imach/src/ChangeLog - view

File: [Local Repository] / imach / src / ChangeLog
Revision 1.45: download - view: text, annotated - select for diffs
Wed Mar 31 14:11:04 2021 UTC (3 years, 2 months ago) by brouard
Branches: MAIN
CVS tags: HEAD

Summary: Version 0.99r23

Bugs in the relsutlines solved

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