Annotation of imach/src/ChangeLog, revision 1.71
1.71 ! brouard 1: 2024-06-28 Nicolas Brouard <brouard@brouardtwo>
! 2:
! 3: * imach.c (Module): s6 errors with age*age (harmless).
! 4:
1.70 brouard 5: 2024-05-12 Nicolas Brouard <brouard@ined.fr>
6:
7: * imach.c Version 0.99s5 In fact, the covariance of total life
8: expectancy e.. with a partial life expectancy e.j is high,
9: therefore the complete matrix of variance covariance has to be
10: included in the formula of the standard error of the proportion of
11: total life expectancy spent in a specific state:
12: var(X/Y)=mu_x^2/mu_y^2*(sigma_x^2/mu_x^2 -2
13: sigma_xy/mu_x/mu_y+sigma^2/mu_y^2). Also an error with mle=-3
14: made the program core dump. It is fixed in this version.
15:
1.69 brouard 16: 2024-04-30 Nicolas Brouard <brouard@ined.fr>
17:
18: * (Module): In version 0.99s4, we incorporated the calculation of
19: the std error of the proportion of total life expectancy spent in
20: a specific state Var(e.j/e..) using the formula of Var(X/Y)
21: depending only of the variances of X and Y and expectancies.
22:
1.68 brouard 23: 2024-04-24 Nicolas Brouard <brouard@ined.fr>
24:
25: * (Module): This version comes late after having tested
26: successfully the praxis C version of Buckhardt. But Buckardt's
27: version was difficult to read and Gegenfurtner's version had a few
28: typos which made its results less reliable than Buckhardt's
29: results. The most important work consisted in retyping the Brent
30: original PRAXIS program written in Algol W (published with errors,
31: ommitting the transposition of matrix V before its QR reduction
32: from Golub. I used the recent "awe" compiler from Gkynn Webster.
33: The awe library had errors, for example in arc tangent function
34: which have been fixed.
35:
36: The main objective was to get identical results with the three
37: versions: (1) Algol W, (2) Buckhardt'C version as well (3)
38: Gegenfürtner C versions on the various test functions published by
39: Brent in 1973 in Algol W.
40:
41: Also, in order to compare them, the random function had to produce
42: the same sequence for the 3 softwares. The random function used in
43: imach corresponds to original Brent's random function written in
44: Algol W. Other point, in Algol W, the arrays of dimension n are
45: 'normal' mathematical arrays starting from 1 to n. But this is a
46: real issue in C where, by default, arrays are starting from 0 to
47: n-1. In Buckhardt, as well as in Gegenfürtner C code, it can be
48: seen that authors while trying to mimick original Brent Algol W
49: code are hesitating by changing either a loop originally from 1 to
50: n in a loop from 0 to n-1, or keeping Brent's loop from 1 to n and
51: shifting the index from original X(I) in Algol W to x[i-1] in C.
52: But as IMaCh is using, since the beginning, the Numerical Recipes
53: functions vector or matrix, I changed Geggenfürtner code to mimick
54: the original Algol W arrays. Thus the X(I) is translated in C as
55: x[i] which minimizes the errors. The Golub QR algorithm was
56: published in Algol with overflow errors which were reproduced in
57: Brent's Algol W code. Buckhardt code fixed these errors which are
58: much more problematic in C than in Algol W. Thus Buckhardt code
59: seems very safe, but i haven't chosen it for IMaCh because the C
60: style is horrible and almost unreadable compared to Gegenfürtner
61: CO code which is very close to Brent's original. Also what makes
62: Buckhardt code more difficult to read is, instead of passing the
63: minimum of parameters in the functions calls, as it is in Algol
64: Brent's code or Gegenfürtner's code, the list of parameters is
65: high. For example, the flin function LONG REAL PROCEDURE FLIN
66: (LONG REAL VALUE L) has only one parameter in Algol W, the
67: Gegenfürtner flin function had two parameters: static double
68: flin(l, j) double l; { int i; double tflin[N];} but Buckhardt
69: function has 14 parameters which makes the code unreadable and
70: useless. Gegenfürtner used a lot of static variables or functions
71: which I tried to minimize. Also in Gegefürtner, array dimensions
72: were fixed to N. In my adaptation the flin is static double
73: flin(double l, int j) and the parameter used are global variables.
