imach/src/ChangeLog - view

File: [Local Repository] / imach / src / ChangeLog
Revision 1.47: download - view: text, annotated - select for diffs
Thu Mar 17 08:58:13 2022 UTC (2 years, 7 months ago) by brouard
Branches: MAIN
CVS tags: HEAD

*** empty log message ***

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