Annotation of imach/src/ChangeLog, revision 1.73
1.72 brouard 1: 2024-07-02 Nicolas Brouard <brouard@ined.fr>
2:
3: * imach.c (Module): Trying compiling on Linux with clang (instead
4: of gcc which is too slow) and lot of warnings suppressed
5:
1.73 ! brouard 6: 2024-06-28 Nicolas Brouard <brouard@ined.fr>
! 7:
! 8: * imach.c (Module): fixing some bugs in gnuplot and quantitative variables, but not completely solved
! 9:
1.72 brouard 10: 2024-06-28 Nicolas Brouard <brouard@ined.fr>
1.71 brouard 11:
12: * imach.c (Module): s6 errors with age*age (harmless).
13:
1.70 brouard 14: 2024-05-12 Nicolas Brouard <brouard@ined.fr>
15:
16: * imach.c Version 0.99s5 In fact, the covariance of total life
17: expectancy e.. with a partial life expectancy e.j is high,
18: therefore the complete matrix of variance covariance has to be
19: included in the formula of the standard error of the proportion of
20: total life expectancy spent in a specific state:
21: var(X/Y)=mu_x^2/mu_y^2*(sigma_x^2/mu_x^2 -2
22: sigma_xy/mu_x/mu_y+sigma^2/mu_y^2). Also an error with mle=-3
23: made the program core dump. It is fixed in this version.
24:
1.69 brouard 25: 2024-04-30 Nicolas Brouard <brouard@ined.fr>
26:
27: * (Module): In version 0.99s4, we incorporated the calculation of
28: the std error of the proportion of total life expectancy spent in
29: a specific state Var(e.j/e..) using the formula of Var(X/Y)
30: depending only of the variances of X and Y and expectancies.
31:
1.68 brouard 32: 2024-04-24 Nicolas Brouard <brouard@ined.fr>
33:
34: * (Module): This version comes late after having tested
35: successfully the praxis C version of Buckhardt. But Buckardt's
36: version was difficult to read and Gegenfurtner's version had a few
37: typos which made its results less reliable than Buckhardt's
38: results. The most important work consisted in retyping the Brent
39: original PRAXIS program written in Algol W (published with errors,
40: ommitting the transposition of matrix V before its QR reduction
41: from Golub. I used the recent "awe" compiler from Gkynn Webster.
42: The awe library had errors, for example in arc tangent function
43: which have been fixed.
44:
45: The main objective was to get identical results with the three
46: versions: (1) Algol W, (2) Buckhardt'C version as well (3)
47: Gegenfürtner C versions on the various test functions published by
48: Brent in 1973 in Algol W.
49:
50: Also, in order to compare them, the random function had to produce
51: the same sequence for the 3 softwares. The random function used in
52: imach corresponds to original Brent's random function written in
53: Algol W. Other point, in Algol W, the arrays of dimension n are
54: 'normal' mathematical arrays starting from 1 to n. But this is a
55: real issue in C where, by default, arrays are starting from 0 to
56: n-1. In Buckhardt, as well as in Gegenfürtner C code, it can be
57: seen that authors while trying to mimick original Brent Algol W
58: code are hesitating by changing either a loop originally from 1 to
59: n in a loop from 0 to n-1, or keeping Brent's loop from 1 to n and
60: shifting the index from original X(I) in Algol W to x[i-1] in C.
61: But as IMaCh is using, since the beginning, the Numerical Recipes
62: functions vector or matrix, I changed Geggenfürtner code to mimick
63: the original Algol W arrays. Thus the X(I) is translated in C as
64: x[i] which minimizes the errors. The Golub QR algorithm was
65: published in Algol with overflow errors which were reproduced in
66: Brent's Algol W code. Buckhardt code fixed these errors which are
67: much more problematic in C than in Algol W. Thus Buckhardt code
68: seems very safe, but i haven't chosen it for IMaCh because the C
69: style is horrible and almost unreadable compared to Gegenfürtner
70: CO code which is very close to Brent's original. Also what makes
71: Buckhardt code more difficult to read is, instead of passing the
72: minimum of parameters in the functions calls, as it is in Algol
73: Brent's code or Gegenfürtner's code, the list of parameters is
74: high. For example, the flin function LONG REAL PROCEDURE FLIN
75: (LONG REAL VALUE L) has only one parameter in Algol W, the
76: Gegenfürtner flin function had two parameters: static double
77: flin(l, j) double l; { int i; double tflin[N];} but Buckhardt
78: function has 14 parameters which makes the code unreadable and
79: useless. Gegenfürtner used a lot of static variables or functions
80: which I tried to minimize. Also in Gegefürtner, array dimensions
81: were fixed to N. In my adaptation the flin is static double
82: flin(double l, int j) and the parameter used are global variables.