74:
75: 2023-06-14 Nicolas Brouard <brouard@ined.fr>
76:
77: * imach.c (Module): Testing if conjugate gradient could be quicker
78: when lot of variables POWELLORIGINCONJUGATE
79:
1.67 brouard 80: 2023-05-23 Nicolas Brouard <brouard@ined.fr>
81:
82: * imach.c (Module): Fixed PROB_r
83:
84: 2023-05-22 Nicolas Brouard <brouard@ined.fr>
85:
86: * imach.c (Module): In the ILK....txt file, the number of columns
87: before the covariates values is dependent of the number of states (16+nlstate): 0.99r46
88:
1.66 brouard 89: 2023-05-08 Nicolas Brouard <brouard@ined.fr>
90:
91: * (Module): Error V0 when result:. and model 1+age+V1: fixed
92:
1.63 brouard 93: 2023-04-29 Nicolas Brouard <brouard@ined.fr>
94:
95: * imach.c (Module): Inverting the model equation and fixingg bugs
96: in the drawings
97: "1+age+V7*V4*age+V6*V4*age+V7*V3*age+V6*V3*age+V6*V2*age+V7*age+V6*age+V4*age+V3*age+V2*age+V7*V4+V6*V4+V7*V3+V6*V3+V7*V2+V6*V2+V7+V6+V4+V3+V2\000\0003+V2"
98:
99: 2023-04-24 Nicolas Brouard <brouard@ined.fr>
100:
101: * imach.c (Module): some bugs in printinggnuplot
102:
1.62 brouard 103: 2022-09-19 Nicolas Brouard <brouard@ined.fr>
104:
105: * imach.c (Module): Version 0.99r42 needed a newer version of
106: Gnuplot. But newer version 0.99r43 should run with the Gnuplot
107: version 5.0 or 5.1 distributed with IMaCh.
108:
1.61 brouard 109: 2022-09-18 Nicolas Brouard <brouard@ined.fr>
110:
111: * imach.c (Module): Fixing when a state in the data is 0 or higher
112: than lstate+ndeath. Fixing the plot of contribution to Likelihood.
113:
1.63 brouard 114: 2022-09-16 Nicolas Brouard <brouard@ined.fr>
115:
116: * imach.c (Module): 0.99r41 Was an error when product of timevarying and fixed. Using FixedV[of name] now. Thank you Feinuo
117:
118: 2022-09-14 Nicolas Brouard <brouard@ined.fr>
119:
120: * imach.c (Module): Fixing names of variables in T_ (thanks to Feinuo)
121:
1.61 brouard 122: 2022-09-14 Nicolas Brouard <brouard@ined.fr>
123:
124: * imach.c (Module): Version 0.99r39 with colored dummy covariates
125: (fixed or time varying), using new last columns of
126: ILK_parameter.txt file.
127:
1.60 brouard 128: 2022-09-11 Nicolas Brouard <brouard@ined.fr>
129:
130: * imach.c (Module): Adding timevarying products of any kinds,
131: should work before shifting cotvar from ncovcol+nqv columns in
132: order to have a correspondance between the column of cotvar and
133: the id of column.
1.61 brouard 134: (Module): Some cleaning and adding covariates in ILK.txt
1.60 brouard 135:
136: 2022-09-09 Nicolas Brouard <brouard@ined.fr>
137:
138: * imach.c (Module): Many improvements for fixing products of fixed
139: timevarying as well as fixed * fixed, and test with quantitative
140: covariate.
141:
1.59 brouard 142: 2022-09-04 Nicolas Brouard <brouard@ined.fr>
143:
144: * imach.c (Module): Now the easy runs i.e. without result or
145: model=1+age only did not work. The defautl combination should be 1
146: and not 0 because everything hasn't been tranformed yet.
147:
148: 2022-09-02 Nicolas Brouard <brouard@ined.fr>
149:
150: * imach.c: Version 0.99r35 because it outputs same results with
151: 1+age+V1+V1*age for females and 1+age for females only
152: (education=1 noweight)
153:
1.58 brouard 154: 2022-08-31 Nicolas Brouard <brouard@ined.fr>
155:
156: * imach.c (Module): Some improvments in fichtm and many verifications 0.99r34
157:
1.56 brouard 158: 2022-08-21 Nicolas Brouard <brouard@ined.fr>
159:
160: * imach.c (Module): Version 0.99r33 A lot of changes in
161: reassigning covariates: my first idea was that people will always
162: use the first covariate V1 into the model but in fact they are
163: producing data with many covariates and can use an equation model
164: with some of the covariate; it means that in a model V2+V3 instead
165: of codtabm(k,Tvaraff[j]) which calculates for combination k, for
166: three covariates (V1, V2, V3) the value of Tvaraff[j], but in fact
167: the equation model is restricted to two variables only (V2, V3)
168: and the combination for V2 should be codtabm(k,1) instead of
169: (codtabm(k,2), and the code should be
170: codtabm(k,TnsdVar[Tvaraff[j]]. Many many changes have been
171: made. All of these should be simplified once a day like we did in
172: hpxij() for example by using precov[nres] which is computed in
173: decoderesult for each nres of each resultline. Loop should be done
174: on the equation model globally by distinguishing only product with
175: age (which are changing with age) and no more on type of
176: covariates, single dummies, single covariates.
177:
178: 2022-08-06 Nicolas Brouard <brouard@ined.fr>
179:
180: * imach.c (Module): Version of imach using partly decoderesult to rebuild xpxij function
181:
182: 2022-08-03 Nicolas Brouard <brouard@ined.fr>
183:
184: * imach.c (Module): Many errors in graphs fixed with Vn*age covariates.
185:
1.55 brouard 186: 2022-07-25 Brouard Nicolas <brouard@brouard.name>
187:
188: * imach.c (Module): Error cptcovn instead of nsd in bmij (was
189: coredumped, revealed by Feiuno, thank you.
