489: 2015-08-03 Nicolas J Brouard <nbrouard@tugault.ined.fr>
490:
491: * (Module): Changing Variance of one-step probabilities into Standard deviation (thanks to Yao-Chi Shih)
492:
493: 2014-12-16 Nicolas J Brouard <nbrouard@tugault.local>
494:
495: * imach.c (Module): Merging 1.61 to 1.162
496:
497: 2014-09-02 Nicolas J Brouard <nbrouard@njbrouard.ined.fr>
498:
499: * prevlim.h (Module):
500:
1.34 brouard 501: 2014-01-26 Nicolas J Brouard <nbrouard@ledermann-2.local>
502:
503: * imach.c (Module): Trying to merge old staffs together while being at Tokyo. Not tested...
504: (Module): Version 0.98nR Running ok, but output format still only works for three covariates.
505:
1.33 brouard 506: 2010-04-29 brouard <brouard@ined.fr>
507:
508: * imach.c (Module): Checking covariates for more complex models
509: than V1+V2. A lot of change to be done. Unstable.
510:
511: 2010-04-26 brouard <brouard@ined.fr>
512:
513: * imach.c (Module): merging some libgsl code. Fixing computation
514: of likelione (using inter/intrapolation if mle = 0) in order to
515: get same likelihood as if mle=1.
516: Some cleaning of code and comments added.
517:
1.32 brouard 518: 2009-10-29 brouard <brouard@ined.fr>
519:
520: * imach.c (Module): Now imach stops if date of birth, at least year of birth, is not given. Some cleaning of the code.
521:
1.31 brouard 522: 2006-06-30 Brouard Nicolas <brouard@localhost>
523:
524: * imach.c (Module): Clarifications on computing e.j
525:
1.30 brouard 526: 2006-04-28 Brouard Nicolas <brouard@localhost>
527:
528: * imach.c (Module): Yes the sum of survivors was wrong since
529: imach-114 because nhstepm was no more computed in the age
530: loop. Now we define nhstepma in the age loop.
1.31 brouard 531: (Module): In order to speed up (in case of numerous covariates) we
532: compute health expectancies (without variances) in a first step
533: and then all the health expectancies with variances or standard
534: deviation (needs data from the Hessian matrices) which slows the
535: computation.
536: In the future we should be able to stop the program is only health
537: expectancies and graph are needed without standard deviations.
1.30 brouard 538:
1.29 lievre 539: 2006-04-04 LIEVRE Agnes <lievre@PC_00697.ined.fr>
540:
541: * imach.iss (Module):
542:
543: * imach.c (Module): bugs in evsi + population file added in htm output file
544:
545: 2006-03-22 LIEVRE Agnes <lievre@PC_00697.ined.fr>
546:
547: * imach.c (Module):
548:
1.27 brouard 549: 2006-03-20 Brouard Nicolas <brouard@localhost>
550:
1.28 brouard 551: * imach.c (Module): <title> changed, corresponds to .htm file
552: name. <head> headers where missing.
553:
1.27 brouard 554: * Makefile (Module): 0.98g
555:
556: * imach.c (Module): Weights can have a decimal point as for
557: English (a comma might work with a correct LC_NUMERIC environment,
558: otherwise the weight is truncated).
559: Modification of warning when the covariates values are not 0 or
560: 1.
561: Version 0.98g
562:
1.24 lievre 563: 2006-03-16 LIEVRE Agnes <lievre@PC_00697.ined.fr>
564:
1.26 lievre 565: * imach.c (Module): Comments concerning covariates added
566:
1.25 lievre 567: * noreg-setup.iss (Module): Version 0.98f
568:
1.24 lievre 569: * Makefile (Module): Version 0.98f make _windows=1 imachcyg-setup
570:
571: * imach.c (Module): refinements in the computation of lli if
572: status=-2 in order to have more reliable computation if stepm is
573: not 1 month. Version 0.98f
574:
1.22 brouard 575: 2006-03-15 Brouard Nicolas <brouard@localhost>
576:
577: * imach.c (Module): Bug if status = -2, the loglikelihood was
578: computed as likelihood omitting the logarithm. Version O.98e
579:
1.21 brouard 580: 2006-03-14 Brouard Nicolas <brouard@localhost>
581:
582: * imach.c (Module): varevsij Comments added explaining the second
583: table of variances if popbased=1 .