83:
84: 2023-06-14 Nicolas Brouard <brouard@ined.fr>
85:
86: * imach.c (Module): Testing if conjugate gradient could be quicker
87: when lot of variables POWELLORIGINCONJUGATE
88:
1.67 brouard 89: 2023-05-23 Nicolas Brouard <brouard@ined.fr>
90:
91: * imach.c (Module): Fixed PROB_r
92:
93: 2023-05-22 Nicolas Brouard <brouard@ined.fr>
94:
95: * imach.c (Module): In the ILK....txt file, the number of columns
96: before the covariates values is dependent of the number of states (16+nlstate): 0.99r46
97:
1.66 brouard 98: 2023-05-08 Nicolas Brouard <brouard@ined.fr>
99:
100: * (Module): Error V0 when result:. and model 1+age+V1: fixed
101:
1.63 brouard 102: 2023-04-29 Nicolas Brouard <brouard@ined.fr>
103:
104: * imach.c (Module): Inverting the model equation and fixingg bugs
105: in the drawings
106: "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"
107:
108: 2023-04-24 Nicolas Brouard <brouard@ined.fr>
109:
110: * imach.c (Module): some bugs in printinggnuplot
111:
1.62 brouard 112: 2022-09-19 Nicolas Brouard <brouard@ined.fr>
113:
114: * imach.c (Module): Version 0.99r42 needed a newer version of
115: Gnuplot. But newer version 0.99r43 should run with the Gnuplot
116: version 5.0 or 5.1 distributed with IMaCh.
117:
1.61 brouard 118: 2022-09-18 Nicolas Brouard <brouard@ined.fr>
119:
120: * imach.c (Module): Fixing when a state in the data is 0 or higher
121: than lstate+ndeath. Fixing the plot of contribution to Likelihood.
122:
1.63 brouard 123: 2022-09-16 Nicolas Brouard <brouard@ined.fr>
124:
125: * imach.c (Module): 0.99r41 Was an error when product of timevarying and fixed. Using FixedV[of name] now. Thank you Feinuo
126:
127: 2022-09-14 Nicolas Brouard <brouard@ined.fr>
128:
129: * imach.c (Module): Fixing names of variables in T_ (thanks to Feinuo)
130:
1.61 brouard 131: 2022-09-14 Nicolas Brouard <brouard@ined.fr>
132:
133: * imach.c (Module): Version 0.99r39 with colored dummy covariates
134: (fixed or time varying), using new last columns of
135: ILK_parameter.txt file.
136:
1.60 brouard 137: 2022-09-11 Nicolas Brouard <brouard@ined.fr>
138:
139: * imach.c (Module): Adding timevarying products of any kinds,
140: should work before shifting cotvar from ncovcol+nqv columns in
141: order to have a correspondance between the column of cotvar and
142: the id of column.
1.61 brouard 143: (Module): Some cleaning and adding covariates in ILK.txt
1.60 brouard 144:
145: 2022-09-09 Nicolas Brouard <brouard@ined.fr>
146:
147: * imach.c (Module): Many improvements for fixing products of fixed
148: timevarying as well as fixed * fixed, and test with quantitative
149: covariate.
150:
1.59 brouard 151: 2022-09-04 Nicolas Brouard <brouard@ined.fr>
152:
153: * imach.c (Module): Now the easy runs i.e. without result or
154: model=1+age only did not work. The defautl combination should be 1
155: and not 0 because everything hasn't been tranformed yet.
156:
157: 2022-09-02 Nicolas Brouard <brouard@ined.fr>
158:
159: * imach.c: Version 0.99r35 because it outputs same results with
160: 1+age+V1+V1*age for females and 1+age for females only
161: (education=1 noweight)
162:
1.58 brouard 163: 2022-08-31 Nicolas Brouard <brouard@ined.fr>
164:
165: * imach.c (Module): Some improvments in fichtm and many verifications 0.99r34
166:
1.56 brouard 167: 2022-08-21 Nicolas Brouard <brouard@ined.fr>
168:
169: * imach.c (Module): Version 0.99r33 A lot of changes in
170: reassigning covariates: my first idea was that people will always
171: use the first covariate V1 into the model but in fact they are
172: producing data with many covariates and can use an equation model
173: with some of the covariate; it means that in a model V2+V3 instead
174: of codtabm(k,Tvaraff[j]) which calculates for combination k, for
175: three covariates (V1, V2, V3) the value of Tvaraff[j], but in fact
176: the equation model is restricted to two variables only (V2, V3)
177: and the combination for V2 should be codtabm(k,1) instead of
178: (codtabm(k,2), and the code should be
179: codtabm(k,TnsdVar[Tvaraff[j]]. Many many changes have been
180: made. All of these should be simplified once a day like we did in
181: hpxij() for example by using precov[nres] which is computed in
182: decoderesult for each nres of each resultline. Loop should be done
183: on the equation model globally by distinguishing only product with
184: age (which are changing with age) and no more on type of
185: covariates, single dummies, single covariates.
186:
187: 2022-08-06 Nicolas Brouard <brouard@ined.fr>
188:
189: * imach.c (Module): Version of imach using partly decoderesult to rebuild xpxij function
190:
191: 2022-08-03 Nicolas Brouard <brouard@ined.fr>
192:
193: * imach.c (Module): Many errors in graphs fixed with Vn*age covariates.