1.57 brouard 190:
191: 2022-07-23 Nicolas Brouard <brouard@ined.fr>
192:
193: * r29 W and not sqrt(Wald)
194:
195: 2022-07-22 Nicolas Brouard <brouard@ined.fr>
196:
197: * imach.c (Module): Output of Wald test in the htm file and not only in the log.
198:
1.55 brouard 199: 2022-06-02 Brouard Nicolas <brouard@brouard.name>
200:
201: * imach.c (Module): Adding the Wald tests from the log to the main
1.65 brouard 202: htm for better display of the maximum likelihood estimators.
1.57 brouard 203:
1.65 brouard 204: 2022-05-30 Brouard Nicolas <brouard@brouard.name>
205:
206: * imach.c: With products of covariates (age or dummies or
207: quantitatives), estimates of parameters were good but when
208: estimating variances the positions of newly created covariates
209: were wrongly assigned and results were wrong. Thank to Feinua_Sun!
210:
211: 2022-05-24 Nicolas Brouard <brouard@ined.fr>
212:
213: * imach.c (Module): Some attempts to find a bug of wrong estimates
214: of confidencce intervals with product in the equation modelC
215:
216: 2022-05-15 Nicolas Brouard <brouard@ined.fr>
217:
218: * imach.c (Module): Some minor improvements
219:
220: 2022-04-13 Brouard Nicolas <brouard@brouard.name>
221:
222: * imach.c (Module): Adding link to text data files
223:
224: 2022-04-11 Nicolas Brouard <brouard@ined.fr>
225:
226: * imach.c (Module): Error in rewriting the 'r' file with yearsfproj or yearsbproj fixed
227:
228: 2022-04-05 Brouard Nicolas <brouard@ined.fr>
229:
230: * imach.c (Module): Fixed covariates (dummy or quantitative)
231: with missing values have never been allowed but are ERRORS and
232: program quits. Standard deviations of fixed covariates were
233: wrongly computed. Mean and standard deviations of time varying
234: covariates are still not computed.
235:
236: 2022-03-17 Brouard Nicolas <brouard@ined.fr>
237:
238: * 99r25 Improvements in fixing discrepancies between covariates
239: missing in result line but in model.
240:
241: *Wed Mar 31 2021 Nicolas Brouard <brouard@ined.fr>
242: * imach.c (Module): Still bugs in the result loop. Thank to Holly Benett
243:
244: *2021-03-08 Nicolas Brouard <brouard@ined.fr>
245:
246: * ./ (Module): Fixed bug on result:
247:
248: *2021-02-20 Nicolas Brouard <brouard@ined.fr>
249:
250: * imach.c (Module): Fix bug on quitting after result lines!
251: (Module): Version 0.99r21
252:
253: 2021-02-12 Nicolas Brouard <brouard@ined.fr>
254:
255: * imach.c (Module): The use of a Windows BOM (huge) file is now an error
256:
257:
258: 2021-02-11 Nicolas Brouard <brouard@ined.fr>
259:
260: * (Module): imach.c Someone entered 'results:' instead of 'result:'. Now it is an error which is printed.
261:
262: 2020-02-22 Brouard Nicolas <brouard@ined.fr>
263:
264: * (Module): imach.c Update mle=-3 (for computing Life expectancy
265: and life table from the data without any state)
266:
267: 2019-05-20 Brouard Nicolas <brouard@ined.fr>
268:
269: * version.h: Summary: version 0.99.r19
270:
271: * imach.c: Summary: Projection syntax simplified
272: We can now start projections, forward or backward, from the mean date
273: of inteviews up to or down to a number of years of projection:
274: prevforecast=1 yearsfproj=15.3 mobil_average=0
275: or
276: prevforecast=1 starting-proj-date=1/1/2007 final-proj-date=12/31/2017 mobil_average=0
277: or
278: prevbackcast=1 yearsbproj=12.3 mobil_average=1
279: or
280: prevbackcast=1 starting-back-date=1/10/1999 final-back-date=1/1/1985 mobil_average=1
281:
282: 2019-05-18 Brouard Nicolas <brouard@ined.fr>
283:
284: * imach.c: Summary: doxygen tex bug
285:
286: 2019-05-16 Brouard Nicolas <brouard@ined.fr>
287:
288: * imach.c: Summary: There was some wrong lines added
289:
290: 2019-05-09 Brouard Nicolas <brouard@ined.fr>
291:
292: * Makefile, imach.c: *** empty log message ***
293:
294: * ChangeLog: Summary: C=
295:
296: * imach.c: Summary: Some updates
297:
298: * imach.c: Summary: Before ncovmax
299:
300: * version.h: *** empty log message ***
301:
302: * imach.c: Summary: 0.99r18 unlimited number of individuals
303: 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.
