imach/src/ChangeLog - view

File: [Local Repository] / imach / src / ChangeLog
Revision 1.52: download - view: text, annotated - select for diffs
Mon May 30 08:28:04 2022 UTC (2 years, 5 months ago) by brouard
Branches: MAIN
CVS tags: HEAD

*** empty log message ***

1: 2022-05-30 Brouard Nicolas <brouard@brouard.name> 2: 3: * imach.c: With products of covariates (age or dummies or 4: quantitatives), estimates of parameters were good but when 5: estimating variances the positions of newly created covariates 6: were wrongly assigned and results were wrong. Thank to Feinua_Sun! 7: 8: 2022-05-24 Nicolas Brouard <brouard@ined.fr> 9: 10: * imach.c (Module): Some attempts to find a bug of wrong estimates 11: of confidencce intervals with product in the equation modelC 12: 13: 2022-05-15 Nicolas Brouard <brouard@ined.fr> 14: 15: * imach.c (Module): Some minor improvements 16: 17: 2022-04-13 Brouard Nicolas <brouard@brouard.name> 18: 19: * imach.c (Module): Adding link to text data files 20: 21: 2022-04-11 Nicolas Brouard <brouard@ined.fr> 22: 23: * imach.c (Module): Error in rewriting the 'r' file with yearsfproj or yearsbproj fixed 24: 25: 2022-04-05 Brouard Nicolas <brouard@ined.fr> 26: 27: * imach.c (Module): Fixed covariates (dummy or quantitative) 28: with missing values have never been allowed but are ERRORS and 29: program quits. Standard deviations of fixed covariates were 30: wrongly computed. Mean and standard deviations of time varying 31: covariates are still not computed. 32: 33: 2022-03-17 Brouard Nicolas <brouard@ined.fr> 34: 35: * 99r25 Improvements in fixing discrepancies between covariates 36: missing in result line but in model. 37: 38: *Wed Mar 31 2021 Nicolas Brouard <brouard@ined.fr> 39: * imach.c (Module): Still bugs in the result loop. Thank to Holly Benett 40: 41: *2021-03-08 Nicolas Brouard <brouard@ined.fr> 42: 43: * ./ (Module): Fixed bug on result: 44: 45: *2021-02-20 Nicolas Brouard <brouard@ined.fr> 46: 47: * imach.c (Module): Fix bug on quitting after result lines! 48: (Module): Version 0.99r21 49: 50: 2021-02-12 Nicolas Brouard <brouard@ined.fr> 51: 52: * imach.c (Module): The use of a Windows BOM (huge) file is now an error 53: 54: 55: 2021-02-11 Nicolas Brouard <brouard@ined.fr> 56: 57: * (Module): imach.c Someone entered 'results:' instead of 'result:'. Now it is an error which is printed. 58: 59: 2020-02-22 Brouard Nicolas <brouard@ined.fr> 60: 61: * (Module): imach.c Update mle=-3 (for computing Life expectancy 62: and life table from the data without any state) 63: 64: 2019-05-20 Brouard Nicolas <brouard@ined.fr> 65: 66: * version.h: Summary: version 0.99.r19 67: 68: * imach.c: Summary: Projection syntax simplified 69: We can now start projections, forward or backward, from the mean date 70: of inteviews up to or down to a number of years of projection: 71: prevforecast=1 yearsfproj=15.3 mobil_average=0 72: or 73: prevforecast=1 starting-proj-date=1/1/2007 final-proj-date=12/31/2017 mobil_average=0 74: or 75: prevbackcast=1 yearsbproj=12.3 mobil_average=1 76: or 77: prevbackcast=1 starting-back-date=1/10/1999 final-back-date=1/1/1985 mobil_average=1 78: 79: 2019-05-18 Brouard Nicolas <brouard@ined.fr> 80: 81: * imach.c: Summary: doxygen tex bug 82: 83: 2019-05-16 Brouard Nicolas <brouard@ined.fr> 84: 85: * imach.c: Summary: There was some wrong lines added 86: 87: 2019-05-09 Brouard Nicolas <brouard@ined.fr> 88: 89: * Makefile, imach.c: *** empty log message *** 90: 91: * ChangeLog: Summary: C= 92: 93: * imach.c: Summary: Some updates 94: 95: * imach.c: Summary: Before ncovmax 96: 97: * version.h: *** empty log message *** 98: 99: * imach.c: Summary: 0.99r18 unlimited number of individuals 100: 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. 