194:
1.55 brouard 195: 2022-07-25 Brouard Nicolas <brouard@brouard.name>
196:
197: * imach.c (Module): Error cptcovn instead of nsd in bmij (was
198: coredumped, revealed by Feiuno, thank you.
1.57 brouard 199:
200: 2022-07-23 Nicolas Brouard <brouard@ined.fr>
201:
202: * r29 W and not sqrt(Wald)
203:
204: 2022-07-22 Nicolas Brouard <brouard@ined.fr>
205:
206: * imach.c (Module): Output of Wald test in the htm file and not only in the log.
207:
1.55 brouard 208: 2022-06-02 Brouard Nicolas <brouard@brouard.name>
209:
210: * imach.c (Module): Adding the Wald tests from the log to the main
1.65 brouard 211: htm for better display of the maximum likelihood estimators.
1.57 brouard 212:
1.65 brouard 213: 2022-05-30 Brouard Nicolas <brouard@brouard.name>
214:
215: * imach.c: With products of covariates (age or dummies or
216: quantitatives), estimates of parameters were good but when
217: estimating variances the positions of newly created covariates
218: were wrongly assigned and results were wrong. Thank to Feinua_Sun!
219:
220: 2022-05-24 Nicolas Brouard <brouard@ined.fr>
221:
222: * imach.c (Module): Some attempts to find a bug of wrong estimates
223: of confidencce intervals with product in the equation modelC
224:
225: 2022-05-15 Nicolas Brouard <brouard@ined.fr>
226:
227: * imach.c (Module): Some minor improvements
228:
229: 2022-04-13 Brouard Nicolas <brouard@brouard.name>
230:
231: * imach.c (Module): Adding link to text data files
232:
233: 2022-04-11 Nicolas Brouard <brouard@ined.fr>
234:
235: * imach.c (Module): Error in rewriting the 'r' file with yearsfproj or yearsbproj fixed
236:
237: 2022-04-05 Brouard Nicolas <brouard@ined.fr>
238:
239: * imach.c (Module): Fixed covariates (dummy or quantitative)
240: with missing values have never been allowed but are ERRORS and
241: program quits. Standard deviations of fixed covariates were
242: wrongly computed. Mean and standard deviations of time varying
243: covariates are still not computed.
244:
245: 2022-03-17 Brouard Nicolas <brouard@ined.fr>
246:
247: * 99r25 Improvements in fixing discrepancies between covariates
248: missing in result line but in model.
249:
250: *Wed Mar 31 2021 Nicolas Brouard <brouard@ined.fr>
251: * imach.c (Module): Still bugs in the result loop. Thank to Holly Benett
252:
253: *2021-03-08 Nicolas Brouard <brouard@ined.fr>
254:
255: * ./ (Module): Fixed bug on result:
256:
257: *2021-02-20 Nicolas Brouard <brouard@ined.fr>
258:
259: * imach.c (Module): Fix bug on quitting after result lines!
260: (Module): Version 0.99r21
261:
262: 2021-02-12 Nicolas Brouard <brouard@ined.fr>
263:
264: * imach.c (Module): The use of a Windows BOM (huge) file is now an error
265:
266:
267: 2021-02-11 Nicolas Brouard <brouard@ined.fr>
268:
269: * (Module): imach.c Someone entered 'results:' instead of 'result:'. Now it is an error which is printed.
270:
271: 2020-02-22 Brouard Nicolas <brouard@ined.fr>
272:
273: * (Module): imach.c Update mle=-3 (for computing Life expectancy
274: and life table from the data without any state)
275:
276: 2019-05-20 Brouard Nicolas <brouard@ined.fr>
277:
278: * version.h: Summary: version 0.99.r19
279:
280: * imach.c: Summary: Projection syntax simplified
281: We can now start projections, forward or backward, from the mean date
282: of inteviews up to or down to a number of years of projection:
283: prevforecast=1 yearsfproj=15.3 mobil_average=0
284: or
285: prevforecast=1 starting-proj-date=1/1/2007 final-proj-date=12/31/2017 mobil_average=0
286: or
287: prevbackcast=1 yearsbproj=12.3 mobil_average=1
288: or
289: prevbackcast=1 starting-back-date=1/10/1999 final-back-date=1/1/1985 mobil_average=1
290:
291: 2019-05-18 Brouard Nicolas <brouard@ined.fr>
292:
293: * imach.c: Summary: doxygen tex bug
294:
295: 2019-05-16 Brouard Nicolas <brouard@ined.fr>
296:
297: * imach.c: Summary: There was some wrong lines added
298:
299: 2019-05-09 Brouard Nicolas <brouard@ined.fr>
300:
301: * Makefile, imach.c: *** empty log message ***
302:
303: * ChangeLog: Summary: C=
304:
305: * imach.c: Summary: Some updates
306:
307: * imach.c: Summary: Before ncovmax
308:
309: * version.h: *** empty log message ***
310:
311: * imach.c: Summary: 0.99r18 unlimited number of individuals
312: 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.