584: (Module): Covariances of eij, ekl added, graphs fixed, new html link.
585: (Module): Function pstamp added
586: (Module): Version 0.98d
587:
1.20 brouard 588: 2006-03-06 Brouard Nicolas <brouard@localhost>
589:
590: * imach.c (Module): Variance-covariance wrong links and
591: varian-covariance of ej. is needed (Saito).
592:
1.19 brouard 593: 2006-02-27 Brouard Nicolas <brouard@localhost>
594:
595: * imach.c (Module): One freematrix added in mlikeli!
596:
597: 2006-02-26 Brouard Nicolas <brouard@localhost>
598:
599: * imach.c (Module): Some improvements in processing parameter
600: filename with strsep.
601:
602: 2006-02-24 Brouard Nicolas <brouard@localhost>
603:
604: * imach.c (Module): Memory leaks checks with valgrind and:
605: datafile was not closed, some imatrix were not freed and on matrix
606: allocation too.
607:
1.16 lievre 608: 2006-02-09 LIEVRE Agnes <lievre@PC_00697.ined.fr>
609:
1.18 lievre 610: * strsep.c (Module): Inclusion because not in mingw32!!!
611:
1.17 lievre 612: * setup.iss.in (Module): IMACHSETUPVERSION added
613:
614: * noreg-setup.iss (Module): added to cvs tree
615:
1.16 lievre 616: * Makefile (Module): IMACHSETUPVERSION added
617:
1.15 brouard 618: 2006-01-30 BROUARD Nicolas <brouard@localhost>
619:
1.23 brouard 620: * Makefile (Module, Module): Latest Makefile
621:
1.15 brouard 622: * imach.c (Module): Back to gnuplot.exe instead of wgnuplot.exe
623:
624: 2006-01-27 BROUARD Nicolas <brouard@localhost>
625:
626: * noreg-setup.iss (Module): ADDED
627:
628: 2006-01-24 BROUARD Nicolas <brouard@localhost>
629:
630: * imach.c (Module): Comments (lines starting with a #) are allowed in data.
631:
1.14 brouard 632: 2005-10-25 Nicolas Brouard <brouard@dhcp171.recherche.ined.fr>
633:
634: * Makefile (Module): Added Imach98.pmsp and howto crete a dmg
635:
636: * createdmg.sh (Module): Creates a dmg disk for MaC OS/X
637:
1.12 lievre 638: 2005-09-30 <lievre@PC_00595>
639:
640: * imach.c (Module): sump fixed, loop imx fixed, and simplifications.
1.13 lievre 641: (Module): If the status is missing at the last wave but we know
642: that the person is alive, then we can code his/her status as -2
643: (instead of missing=-1 in earlier versions) and his/her
644: contributions to the likelihood is 1 - Prob of dying from last
645: health status (= 1-p13= p11+p12 in the easiest case of somebody in
646: the healthy state at last known wave). Version is 0.98
1.12 lievre 647:
1.11 brouard 648: 2004-05-20 Brouard Nicolas <brouard@localhost>
649:
650: * imach.c (Repository):
651: Agnes added a direct estimation of mortality (without the need of
652: computing period prevalence and differential mortality). Thus here
653: is version 0.97a which has been distributed to some people at
654: REVES 16 in Brugge using an Inno setup.exe for PCs. Estimates of
655: mortality using covariates is not done today. Estimating direct
656: mortality is a very different process because it doesn't need
657: interpolation because it is easy to get the lx from the force of
658: the mortality mux in the simplest case as for a Gompertz (log mux
659: = a + b*x . But we have been able to incorporate the new code
660: within former imach program (0.96d) without deteriorating too much
661: the understanding of the program.