304:
305: 2018-12-13 Brouard Nicolas <brouard@ined.fr>
306:
307: * imach.c: Summary: Bug for young ages (<-30) will be in r17
308:
309: 2018-12-05 Brouard Nicolas <brouard@ined.fr>
310:
311: * Makefile: Summary: 0.99r16
312:
313: 2018-05-02 Brouard Nicolas <brouard@ined.fr>
314:
315: * imach.c: Summary: Some bugs fixed
316:
317: 2018-05-02 Brouard Nicolas <brouard@ined.fr>
318:
319: * imach.c: Summary: Bug for young ages (<-30) will be in r17
320:
321: 2018-05-02 Brouard Nicolas <brouard@ined.fr>
322:
323: * imach.c: Summary: Some bugs fixed
324:
325: 2018-05-01 Brouard Nicolas <brouard@ined.fr>
326:
327: * imach.c:
328: Summary: Bug fixed by providing frequencies only for non missing covariates
329:
330: 2018-04-27 Brouard Nicolas <brouard@ined.fr>
331:
332: * imach.c: Summary: some minor bugs
333:
334: 2018-04-21 Brouard Nicolas <brouard@ined.fr>
335:
336: * README.txt: *** empty log message ***
337:
338: * imach.c: Summary: Some bugs fixed, valgrind tested
339:
340: 2018-04-20 Brouard Nicolas <brouard@ined.fr>
341:
342: * Makefile, README.txt, setup.iss: Summary: imach 0.99r16
343:
344: * imach.c:
345: Summary: Computing mean and stdeviation of fixed quantitative variables
346:
347: 2018-04-19 Brouard Nicolas <brouard@ined.fr>
348:
349: * imach.c: Summary: Some minor bugs fixed
350:
351: * version.h: *** empty log message ***
352:
353: 2018-02-27 Brouard Nicolas <brouard@ined.fr>
354:
355: * imach.c: *** empty log message ***
356:
357: * imach.c: Summary: Adding second argument for quitting
358:
359: 2018-02-21 Brouard Nicolas <brouard@ined.fr>
360:
361: * Makefile, README.txt, imach.c: Summary: 0.99r15
362: New Makefile with recent VirtualBox 5.26. Bug in sqrt negatve in imach.c
363:
364: 2017-07-20 Brouard Nicolas <brouard@ined.fr>
365:
366: * imach.c: Summary: temporary working
367:
368: 2017-07-19 Brouard Nicolas <brouard@ined.fr>
369:
370: * imach.c: Summary: Bug for mobil_average=0 and prevforecast fixed(?)
371:
372: 2017-07-17 Brouard Nicolas <brouard@ined.fr>
373:
374: * imach.c: Summary: BOM files can be read now
375:
376: 2017-06-30 Brouard Nicolas <brouard@ined.fr>
377:
378: * imach.c: Summary: Graphs improvements
379:
380: * imach.c: Summary: Saito's color
381:
382: 2017-06-29 Brouard Nicolas <brouard@ined.fr>
383:
384: * imach.c: Summary: Version 0.99r14
385:
386: 2017-06-27 Brouard Nicolas <brouard@ined.fr>
387:
388: * imach.c: Summary: More documentation on projections
389:
390: * imach.c: Summary: Color of backprojection changed from 6 to 5(yellow)
391:
392: * imach.c: Summary: Some bug with rint
393:
394: 2017-05-24 Brouard Nicolas <brouard@ined.fr>
395:
396: * imach.c: *** empty log message ***
397:
398: 2017-05-23 Brouard Nicolas <brouard@ined.fr>
399:
400: * imach.c: Summary: Code into subroutine, cleanings
401:
402: 2017-05-18 Brouard Nicolas <brouard@ined.fr>
403:
404: * imach.c:
405: Summary: backprojection and confidence intervals of backprevalence
406:
407: 2017-05-13 Brouard Nicolas <brouard@ined.fr>
408:
409: * imach.c: Summary: temporary save for backprojection
410:
411: * imach.c: Summary: Version 0.99r13 (improvements and bugs fixed)
412:
413: 2017-04-26 Brouard Nicolas <brouard@ined.fr>
414:
415: * imach.c: Summary: imach 0.99r13 Some bugs fixed
416:
417: * imach.c: Summary: Labels in graphs
418:
419: 2017-04-24 Brouard Nicolas <brouard@ined.fr>
420:
421: * imach.c: Summary: to save
422:
423: 2017-04-18 Brouard Nicolas <brouard@ined.fr>
424:
425: * imach.c: *** empty log message ***
426:
427: 2017-04-05 Brouard Nicolas <brouard@ined.fr>
428:
429: * imach.c: Summary: Bug in E_ as well as in T_ fixed nres-1 vs k1-1
430:
431: 2017-04-04 Brouard Nicolas <brouard@ined.fr>
432:
433: * imach.c: Summary: Gnuplot indexations fixed (humm)
434:
435: * imach.c:
436: Summary: Some errors to warnings only if date of death is unknown but status is death we could set to pi3
437:
438: 2017-04-03 Brouard Nicolas <brouard@ined.fr>
439:
440: * imach.c: Summary: Version 0.99r12
441: Some cleanings, conformed with updated documentation.