313:
314: 2018-12-13 Brouard Nicolas <brouard@ined.fr>
315:
316: * imach.c: Summary: Bug for young ages (<-30) will be in r17
317:
318: 2018-12-05 Brouard Nicolas <brouard@ined.fr>
319:
320: * Makefile: Summary: 0.99r16
321:
322: 2018-05-02 Brouard Nicolas <brouard@ined.fr>
323:
324: * imach.c: Summary: Some bugs fixed
325:
326: 2018-05-02 Brouard Nicolas <brouard@ined.fr>
327:
328: * imach.c: Summary: Bug for young ages (<-30) will be in r17
329:
330: 2018-05-02 Brouard Nicolas <brouard@ined.fr>
331:
332: * imach.c: Summary: Some bugs fixed
333:
334: 2018-05-01 Brouard Nicolas <brouard@ined.fr>
335:
336: * imach.c:
337: Summary: Bug fixed by providing frequencies only for non missing covariates
338:
339: 2018-04-27 Brouard Nicolas <brouard@ined.fr>
340:
341: * imach.c: Summary: some minor bugs
342:
343: 2018-04-21 Brouard Nicolas <brouard@ined.fr>
344:
345: * README.txt: *** empty log message ***
346:
347: * imach.c: Summary: Some bugs fixed, valgrind tested
348:
349: 2018-04-20 Brouard Nicolas <brouard@ined.fr>
350:
351: * Makefile, README.txt, setup.iss: Summary: imach 0.99r16
352:
353: * imach.c:
354: Summary: Computing mean and stdeviation of fixed quantitative variables
355:
356: 2018-04-19 Brouard Nicolas <brouard@ined.fr>
357:
358: * imach.c: Summary: Some minor bugs fixed
359:
360: * version.h: *** empty log message ***
361:
362: 2018-02-27 Brouard Nicolas <brouard@ined.fr>
363:
364: * imach.c: *** empty log message ***
365:
366: * imach.c: Summary: Adding second argument for quitting
367:
368: 2018-02-21 Brouard Nicolas <brouard@ined.fr>
369:
370: * Makefile, README.txt, imach.c: Summary: 0.99r15
371: New Makefile with recent VirtualBox 5.26. Bug in sqrt negatve in imach.c
372:
373: 2017-07-20 Brouard Nicolas <brouard@ined.fr>
374:
375: * imach.c: Summary: temporary working
376:
377: 2017-07-19 Brouard Nicolas <brouard@ined.fr>
378:
379: * imach.c: Summary: Bug for mobil_average=0 and prevforecast fixed(?)
380:
381: 2017-07-17 Brouard Nicolas <brouard@ined.fr>
382:
383: * imach.c: Summary: BOM files can be read now
384:
385: 2017-06-30 Brouard Nicolas <brouard@ined.fr>
386:
387: * imach.c: Summary: Graphs improvements
388:
389: * imach.c: Summary: Saito's color
390:
391: 2017-06-29 Brouard Nicolas <brouard@ined.fr>
392:
393: * imach.c: Summary: Version 0.99r14
394:
395: 2017-06-27 Brouard Nicolas <brouard@ined.fr>
396:
397: * imach.c: Summary: More documentation on projections
398:
399: * imach.c: Summary: Color of backprojection changed from 6 to 5(yellow)
400:
401: * imach.c: Summary: Some bug with rint
402:
403: 2017-05-24 Brouard Nicolas <brouard@ined.fr>
404:
405: * imach.c: *** empty log message ***
406:
407: 2017-05-23 Brouard Nicolas <brouard@ined.fr>
408:
409: * imach.c: Summary: Code into subroutine, cleanings
410:
411: 2017-05-18 Brouard Nicolas <brouard@ined.fr>
412:
413: * imach.c:
414: Summary: backprojection and confidence intervals of backprevalence
415:
416: 2017-05-13 Brouard Nicolas <brouard@ined.fr>
417:
418: * imach.c: Summary: temporary save for backprojection
419:
420: * imach.c: Summary: Version 0.99r13 (improvements and bugs fixed)
421:
422: 2017-04-26 Brouard Nicolas <brouard@ined.fr>
423:
424: * imach.c: Summary: imach 0.99r13 Some bugs fixed
425:
426: * imach.c: Summary: Labels in graphs
427:
428: 2017-04-24 Brouard Nicolas <brouard@ined.fr>
429:
430: * imach.c: Summary: to save
431:
432: 2017-04-18 Brouard Nicolas <brouard@ined.fr>
433:
434: * imach.c: *** empty log message ***
435:
436: 2017-04-05 Brouard Nicolas <brouard@ined.fr>
437:
438: * imach.c: Summary: Bug in E_ as well as in T_ fixed nres-1 vs k1-1
439:
440: 2017-04-04 Brouard Nicolas <brouard@ined.fr>
441:
442: * imach.c: Summary: Gnuplot indexations fixed (humm)
443:
444: * imach.c:
445: Summary: Some errors to warnings only if date of death is unknown but status is death we could set to pi3
446:
447: 2017-04-03 Brouard Nicolas <brouard@ined.fr>
448:
449: * imach.c: Summary: Version 0.99r12
450: Some cleanings, conformed with updated documentation.