662:
1.10 brouard 663: 2003-06-25 <brouard@BROUARD>
664:
665: * imach.c (Module): On windows (cygwin) function asctime_r doesn't
666: exist so I changed back to asctime which exists.
667: (Module): Version 0.96b
668:
669: 2003-06-24 <brouard@BROUARD>
670:
671: * imach.c (Module): Some bugs corrected for windows. Also, when
672: mle=-1 a template is output in file "or"mypar.txt with the design
673: of the covariance matrix to be input.
674:
1.9 brouard 675: 2003-06-25 Brouard Nicolas <brouard@homebrou>
676:
677: * imach.c (Repository): Duplicated warning errors corrected.
678: (Repository): Elapsed time after each iteration is now output. It
679: helps to forecast when convergence will be reached. Elapsed time
680: is stamped in powell. We created a new html file for the graphs
681: concerning matrix of covariance. It has extension -cov.htm.
682:
1.8 brouard 683: 2003-06-23 Brouard Nicolas <brouard@homebrou>
684:
685: * 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.
686:
687: 2003-06-18 Brouard Nicolas <brouard@homebrou>
688:
689: * imach.c (Repository): Suppress abusive calls to append to file html (solution was to put fichtm as a global variable. Version 0.96
690:
1.7 brouard 691: 2003-06-17 Brouard Nicolas <brouard@homebrou>
692:
693:
694: * imach.c (Repository): Check when date of death was earlier that
695: current date of interview. It may happen when the death was just
696: prior to the death. In this case, dh was negative and likelihood
697: was wrong (infinity). We still send an "Error" but patch by
698: assuming that the date of death was just one stepm after the
699: interview.
700: (Repository): Because some people have very long ID (first column)
701: we changed int to long in num[] and we added a new lvector for
702: memory allocation. But we also truncated to 8 characters (left
703: truncation)
704:
705: (Repository): No more line truncation errors.
706:
707: 2003-06-14 Brouard Nicolas <brouard@homebrou>
708:
709: * imach.c (Repository): Add of a routine likelione (likelihood
710: only once) which prints on a text file
711: (ilk) the contributions to the likelihood for each
712: individual/wave.
713:
714: 2003-06-13 Brouard Nicolas <brouard@homebrou>
715: * imach.c (Repository): Replace "freqsummary" at a correct
716: place. It differs from routine "prevalence" which may be called
717: many times. Probs is memory consuming and must be used with
718: parcimony.
719:
720: 2003-06-17 <brouard@BROUARD>
721:
722: * timeval.h (Module): Added included file to make use of
723: gettimeofday working on win32 with cygwin.
724:
725: 2003-05-16 Brouard Nicolas <brouard@brouard>
726: * imach.c (Module): Insert of a warning if the delay between two
727: waves is negative.
728:
729: * imach.c (Module):
730:
731: 2003-05-03 <brouard@BROUARD>
732:
733: * imach.c: Some cleaning
734:
735: 2003-03-28 <brouard@BROUARD>
736: * imach.c (Module): In version up to 0.92 likelihood was computed
737: as if date of death was unknown. Death was treated as any other
738: health state: the date of the interview describes the actual state
739: and not the date of a change in health state. The former idea was
740: to consider that at each interview the state was recorded
741: (healthy, disable or death) and IMaCh was corrected; but when we
742: introduced the exact date of death then we should have modified
743: the contribution of an exact death to the likelihood. This new
744: contribution is smaller and very dependent of the step unit
745: stepm. It is no more the probability to die between last interview
746: and month of death but the probability to survive from last
747: interview up to one month before death multiplied by the
748: probability to die within a month. Thanks to Chris
749: Jackson for correcting this bug. Former versions increased
750: mortality artificially. The bad side is that we add another loop
751: which slows down the processing. The difference can be up to 10%
752: lower mortality.
753:
754: 2002-05-30 <brouard@BROUARD>
755: *
756: * imach.c (Module): Add correlation matrix of one-step
757: probabilities and covariance matrix
758:
759:
760:
761:
762:
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