442:
443: 2017-03-30 Brouard Nicolas <brouard@ined.fr>
444:
445: * version.h: *** empty log message ***
446:
447: * version.h: Summary:0.99r11
448:
449: 2017-03-29 Brouard Nicolas <brouard@ined.fr>
450:
451: * imach.c: Summary: Temp
452:
453: 2017-03-27 Brouard Nicolas <brouard@ined.fr>
454:
455: * imach.c: Summary: Temporary
456:
457: 2017-03-08 Brouard Nicolas <brouard@ined.fr>
458:
459: * imach.c: Summary: IMaCh version 0.99r10 bugs in gnuplot fixed
460:
461: * imach.c: Summary: Fixing data parameter line
462:
463: 2016-12-15 Brouard Nicolas <brouard@ined.fr>
464:
465: * imach.c: Summary: 0.99 in progress
466:
467: 2016-09-15 Brouard Nicolas <brouard@ined.fr>
468:
469: * imach.c: *** empty log message ***
470:
471: * imach.c: Summary: not working
472:
473: 2016-09-08 Brouard Nicolas <brouard@ined.fr>
474:
475: * imach.c: Summary: continue
476:
477: 2016-09-07 Brouard Nicolas <brouard@ined.fr>
478:
479: * imach.c: Summary: Starting values from frequencies
480:
481: * imach.c: *** empty log message ***
482:
483: 2016-09-02 Brouard Nicolas <brouard@ined.fr>
484:
485: * imach.c: *** empty log message ***
486:
487: 2016-08-30 Brouard Nicolas <brouard@ined.fr>
488:
489: * imach.c: Summary: Fixing a lots
490:
491: 2016-08-29 Brouard Nicolas <brouard@ined.fr>
492:
493: * imach.c: Summary: gnuplot problem in Back projection to fix
494:
495: * imach.c: Summary: Better
496:
497: 2016-08-26 Brouard Nicolas <brouard@ined.fr>
498:
499: * imach.c:
500: Summary: Improvement in Powell output in order to copy and paste
501:
502: * imach.c: Summary: Starting tests of 0.99
503:
504: * imach.c: Summary: to valgrind
505:
506: 2016-08-25 Brouard Nicolas <brouard@ined.fr>
507:
508: * imach.c: *** empty log message ***
509:
510: 2016-08-23 Brouard Nicolas <brouard@ined.fr>
511:
512: * imach.c: *** empty log message ***
513:
514: * imach.c: Summary: not working
515:
516: 2016-08-22 Brouard Nicolas <brouard@ined.fr>
517:
518: * imach.c: Summary: not working
519:
520: * imach.c: Summary: Not working
521:
522: 2016-07-23 Brouard Nicolas <brouard@ined.fr>
523:
524: * imach.c: Summary: Completing for func too
525:
526: 2016-07-22 Brouard Nicolas <brouard@ined.fr>
527:
528: * imach.c: Summary: Fixing some arrays, still debugging
529:
530: 2016-07-21 Brouard Nicolas <brouard@ined.fr>
531:
532: * imach.c:
533: Summary: 0.99 working (more or less) for Asian Workshop on multitate methods
534:
535: 2016-07-12 Brouard Nicolas <brouard@ined.fr>
536:
537: * imach.c: Summary: temp
538:
539: * imach.c: Summary: saving but not running
540:
541: 2016-07-01 Brouard Nicolas <brouard@ined.fr>
542:
543: * imach.c: Summary: Fixes
544:
545: 2016-02-19 Brouard Nicolas <brouard@ined.fr>
546:
547: * imach-0.98r.c: Summary: Kind of 0.98r? series, starting with r7
548:
549: * setup.iss, Makefile, version.h: *** empty log message ***
550:
551: * imach.c: Summary: temporary
552:
553: 2016-02-17 Brouard Nicolas <brouard@ined.fr>
554:
555: * imach.c: Summary: Probably last 0.98 stable version 0.98r6
556:
557: 2016-02-16 Brouard Nicolas <brouard@ined.fr>
558:
559: * imach.c: Summary: minor bug
560:
561: * imach.c: Summary: 0.99r2
562:
563: 2016-02-15 Brouard Nicolas <brouard@ined.fr>
564:
565: * imach.c: *** empty log message ***
566:
567: 2016-02-12 Brouard Nicolas <brouard@ined.fr>
568:
569: * imach.c: Summary: 0.99 Back projections
570:
571: 2015-12-23 Brouard Nicolas <brouard@ined.fr>
572:
573: * imach.c: Summary: Experimental backcast
574:
575: 2015-12-18 Brouard Nicolas <brouard@ined.fr>
576:
577: * imach.c: Summary: 0.98r4 Warning and status=-2
578:
579: Version 0.98r4 is now:
580: - displaying an error when status is -1, date of interview unknown and date of death known;
581: - permitting a status -2 when the vital status is unknown at a known date of right truncation.
582: Older changes concerning s=-2, dating from 2005 have been supersed.