101: 102: 2018-12-13 Brouard Nicolas <brouard@ined.fr> 103: 104: * imach.c: Summary: Bug for young ages (<-30) will be in r17 105: 106: 2018-12-05 Brouard Nicolas <brouard@ined.fr> 107: 108: * Makefile: Summary: 0.99r16 109: 110: 2018-05-02 Brouard Nicolas <brouard@ined.fr> 111: 112: * imach.c: Summary: Some bugs fixed 113: 114: 2018-05-02 Brouard Nicolas <brouard@ined.fr> 115: 116: * imach.c: Summary: Bug for young ages (<-30) will be in r17 117: 118: 2018-05-02 Brouard Nicolas <brouard@ined.fr> 119: 120: * imach.c: Summary: Some bugs fixed 121: 122: 2018-05-01 Brouard Nicolas <brouard@ined.fr> 123: 124: * imach.c: 125: Summary: Bug fixed by providing frequencies only for non missing covariates 126: 127: 2018-04-27 Brouard Nicolas <brouard@ined.fr> 128: 129: * imach.c: Summary: some minor bugs 130: 131: 2018-04-21 Brouard Nicolas <brouard@ined.fr> 132: 133: * README.txt: *** empty log message *** 134: 135: * imach.c: Summary: Some bugs fixed, valgrind tested 136: 137: 2018-04-20 Brouard Nicolas <brouard@ined.fr> 138: 139: * Makefile, README.txt, setup.iss: Summary: imach 0.99r16 140: 141: * imach.c: 142: Summary: Computing mean and stdeviation of fixed quantitative variables 143: 144: 2018-04-19 Brouard Nicolas <brouard@ined.fr> 145: 146: * imach.c: Summary: Some minor bugs fixed 147: 148: * version.h: *** empty log message *** 149: 150: 2018-02-27 Brouard Nicolas <brouard@ined.fr> 151: 152: * imach.c: *** empty log message *** 153: 154: * imach.c: Summary: Adding second argument for quitting 155: 156: 2018-02-21 Brouard Nicolas <brouard@ined.fr> 157: 158: * Makefile, README.txt, imach.c: Summary: 0.99r15 159: New Makefile with recent VirtualBox 5.26. Bug in sqrt negatve in imach.c 160: 161: 2017-07-20 Brouard Nicolas <brouard@ined.fr> 162: 163: * imach.c: Summary: temporary working 164: 165: 2017-07-19 Brouard Nicolas <brouard@ined.fr> 166: 167: * imach.c: Summary: Bug for mobil_average=0 and prevforecast fixed(?) 168: 169: 2017-07-17 Brouard Nicolas <brouard@ined.fr> 170: 171: * imach.c: Summary: BOM files can be read now 172: 173: 2017-06-30 Brouard Nicolas <brouard@ined.fr> 174: 175: * imach.c: Summary: Graphs improvements 176: 177: * imach.c: Summary: Saito's color 178: 179: 2017-06-29 Brouard Nicolas <brouard@ined.fr> 180: 181: * imach.c: Summary: Version 0.99r14 182: 183: 2017-06-27 Brouard Nicolas <brouard@ined.fr> 184: 185: * imach.c: Summary: More documentation on projections 186: 187: * imach.c: Summary: Color of backprojection changed from 6 to 5(yellow) 188: 189: * imach.c: Summary: Some bug with rint 190: 191: 2017-05-24 Brouard Nicolas <brouard@ined.fr> 192: 193: * imach.c: *** empty log message *** 194: 195: 2017-05-23 Brouard Nicolas <brouard@ined.fr> 196: 197: * imach.c: Summary: Code into subroutine, cleanings 198: 199: 2017-05-18 Brouard Nicolas <brouard@ined.fr> 200: 201: * imach.c: 202: Summary: backprojection and confidence intervals of backprevalence 203: 204: 2017-05-13 Brouard Nicolas <brouard@ined.fr> 205: 206: * imach.c: Summary: temporary save for backprojection 207: 208: * imach.c: Summary: Version 0.99r13 (improvements and bugs fixed) 209: 210: 2017-04-26 Brouard Nicolas <brouard@ined.fr> 211: 212: * imach.c: Summary: imach 0.99r13 Some bugs fixed 213: 214: * imach.c: Summary: Labels in graphs 215: 216: 2017-04-24 Brouard Nicolas <brouard@ined.fr> 217: 218: * imach.c: Summary: to save 219: 220: 2017-04-18 Brouard Nicolas <brouard@ined.fr> 221: 222: * imach.c: *** empty log message *** 223: 224: 2017-04-05 Brouard Nicolas <brouard@ined.fr> 225: 226: * imach.c: Summary: Bug in E_ as well as in T_ fixed nres-1 vs k1-1 227: 228: 2017-04-04 Brouard Nicolas <brouard@ined.fr> 229: 230: * imach.c: Summary: Gnuplot indexations fixed (humm) 231: 232: * imach.c: 233: Summary: Some errors to warnings only if date of death is unknown but status is death we could set to pi3 234: 235: 2017-04-03 Brouard Nicolas <brouard@ined.fr> 236: 237: * imach.c: Summary: Version 0.99r12 238: Some cleanings, conformed with updated documentation. 