451:
452: 2017-03-30 Brouard Nicolas <brouard@ined.fr>
453:
454: * version.h: *** empty log message ***
455:
456: * version.h: Summary:0.99r11
457:
458: 2017-03-29 Brouard Nicolas <brouard@ined.fr>
459:
460: * imach.c: Summary: Temp
461:
462: 2017-03-27 Brouard Nicolas <brouard@ined.fr>
463:
464: * imach.c: Summary: Temporary
465:
466: 2017-03-08 Brouard Nicolas <brouard@ined.fr>
467:
468: * imach.c: Summary: IMaCh version 0.99r10 bugs in gnuplot fixed
469:
470: * imach.c: Summary: Fixing data parameter line
471:
472: 2016-12-15 Brouard Nicolas <brouard@ined.fr>
473:
474: * imach.c: Summary: 0.99 in progress
475:
476: 2016-09-15 Brouard Nicolas <brouard@ined.fr>
477:
478: * imach.c: *** empty log message ***
479:
480: * imach.c: Summary: not working
481:
482: 2016-09-08 Brouard Nicolas <brouard@ined.fr>
483:
484: * imach.c: Summary: continue
485:
486: 2016-09-07 Brouard Nicolas <brouard@ined.fr>
487:
488: * imach.c: Summary: Starting values from frequencies
489:
490: * imach.c: *** empty log message ***
491:
492: 2016-09-02 Brouard Nicolas <brouard@ined.fr>
493:
494: * imach.c: *** empty log message ***
495:
496: 2016-08-30 Brouard Nicolas <brouard@ined.fr>
497:
498: * imach.c: Summary: Fixing a lots
499:
500: 2016-08-29 Brouard Nicolas <brouard@ined.fr>
501:
502: * imach.c: Summary: gnuplot problem in Back projection to fix
503:
504: * imach.c: Summary: Better
505:
506: 2016-08-26 Brouard Nicolas <brouard@ined.fr>
507:
508: * imach.c:
509: Summary: Improvement in Powell output in order to copy and paste
510:
511: * imach.c: Summary: Starting tests of 0.99
512:
513: * imach.c: Summary: to valgrind
514:
515: 2016-08-25 Brouard Nicolas <brouard@ined.fr>
516:
517: * imach.c: *** empty log message ***
518:
519: 2016-08-23 Brouard Nicolas <brouard@ined.fr>
520:
521: * imach.c: *** empty log message ***
522:
523: * imach.c: Summary: not working
524:
525: 2016-08-22 Brouard Nicolas <brouard@ined.fr>
526:
527: * imach.c: Summary: not working
528:
529: * imach.c: Summary: Not working
530:
531: 2016-07-23 Brouard Nicolas <brouard@ined.fr>
532:
533: * imach.c: Summary: Completing for func too
534:
535: 2016-07-22 Brouard Nicolas <brouard@ined.fr>
536:
537: * imach.c: Summary: Fixing some arrays, still debugging
538:
539: 2016-07-21 Brouard Nicolas <brouard@ined.fr>
540:
541: * imach.c:
542: Summary: 0.99 working (more or less) for Asian Workshop on multitate methods
543:
544: 2016-07-12 Brouard Nicolas <brouard@ined.fr>
545:
546: * imach.c: Summary: temp
547:
548: * imach.c: Summary: saving but not running
549:
550: 2016-07-01 Brouard Nicolas <brouard@ined.fr>
551:
552: * imach.c: Summary: Fixes
553:
554: 2016-02-19 Brouard Nicolas <brouard@ined.fr>
555:
556: * imach-0.98r.c: Summary: Kind of 0.98r? series, starting with r7
557:
558: * setup.iss, Makefile, version.h: *** empty log message ***
559:
560: * imach.c: Summary: temporary
561:
562: 2016-02-17 Brouard Nicolas <brouard@ined.fr>
563:
564: * imach.c: Summary: Probably last 0.98 stable version 0.98r6
565:
566: 2016-02-16 Brouard Nicolas <brouard@ined.fr>
567:
568: * imach.c: Summary: minor bug
569:
570: * imach.c: Summary: 0.99r2
571:
572: 2016-02-15 Brouard Nicolas <brouard@ined.fr>
573:
574: * imach.c: *** empty log message ***
575:
576: 2016-02-12 Brouard Nicolas <brouard@ined.fr>
577:
578: * imach.c: Summary: 0.99 Back projections
579:
580: 2015-12-23 Brouard Nicolas <brouard@ined.fr>
581:
582: * imach.c: Summary: Experimental backcast
583:
584: 2015-12-18 Brouard Nicolas <brouard@ined.fr>
585:
586: * imach.c: Summary: 0.98r4 Warning and status=-2
587:
588: Version 0.98r4 is now:
589: - displaying an error when status is -1, date of interview unknown and date of death known;
590: - permitting a status -2 when the vital status is unknown at a known date of right truncation.
591: Older changes concerning s=-2, dating from 2005 have been supersed.