583:
584: * Makefile: *** empty log message ***
585:
586: 2015-12-16 Brouard Nicolas <brouard@ined.fr>
587:
588: * Makefile: *** empty log message ***
589:
590: * imach.c: Summary: 0.98r4 working
591:
592: * Makefile: Summary: linuxrpm added
593:
594: * Makefile: *** empty log message ***
595:
596: * imach.c: Summary: temporary not working
597:
598: 2015-12-11 Brouard Nicolas <brouard@ined.fr>
599:
600: * imach.c: Summary: 0.98r4
601:
602: 2015-12-08 Brouard Nicolas <brouard@ined.fr>
603:
604: * Makefile: *** empty log message ***
605:
606: 2015-11-21 Brouard Nicolas <brouard@ined.fr>
607:
608: * Makefile:
609: Summary: VBoxManage change from execute --image to run --exe and --wait-exit doesn't exist any more
610:
611: * imach.c: Summary: minor typo
612:
613: * imach.c: Summary: 0.98r3 with some graph of projected cross-sectional
614:
615: Author: Nicolas Brouard
616:
617: 2015-11-18 Brouard Nicolas <brouard@ined.fr>
618:
619: * imach.c: Summary: Start working on projected prevalences
620:
621: 2015-11-17 Brouard Nicolas <brouard@ined.fr>
622:
623: * imach.c: Summary: Adding ftolpl parameter
624: Author: N Brouard
625:
626: We had difficulties to get smoothed confidence intervals. It was due
627: to the period prevalence which wasn't computed accurately. The inner
628: parameter ftolpl is now an outer parameter of the .imach parameter
629: file after estepm. If ftolpl is small 1.e-4 and estepm too,
630: computation are long.
631:
632: * version.h: *** empty log message ***
633:
634: * imach.c: Summary: temporary
635:
636: 2015-10-27 Brouard Nicolas <brouard@ined.fr>
637:
638: * Makefile: *** empty log message ***
639:
640: * setup.iss.in: Summary: some new subdirs
641:
642: * imach.c: *** empty log message ***
643:
644: * setup.iss.in:
645: Summary: Adding gnuplot 5.1 with bin and etc for pango fonts
646:
647: 2015-10-24 Brouard Nicolas <brouard@ined.fr>
648:
649: * imach.c: *** empty log message ***
650:
651: 2015-10-23 Brouard Nicolas <brouard@ined.fr>
652:
653: * imach.c:
654: Summary: 0.98r3 some clarification for graphs on likelihood contributions
655:
656: 2015-10-01 Brouard Nicolas <brouard@ined.fr>
657:
658: * imach.c: Summary: Some new graphs of contribution to likelihood
659:
660: 2015-09-30 Brouard Nicolas <brouard@ined.fr>
661:
662: * Makefile:
663: Summary: Version read from version.h, itself read with cmake
664:
665: * imach.c: Summary: looking at better estimation of the hessian
666:
667: Also a better criteria for convergence to the period prevalence And
668: therefore adding the number of years needed to converge. (The
669: prevalence in any alive state shold sum to one
670:
671: * Makefile: *** empty log message ***
672:
673: 2015-09-22 Brouard Nicolas <brouard@ined.fr>
674:
675: * imach.c:
676: Summary: Adding some overall graph on contribution to likelihood. Might change
677:
678: 2015-09-15 Brouard Nicolas <brouard@ined.fr>
679:
680: * Makefile: *** empty log message ***
681:
682: * imach.c: Summary: 0.98r0
683:
684: - Some new graphs like survival functions
685: - Some bugs fixed like model=1+age+V2.
686:
687: * ChangeLog, Makefile: Summary: 0.98r0
688:
689: * CMakeLists.txt: Summary: Some tests for setup.iss
690:
691: 2015-09-15 Nicolas J Brouard <nbrouard@tugault.ined.fr>
692:
693: * (Module): 0.98r0 Some new graphs, some bugs fixed: model=1+age+V2. etc
694:
695: 2015-08-18 Nicolas J Brouard <nbrouard@tugault.local>
696:
697: * (Module): Adding error when the covariance matrix doesn't contain the exact number of lines required by the model line.
698:
699: 2015-08-03 Nicolas J Brouard <nbrouard@tugault.ined.fr>
700:
701: * (Module): Changing Variance of one-step probabilities into Standard deviation (thanks to Yao-Chi Shih)
702:
703: 2014-12-16 Nicolas J Brouard <nbrouard@tugault.local>
704:
705: * imach.c (Module): Merging 1.61 to 1.162
706:
707: 2014-09-02 Nicolas J Brouard <nbrouard@njbrouard.ined.fr>
708:
709: * prevlim.h (Module):
710:
711: 2014-01-26 Nicolas J Brouard <nbrouard@ledermann-2.local>
712:
713: * imach.c (Module): Trying to merge old staffs together while being at Tokyo. Not tested...
714: (Module): Version 0.98nR Running ok, but output format still only works for three covariates.
715:
716: 2010-04-29 brouard <brouard@ined.fr>
717:
718: * imach.c (Module): Checking covariates for more complex models
719: than V1+V2. A lot of change to be done. Unstable.
720:
721: 2010-04-26 brouard <brouard@ined.fr>
722:
723: * imach.c (Module): merging some libgsl code. Fixing computation
724: of likelione (using inter/intrapolation if mle = 0) in order to
725: get same likelihood as if mle=1.