239: 240: 2017-03-30 Brouard Nicolas <brouard@ined.fr> 241: 242: * version.h: *** empty log message *** 243: 244: * version.h: Summary:0.99r11 245: 246: 2017-03-29 Brouard Nicolas <brouard@ined.fr> 247: 248: * imach.c: Summary: Temp 249: 250: 2017-03-27 Brouard Nicolas <brouard@ined.fr> 251: 252: * imach.c: Summary: Temporary 253: 254: 2017-03-08 Brouard Nicolas <brouard@ined.fr> 255: 256: * imach.c: Summary: IMaCh version 0.99r10 bugs in gnuplot fixed 257: 258: * imach.c: Summary: Fixing data parameter line 259: 260: 2016-12-15 Brouard Nicolas <brouard@ined.fr> 261: 262: * imach.c: Summary: 0.99 in progress 263: 264: 2016-09-15 Brouard Nicolas <brouard@ined.fr> 265: 266: * imach.c: *** empty log message *** 267: 268: * imach.c: Summary: not working 269: 270: 2016-09-08 Brouard Nicolas <brouard@ined.fr> 271: 272: * imach.c: Summary: continue 273: 274: 2016-09-07 Brouard Nicolas <brouard@ined.fr> 275: 276: * imach.c: Summary: Starting values from frequencies 277: 278: * imach.c: *** empty log message *** 279: 280: 2016-09-02 Brouard Nicolas <brouard@ined.fr> 281: 282: * imach.c: *** empty log message *** 283: 284: 2016-08-30 Brouard Nicolas <brouard@ined.fr> 285: 286: * imach.c: Summary: Fixing a lots 287: 288: 2016-08-29 Brouard Nicolas <brouard@ined.fr> 289: 290: * imach.c: Summary: gnuplot problem in Back projection to fix 291: 292: * imach.c: Summary: Better 293: 294: 2016-08-26 Brouard Nicolas <brouard@ined.fr> 295: 296: * imach.c: 297: Summary: Improvement in Powell output in order to copy and paste 298: 299: * imach.c: Summary: Starting tests of 0.99 300: 301: * imach.c: Summary: to valgrind 302: 303: 2016-08-25 Brouard Nicolas <brouard@ined.fr> 304: 305: * imach.c: *** empty log message *** 306: 307: 2016-08-23 Brouard Nicolas <brouard@ined.fr> 308: 309: * imach.c: *** empty log message *** 310: 311: * imach.c: Summary: not working 312: 313: 2016-08-22 Brouard Nicolas <brouard@ined.fr> 314: 315: * imach.c: Summary: not working 316: 317: * imach.c: Summary: Not working 318: 319: 2016-07-23 Brouard Nicolas <brouard@ined.fr> 320: 321: * imach.c: Summary: Completing for func too 322: 323: 2016-07-22 Brouard Nicolas <brouard@ined.fr> 324: 325: * imach.c: Summary: Fixing some arrays, still debugging 326: 327: 2016-07-21 Brouard Nicolas <brouard@ined.fr> 328: 329: * imach.c: 330: Summary: 0.99 working (more or less) for Asian Workshop on multitate methods 331: 332: 2016-07-12 Brouard Nicolas <brouard@ined.fr> 333: 334: * imach.c: Summary: temp 335: 336: * imach.c: Summary: saving but not running 337: 338: 2016-07-01 Brouard Nicolas <brouard@ined.fr> 339: 340: * imach.c: Summary: Fixes 341: 342: 2016-02-19 Brouard Nicolas <brouard@ined.fr> 343: 344: * imach-0.98r.c: Summary: Kind of 0.98r? series, starting with r7 345: 346: * setup.iss, Makefile, version.h: *** empty log message *** 347: 348: * imach.c: Summary: temporary 349: 350: 2016-02-17 Brouard Nicolas <brouard@ined.fr> 351: 352: * imach.c: Summary: Probably last 0.98 stable version 0.98r6 353: 354: 2016-02-16 Brouard Nicolas <brouard@ined.fr> 355: 356: * imach.c: Summary: minor bug 357: 358: * imach.c: Summary: 0.99r2 359: 360: 2016-02-15 Brouard Nicolas <brouard@ined.fr> 361: 362: * imach.c: *** empty log message *** 363: 364: 2016-02-12 Brouard Nicolas <brouard@ined.fr> 365: 366: * imach.c: Summary: 0.99 Back projections 367: 368: 2015-12-23 Brouard Nicolas <brouard@ined.fr> 369: 370: * imach.c: Summary: Experimental backcast 371: 372: 2015-12-18 Brouard Nicolas <brouard@ined.fr> 373: 374: * imach.c: Summary: 0.98r4 Warning and status=-2 375: 376: Version 0.98r4 is now: 377: - displaying an error when status is -1, date of interview unknown and date of death known; 378: - permitting a status -2 when the vital status is unknown at a known date of right truncation. 