592:
593: * Makefile: *** empty log message ***
594:
595: 2015-12-16 Brouard Nicolas <brouard@ined.fr>
596:
597: * Makefile: *** empty log message ***
598:
599: * imach.c: Summary: 0.98r4 working
600:
601: * Makefile: Summary: linuxrpm added
602:
603: * Makefile: *** empty log message ***
604:
605: * imach.c: Summary: temporary not working
606:
607: 2015-12-11 Brouard Nicolas <brouard@ined.fr>
608:
609: * imach.c: Summary: 0.98r4
610:
611: 2015-12-08 Brouard Nicolas <brouard@ined.fr>
612:
613: * Makefile: *** empty log message ***
614:
615: 2015-11-21 Brouard Nicolas <brouard@ined.fr>
616:
617: * Makefile:
618: Summary: VBoxManage change from execute --image to run --exe and --wait-exit doesn't exist any more
619:
620: * imach.c: Summary: minor typo
621:
622: * imach.c: Summary: 0.98r3 with some graph of projected cross-sectional
623:
624: Author: Nicolas Brouard
625:
626: 2015-11-18 Brouard Nicolas <brouard@ined.fr>
627:
628: * imach.c: Summary: Start working on projected prevalences
629:
630: 2015-11-17 Brouard Nicolas <brouard@ined.fr>
631:
632: * imach.c: Summary: Adding ftolpl parameter
633: Author: N Brouard
634:
635: We had difficulties to get smoothed confidence intervals. It was due
636: to the period prevalence which wasn't computed accurately. The inner
637: parameter ftolpl is now an outer parameter of the .imach parameter
638: file after estepm. If ftolpl is small 1.e-4 and estepm too,
639: computation are long.
640:
641: * version.h: *** empty log message ***
642:
643: * imach.c: Summary: temporary
644:
645: 2015-10-27 Brouard Nicolas <brouard@ined.fr>
646:
647: * Makefile: *** empty log message ***
648:
649: * setup.iss.in: Summary: some new subdirs
650:
651: * imach.c: *** empty log message ***
652:
653: * setup.iss.in:
654: Summary: Adding gnuplot 5.1 with bin and etc for pango fonts
655:
656: 2015-10-24 Brouard Nicolas <brouard@ined.fr>
657:
658: * imach.c: *** empty log message ***
659:
660: 2015-10-23 Brouard Nicolas <brouard@ined.fr>
661:
662: * imach.c:
663: Summary: 0.98r3 some clarification for graphs on likelihood contributions
664:
665: 2015-10-01 Brouard Nicolas <brouard@ined.fr>
666:
667: * imach.c: Summary: Some new graphs of contribution to likelihood
668:
669: 2015-09-30 Brouard Nicolas <brouard@ined.fr>
670:
671: * Makefile:
672: Summary: Version read from version.h, itself read with cmake
673:
674: * imach.c: Summary: looking at better estimation of the hessian
675:
676: Also a better criteria for convergence to the period prevalence And
677: therefore adding the number of years needed to converge. (The
678: prevalence in any alive state shold sum to one
679:
680: * Makefile: *** empty log message ***
681:
682: 2015-09-22 Brouard Nicolas <brouard@ined.fr>
683:
684: * imach.c:
685: Summary: Adding some overall graph on contribution to likelihood. Might change
686:
687: 2015-09-15 Brouard Nicolas <brouard@ined.fr>
688:
689: * Makefile: *** empty log message ***
690:
691: * imach.c: Summary: 0.98r0
692:
693: - Some new graphs like survival functions
694: - Some bugs fixed like model=1+age+V2.
695:
696: * ChangeLog, Makefile: Summary: 0.98r0
697:
698: * CMakeLists.txt: Summary: Some tests for setup.iss
699:
700: 2015-09-15 Nicolas J Brouard <nbrouard@tugault.ined.fr>
701:
702: * (Module): 0.98r0 Some new graphs, some bugs fixed: model=1+age+V2. etc
703:
704: 2015-08-18 Nicolas J Brouard <nbrouard@tugault.local>
705:
706: * (Module): Adding error when the covariance matrix doesn't contain the exact number of lines required by the model line.
707:
708: 2015-08-03 Nicolas J Brouard <nbrouard@tugault.ined.fr>
709:
710: * (Module): Changing Variance of one-step probabilities into Standard deviation (thanks to Yao-Chi Shih)
711:
712: 2014-12-16 Nicolas J Brouard <nbrouard@tugault.local>
713:
714: * imach.c (Module): Merging 1.61 to 1.162
715:
716: 2014-09-02 Nicolas J Brouard <nbrouard@njbrouard.ined.fr>
717:
718: * prevlim.h (Module):
719:
720: 2014-01-26 Nicolas J Brouard <nbrouard@ledermann-2.local>
721:
722: * imach.c (Module): Trying to merge old staffs together while being at Tokyo. Not tested...
723: (Module): Version 0.98nR Running ok, but output format still only works for three covariates.
724:
725: 2010-04-29 brouard <brouard@ined.fr>
726:
727: * imach.c (Module): Checking covariates for more complex models
728: than V1+V2. A lot of change to be done. Unstable.