726: Some cleaning of code and comments added.
727:
728: 2009-10-29 brouard <brouard@ined.fr>
729:
730: * imach.c (Module): Now imach stops if date of birth, at least year of birth, is not given. Some cleaning of the code.
731:
732: 2006-06-30 Brouard Nicolas <brouard@localhost>
733:
734: * imach.c (Module): Clarifications on computing e.j
735:
736: 2006-04-28 Brouard Nicolas <brouard@localhost>
737:
738: * imach.c (Module): Yes the sum of survivors was wrong since
739: imach-114 because nhstepm was no more computed in the age
740: loop. Now we define nhstepma in the age loop.
741: (Module): In order to speed up (in case of numerous covariates) we
742: compute health expectancies (without variances) in a first step
743: and then all the health expectancies with variances or standard
744: deviation (needs data from the Hessian matrices) which slows the
745: computation.
746: In the future we should be able to stop the program is only health
747: expectancies and graph are needed without standard deviations.
748:
749: 2006-04-04 LIEVRE Agnes <lievre@PC_00697.ined.fr>
750:
751: * imach.iss (Module):
752:
753: * imach.c (Module): bugs in evsi + population file added in htm output file
754:
755: 2006-03-22 LIEVRE Agnes <lievre@PC_00697.ined.fr>
756:
757: * imach.c (Module):
758:
759: 2006-03-20 Brouard Nicolas <brouard@localhost>
760:
761: * imach.c (Module): <title> changed, corresponds to .htm file
762: name. <head> headers where missing.
763:
764: * Makefile (Module): 0.98g
765:
766: * imach.c (Module): Weights can have a decimal point as for
767: English (a comma might work with a correct LC_NUMERIC environment,
768: otherwise the weight is truncated).
769: Modification of warning when the covariates values are not 0 or
770: 1.
771: Version 0.98g
772:
773: 2006-03-16 LIEVRE Agnes <lievre@PC_00697.ined.fr>
774:
775: * imach.c (Module): Comments concerning covariates added
776:
777: * noreg-setup.iss (Module): Version 0.98f
778:
779: * Makefile (Module): Version 0.98f make _windows=1 imachcyg-setup
780:
781: * imach.c (Module): refinements in the computation of lli if
782: status=-2 in order to have more reliable computation if stepm is
783: not 1 month. Version 0.98f
784:
785: 2006-03-15 Brouard Nicolas <brouard@localhost>
786:
787: * imach.c (Module): Bug if status = -2, the loglikelihood was
788: computed as likelihood omitting the logarithm. Version O.98e
789:
790: 2006-03-14 Brouard Nicolas <brouard@localhost>
791:
792: * imach.c (Module): varevsij Comments added explaining the second
793: table of variances if popbased=1 .
794: (Module): Covariances of eij, ekl added, graphs fixed, new html link.
795: (Module): Function pstamp added
796: (Module): Version 0.98d
797:
798: 2006-03-06 Brouard Nicolas <brouard@localhost>
799:
800: * imach.c (Module): Variance-covariance wrong links and
801: varian-covariance of ej. is needed (Saito).
802:
803: 2006-02-27 Brouard Nicolas <brouard@localhost>
804:
805: * imach.c (Module): One freematrix added in mlikeli!
806:
807: 2006-02-26 Brouard Nicolas <brouard@localhost>
808:
809: * imach.c (Module): Some improvements in processing parameter
810: filename with strsep.
811:
812: 2006-02-24 Brouard Nicolas <brouard@localhost>
813:
814: * imach.c (Module): Memory leaks checks with valgrind and:
815: datafile was not closed, some imatrix were not freed and on matrix
816: allocation too.
817:
818: 2006-02-09 LIEVRE Agnes <lievre@PC_00697.ined.fr>
819:
820: * strsep.c (Module): Inclusion because not in mingw32!!!
821:
822: * setup.iss.in (Module): IMACHSETUPVERSION added
823:
824: * noreg-setup.iss (Module): added to cvs tree
825:
826: * Makefile (Module): IMACHSETUPVERSION added
827:
828: 2006-01-30 BROUARD Nicolas <brouard@localhost>
829:
830: * Makefile (Module, Module): Latest Makefile
831:
832: * imach.c (Module): Back to gnuplot.exe instead of wgnuplot.exe
833:
834: 2006-01-27 BROUARD Nicolas <brouard@localhost>
835:
836: * noreg-setup.iss (Module): ADDED
837:
838: 2006-01-24 BROUARD Nicolas <brouard@localhost>
839:
840: * imach.c (Module): Comments (lines starting with a #) are allowed in data.
841:
842: 2005-10-25 Nicolas Brouard <brouard@dhcp171.recherche.ined.fr>
843:
844: * Makefile (Module): Added Imach98.pmsp and howto crete a dmg
845:
846: * createdmg.sh (Module): Creates a dmg disk for MaC OS/X
847:
848: 2005-09-30 <lievre@PC_00595>
849:
850: * imach.c (Module): sump fixed, loop imx fixed, and simplifications.