379: Older changes concerning s=-2, dating from 2005 have been supersed. 380: 381: * Makefile: *** empty log message *** 382: 383: 2015-12-16 Brouard Nicolas <brouard@ined.fr> 384: 385: * Makefile: *** empty log message *** 386: 387: * imach.c: Summary: 0.98r4 working 388: 389: * Makefile: Summary: linuxrpm added 390: 391: * Makefile: *** empty log message *** 392: 393: * imach.c: Summary: temporary not working 394: 395: 2015-12-11 Brouard Nicolas <brouard@ined.fr> 396: 397: * imach.c: Summary: 0.98r4 398: 399: 2015-12-08 Brouard Nicolas <brouard@ined.fr> 400: 401: * Makefile: *** empty log message *** 402: 403: 2015-11-21 Brouard Nicolas <brouard@ined.fr> 404: 405: * Makefile: 406: Summary: VBoxManage change from execute --image to run --exe and --wait-exit doesn't exist any more 407: 408: * imach.c: Summary: minor typo 409: 410: * imach.c: Summary: 0.98r3 with some graph of projected cross-sectional 411: 412: Author: Nicolas Brouard 413: 414: 2015-11-18 Brouard Nicolas <brouard@ined.fr> 415: 416: * imach.c: Summary: Start working on projected prevalences 417: 418: 2015-11-17 Brouard Nicolas <brouard@ined.fr> 419: 420: * imach.c: Summary: Adding ftolpl parameter 421: Author: N Brouard 422: 423: We had difficulties to get smoothed confidence intervals. It was due 424: to the period prevalence which wasn't computed accurately. The inner 425: parameter ftolpl is now an outer parameter of the .imach parameter 426: file after estepm. If ftolpl is small 1.e-4 and estepm too, 427: computation are long. 428: 429: * version.h: *** empty log message *** 430: 431: * imach.c: Summary: temporary 432: 433: 2015-10-27 Brouard Nicolas <brouard@ined.fr> 434: 435: * Makefile: *** empty log message *** 436: 437: * setup.iss.in: Summary: some new subdirs 438: 439: * imach.c: *** empty log message *** 440: 441: * setup.iss.in: 442: Summary: Adding gnuplot 5.1 with bin and etc for pango fonts 443: 444: 2015-10-24 Brouard Nicolas <brouard@ined.fr> 445: 446: * imach.c: *** empty log message *** 447: 448: 2015-10-23 Brouard Nicolas <brouard@ined.fr> 449: 450: * imach.c: 451: Summary: 0.98r3 some clarification for graphs on likelihood contributions 452: 453: 2015-10-01 Brouard Nicolas <brouard@ined.fr> 454: 455: * imach.c: Summary: Some new graphs of contribution to likelihood 456: 457: 2015-09-30 Brouard Nicolas <brouard@ined.fr> 458: 459: * Makefile: 460: Summary: Version read from version.h, itself read with cmake 461: 462: * imach.c: Summary: looking at better estimation of the hessian 463: 464: Also a better criteria for convergence to the period prevalence And 465: therefore adding the number of years needed to converge. (The 466: prevalence in any alive state shold sum to one 467: 468: * Makefile: *** empty log message *** 469: 470: 2015-09-22 Brouard Nicolas <brouard@ined.fr> 471: 472: * imach.c: 473: Summary: Adding some overall graph on contribution to likelihood. Might change 474: 475: 2015-09-15 Brouard Nicolas <brouard@ined.fr> 476: 477: * Makefile: *** empty log message *** 478: 479: * imach.c: Summary: 0.98r0 480: 481: - Some new graphs like survival functions 482: - Some bugs fixed like model=1+age+V2. 483: 484: * ChangeLog, Makefile: Summary: 0.98r0 485: 486: * CMakeLists.txt: Summary: Some tests for setup.iss 487: 488: 2015-09-15 Nicolas J Brouard <nbrouard@tugault.ined.fr> 489: 490: * (Module): 0.98r0 Some new graphs, some bugs fixed: model=1+age+V2. etc 491: 492: 2015-08-18 Nicolas J Brouard <nbrouard@tugault.local> 493: 494: * (Module): Adding error when the covariance matrix doesn't contain the exact number of lines required by the model line. 495: 496: 2015-08-03 Nicolas J Brouard <nbrouard@tugault.ined.fr> 497: 498: * (Module): Changing Variance of one-step probabilities into Standard deviation (thanks to Yao-Chi Shih) 499: 500: 2014-12-16 Nicolas J Brouard <nbrouard@tugault.local> 501: 502: * imach.c (Module): Merging 1.61 to 1.162 503: 504: 2014-09-02 Nicolas J Brouard <nbrouard@njbrouard.ined.fr> 505: 506: * prevlim.h (Module): 507: 508: 2014-01-26 Nicolas J Brouard <nbrouard@ledermann-2.local> 509: 510: * imach.c (Module): Trying to merge old staffs together while being at Tokyo. Not tested... 