imach/src/ChangeLog - view

File: [Local Repository] / imach / src / ChangeLog
Revision 1.48: download - view: text, annotated - select for diffs
Tue Apr 5 21:11:15 2022 UTC (2 years, 7 months ago) by brouard
Branches: MAIN
CVS tags: HEAD

*** empty log message ***

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