851: (Module): If the status is missing at the last wave but we know
852: that the person is alive, then we can code his/her status as -2
853: (instead of missing=-1 in earlier versions) and his/her
854: contributions to the likelihood is 1 - Prob of dying from last
855: health status (= 1-p13= p11+p12 in the easiest case of somebody in
856: the healthy state at last known wave). Version is 0.98
857:
858: 2004-05-20 Brouard Nicolas <brouard@localhost>
859:
860: * imach.c (Repository):
861: Agnes added a direct estimation of mortality (without the need of
862: computing period prevalence and differential mortality). Thus here
863: is version 0.97a which has been distributed to some people at
864: REVES 16 in Brugge using an Inno setup.exe for PCs. Estimates of
865: mortality using covariates is not done today. Estimating direct
866: mortality is a very different process because it doesn't need
867: interpolation because it is easy to get the lx from the force of
868: the mortality mux in the simplest case as for a Gompertz (log mux
869: = a + b*x . But we have been able to incorporate the new code
870: within former imach program (0.96d) without deteriorating too much
871: the understanding of the program.
872:
873: 2003-06-25 <brouard@BROUARD>
874:
875: * imach.c (Module): On windows (cygwin) function asctime_r doesn't
876: exist so I changed back to asctime which exists.
877: (Module): Version 0.96b
878:
879: 2003-06-24 <brouard@BROUARD>
880:
881: * imach.c (Module): Some bugs corrected for windows. Also, when
882: mle=-1 a template is output in file "or"mypar.txt with the design
883: of the covariance matrix to be input.
884:
885: 2003-06-25 Brouard Nicolas <brouard@homebrou>
886:
887: * imach.c (Repository): Duplicated warning errors corrected.
888: (Repository): Elapsed time after each iteration is now output. It
889: helps to forecast when convergence will be reached. Elapsed time
890: is stamped in powell. We created a new html file for the graphs
891: concerning matrix of covariance. It has extension -cov.htm.
892:
893: 2003-06-23 Brouard Nicolas <brouard@homebrou>
894:
895: * 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.
896:
897: 2003-06-18 Brouard Nicolas <brouard@homebrou>
898:
899: * imach.c (Repository): Suppress abusive calls to append to file html (solution was to put fichtm as a global variable. Version 0.96
900:
901: 2003-06-17 Brouard Nicolas <brouard@homebrou>
902:
903:
904: * imach.c (Repository): Check when date of death was earlier that
905: current date of interview. It may happen when the death was just
906: prior to the death. In this case, dh was negative and likelihood
907: was wrong (infinity). We still send an "Error" but patch by
908: assuming that the date of death was just one stepm after the
909: interview.
910: (Repository): Because some people have very long ID (first column)
911: we changed int to long in num[] and we added a new lvector for
912: memory allocation. But we also truncated to 8 characters (left
913: truncation)
914:
915: (Repository): No more line truncation errors.
916:
917: 2003-06-14 Brouard Nicolas <brouard@homebrou>
918:
919: * imach.c (Repository): Add of a routine likelione (likelihood
920: only once) which prints on a text file
921: (ilk) the contributions to the likelihood for each
922: individual/wave.
923:
924: 2003-06-13 Brouard Nicolas <brouard@homebrou>
925: * imach.c (Repository): Replace "freqsummary" at a correct
926: place. It differs from routine "prevalence" which may be called
927: many times. Probs is memory consuming and must be used with
928: parcimony.
929:
930: 2003-06-17 <brouard@BROUARD>
931:
932: * timeval.h (Module): Added included file to make use of
933: gettimeofday working on win32 with cygwin.
934:
935: 2003-05-16 Brouard Nicolas <brouard@brouard>
936: * imach.c (Module): Insert of a warning if the delay between two
937: waves is negative.
938:
939: * imach.c (Module):
940:
941: 2003-05-03 <brouard@BROUARD>
942:
943: * imach.c: Some cleaning
944:
945: 2003-03-28 <brouard@BROUARD>
946: * imach.c (Module): In version up to 0.92 likelihood was computed
947: as if date of death was unknown. Death was treated as any other
948: health state: the date of the interview describes the actual state
949: and not the date of a change in health state. The former idea was
950: to consider that at each interview the state was recorded
951: (healthy, disable or death) and IMaCh was corrected; but when we
952: introduced the exact date of death then we should have modified
953: the contribution of an exact death to the likelihood. This new
954: contribution is smaller and very dependent of the step unit
955: stepm. It is no more the probability to die between last interview
956: and month of death but the probability to survive from last
957: interview up to one month before death multiplied by the
958: probability to die within a month. Thanks to Chris
959: Jackson for correcting this bug. Former versions increased
960: mortality artificially. The bad side is that we add another loop
961: which slows down the processing. The difference can be up to 10%
962: lower mortality.
963:
964: 2002-05-30 <brouard@BROUARD>
965:
966: * imach.c (Module): Add correlation matrix of one-step
967: probabilities and covariance matrix
1.54 brouard 968:
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