729:
730: 2010-04-26 brouard <brouard@ined.fr>
731:
732: * imach.c (Module): merging some libgsl code. Fixing computation
733: of likelione (using inter/intrapolation if mle = 0) in order to
734: get same likelihood as if mle=1.
735: Some cleaning of code and comments added.
736:
737: 2009-10-29 brouard <brouard@ined.fr>
738:
739: * imach.c (Module): Now imach stops if date of birth, at least year of birth, is not given. Some cleaning of the code.
740:
741: 2006-06-30 Brouard Nicolas <brouard@localhost>
742:
743: * imach.c (Module): Clarifications on computing e.j
744:
745: 2006-04-28 Brouard Nicolas <brouard@localhost>
746:
747: * imach.c (Module): Yes the sum of survivors was wrong since
748: imach-114 because nhstepm was no more computed in the age
749: loop. Now we define nhstepma in the age loop.
750: (Module): In order to speed up (in case of numerous covariates) we
751: compute health expectancies (without variances) in a first step
752: and then all the health expectancies with variances or standard
753: deviation (needs data from the Hessian matrices) which slows the
754: computation.
755: In the future we should be able to stop the program is only health
756: expectancies and graph are needed without standard deviations.
757:
758: 2006-04-04 LIEVRE Agnes <lievre@PC_00697.ined.fr>
759:
760: * imach.iss (Module):
761:
762: * imach.c (Module): bugs in evsi + population file added in htm output file
763:
764: 2006-03-22 LIEVRE Agnes <lievre@PC_00697.ined.fr>
765:
766: * imach.c (Module):
767:
768: 2006-03-20 Brouard Nicolas <brouard@localhost>
769:
770: * imach.c (Module): <title> changed, corresponds to .htm file
771: name. <head> headers where missing.
772:
773: * Makefile (Module): 0.98g
774:
775: * imach.c (Module): Weights can have a decimal point as for
776: English (a comma might work with a correct LC_NUMERIC environment,
777: otherwise the weight is truncated).
778: Modification of warning when the covariates values are not 0 or
779: 1.
780: Version 0.98g
781:
782: 2006-03-16 LIEVRE Agnes <lievre@PC_00697.ined.fr>
783:
784: * imach.c (Module): Comments concerning covariates added
785:
786: * noreg-setup.iss (Module): Version 0.98f
787:
788: * Makefile (Module): Version 0.98f make _windows=1 imachcyg-setup
789:
790: * imach.c (Module): refinements in the computation of lli if
791: status=-2 in order to have more reliable computation if stepm is
792: not 1 month. Version 0.98f
793:
794: 2006-03-15 Brouard Nicolas <brouard@localhost>
795:
796: * imach.c (Module): Bug if status = -2, the loglikelihood was
797: computed as likelihood omitting the logarithm. Version O.98e
798:
799: 2006-03-14 Brouard Nicolas <brouard@localhost>
800:
801: * imach.c (Module): varevsij Comments added explaining the second
802: table of variances if popbased=1 .
803: (Module): Covariances of eij, ekl added, graphs fixed, new html link.
804: (Module): Function pstamp added
805: (Module): Version 0.98d
806:
807: 2006-03-06 Brouard Nicolas <brouard@localhost>
808:
809: * imach.c (Module): Variance-covariance wrong links and
810: varian-covariance of ej. is needed (Saito).
811:
812: 2006-02-27 Brouard Nicolas <brouard@localhost>
813:
814: * imach.c (Module): One freematrix added in mlikeli!
815:
816: 2006-02-26 Brouard Nicolas <brouard@localhost>
817:
818: * imach.c (Module): Some improvements in processing parameter
819: filename with strsep.
820:
821: 2006-02-24 Brouard Nicolas <brouard@localhost>
822:
823: * imach.c (Module): Memory leaks checks with valgrind and:
824: datafile was not closed, some imatrix were not freed and on matrix
825: allocation too.
826:
827: 2006-02-09 LIEVRE Agnes <lievre@PC_00697.ined.fr>
828:
829: * strsep.c (Module): Inclusion because not in mingw32!!!
830:
831: * setup.iss.in (Module): IMACHSETUPVERSION added
832:
833: * noreg-setup.iss (Module): added to cvs tree
834:
835: * Makefile (Module): IMACHSETUPVERSION added
836:
837: 2006-01-30 BROUARD Nicolas <brouard@localhost>
838:
839: * Makefile (Module, Module): Latest Makefile
840:
841: * imach.c (Module): Back to gnuplot.exe instead of wgnuplot.exe
842:
843: 2006-01-27 BROUARD Nicolas <brouard@localhost>
844:
845: * noreg-setup.iss (Module): ADDED
846:
847: 2006-01-24 BROUARD Nicolas <brouard@localhost>
848:
849: * imach.c (Module): Comments (lines starting with a #) are allowed in data.
850:
851: 2005-10-25 Nicolas Brouard <brouard@dhcp171.recherche.ined.fr>
852:
853: * Makefile (Module): Added Imach98.pmsp and howto crete a dmg
854:
855: * createdmg.sh (Module): Creates a dmg disk for MaC OS/X
856:
857: 2005-09-30 <lievre@PC_00595>
858:
859: * imach.c (Module): sump fixed, loop imx fixed, and simplifications.
860: (Module): If the status is missing at the last wave but we know
861: that the person is alive, then we can code his/her status as -2
862: (instead of missing=-1 in earlier versions) and his/her
863: contributions to the likelihood is 1 - Prob of dying from last
864: health status (= 1-p13= p11+p12 in the easiest case of somebody in
865: the healthy state at last known wave). Version is 0.98
866:
867: 2004-05-20 Brouard Nicolas <brouard@localhost>
868:
869: * imach.c (Repository):
870: Agnes added a direct estimation of mortality (without the need of
871: computing period prevalence and differential mortality). Thus here
872: is version 0.97a which has been distributed to some people at
873: REVES 16 in Brugge using an Inno setup.exe for PCs. Estimates of
874: mortality using covariates is not done today. Estimating direct
875: mortality is a very different process because it doesn't need
876: interpolation because it is easy to get the lx from the force of
877: the mortality mux in the simplest case as for a Gompertz (log mux
878: = a + b*x . But we have been able to incorporate the new code
879: within former imach program (0.96d) without deteriorating too much
880: the understanding of the program.
881:
882: 2003-06-25 <brouard@BROUARD>
883:
884: * imach.c (Module): On windows (cygwin) function asctime_r doesn't
885: exist so I changed back to asctime which exists.
886: (Module): Version 0.96b
887:
888: 2003-06-24 <brouard@BROUARD>
889:
890: * imach.c (Module): Some bugs corrected for windows. Also, when
891: mle=-1 a template is output in file "or"mypar.txt with the design
892: of the covariance matrix to be input.
893:
894: 2003-06-25 Brouard Nicolas <brouard@homebrou>
895:
896: * imach.c (Repository): Duplicated warning errors corrected.
897: (Repository): Elapsed time after each iteration is now output. It
898: helps to forecast when convergence will be reached. Elapsed time
899: is stamped in powell. We created a new html file for the graphs
900: concerning matrix of covariance. It has extension -cov.htm.
901:
902: 2003-06-23 Brouard Nicolas <brouard@homebrou>
903:
904: * 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.
905:
906: 2003-06-18 Brouard Nicolas <brouard@homebrou>
907:
908: * imach.c (Repository): Suppress abusive calls to append to file html (solution was to put fichtm as a global variable. Version 0.96
909:
910: 2003-06-17 Brouard Nicolas <brouard@homebrou>
911:
912:
913: * imach.c (Repository): Check when date of death was earlier that
914: current date of interview. It may happen when the death was just
915: prior to the death. In this case, dh was negative and likelihood
916: was wrong (infinity). We still send an "Error" but patch by
917: assuming that the date of death was just one stepm after the
918: interview.
919: (Repository): Because some people have very long ID (first column)
920: we changed int to long in num[] and we added a new lvector for
921: memory allocation. But we also truncated to 8 characters (left
922: truncation)
923:
924: (Repository): No more line truncation errors.
925:
926: 2003-06-14 Brouard Nicolas <brouard@homebrou>
927:
928: * imach.c (Repository): Add of a routine likelione (likelihood
929: only once) which prints on a text file
930: (ilk) the contributions to the likelihood for each
931: individual/wave.
932:
933: 2003-06-13 Brouard Nicolas <brouard@homebrou>
934: * imach.c (Repository): Replace "freqsummary" at a correct
935: place. It differs from routine "prevalence" which may be called
936: many times. Probs is memory consuming and must be used with
937: parcimony.
938:
939: 2003-06-17 <brouard@BROUARD>
940:
941: * timeval.h (Module): Added included file to make use of
942: gettimeofday working on win32 with cygwin.
943:
944: 2003-05-16 Brouard Nicolas <brouard@brouard>
945: * imach.c (Module): Insert of a warning if the delay between two
946: waves is negative.
947:
948: * imach.c (Module):
949:
950: 2003-05-03 <brouard@BROUARD>
951:
952: * imach.c: Some cleaning
953:
954: 2003-03-28 <brouard@BROUARD>
955: * imach.c (Module): In version up to 0.92 likelihood was computed
956: as if date of death was unknown. Death was treated as any other
957: health state: the date of the interview describes the actual state
958: and not the date of a change in health state. The former idea was
959: to consider that at each interview the state was recorded
960: (healthy, disable or death) and IMaCh was corrected; but when we
961: introduced the exact date of death then we should have modified
962: the contribution of an exact death to the likelihood. This new
963: contribution is smaller and very dependent of the step unit
964: stepm. It is no more the probability to die between last interview
965: and month of death but the probability to survive from last
966: interview up to one month before death multiplied by the
967: probability to die within a month. Thanks to Chris
968: Jackson for correcting this bug. Former versions increased
969: mortality artificially. The bad side is that we add another loop
970: which slows down the processing. The difference can be up to 10%
971: lower mortality.
972:
973: 2002-05-30 <brouard@BROUARD>
974:
975: * imach.c (Module): Add correlation matrix of one-step
976: probabilities and covariance matrix
1.54 brouard 977:
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