511: (Module): Version 0.98nR Running ok, but output format still only works for three covariates. 512: 513: 2010-04-29 brouard <brouard@ined.fr> 514: 515: * imach.c (Module): Checking covariates for more complex models 516: than V1+V2. A lot of change to be done. Unstable. 517: 518: 2010-04-26 brouard <brouard@ined.fr> 519: 520: * imach.c (Module): merging some libgsl code. Fixing computation 521: of likelione (using inter/intrapolation if mle = 0) in order to 522: get same likelihood as if mle=1. 523: Some cleaning of code and comments added. 524: 525: 2009-10-29 brouard <brouard@ined.fr> 526: 527: * imach.c (Module): Now imach stops if date of birth, at least year of birth, is not given. Some cleaning of the code. 528: 529: 2006-06-30 Brouard Nicolas <brouard@localhost> 530: 531: * imach.c (Module): Clarifications on computing e.j 532: 533: 2006-04-28 Brouard Nicolas <brouard@localhost> 534: 535: * imach.c (Module): Yes the sum of survivors was wrong since 536: imach-114 because nhstepm was no more computed in the age 537: loop. Now we define nhstepma in the age loop. 538: (Module): In order to speed up (in case of numerous covariates) we 539: compute health expectancies (without variances) in a first step 540: and then all the health expectancies with variances or standard 541: deviation (needs data from the Hessian matrices) which slows the 542: computation. 543: In the future we should be able to stop the program is only health 544: expectancies and graph are needed without standard deviations. 545: 546: 2006-04-04 LIEVRE Agnes <lievre@PC_00697.ined.fr> 547: 548: * imach.iss (Module): 549: 550: * imach.c (Module): bugs in evsi + population file added in htm output file 551: 552: 2006-03-22 LIEVRE Agnes <lievre@PC_00697.ined.fr> 553: 554: * imach.c (Module): 555: 556: 2006-03-20 Brouard Nicolas <brouard@localhost> 557: 558: * imach.c (Module): <title> changed, corresponds to .htm file 559: name. <head> headers where missing. 560: 561: * Makefile (Module): 0.98g 562: 563: * imach.c (Module): Weights can have a decimal point as for 564: English (a comma might work with a correct LC_NUMERIC environment, 565: otherwise the weight is truncated). 566: Modification of warning when the covariates values are not 0 or 567: 1. 568: Version 0.98g 569: 570: 2006-03-16 LIEVRE Agnes <lievre@PC_00697.ined.fr> 571: 572: * imach.c (Module): Comments concerning covariates added 573: 574: * noreg-setup.iss (Module): Version 0.98f 575: 576: * Makefile (Module): Version 0.98f make _windows=1 imachcyg-setup 577: 578: * imach.c (Module): refinements in the computation of lli if 579: status=-2 in order to have more reliable computation if stepm is 580: not 1 month. Version 0.98f 581: 582: 2006-03-15 Brouard Nicolas <brouard@localhost> 583: 584: * imach.c (Module): Bug if status = -2, the loglikelihood was 585: computed as likelihood omitting the logarithm. Version O.98e 586: 587: 2006-03-14 Brouard Nicolas <brouard@localhost> 588: 589: * imach.c (Module): varevsij Comments added explaining the second 590: table of variances if popbased=1 . 591: (Module): Covariances of eij, ekl added, graphs fixed, new html link. 592: (Module): Function pstamp added 593: (Module): Version 0.98d 594: 595: 2006-03-06 Brouard Nicolas <brouard@localhost> 596: 597: * imach.c (Module): Variance-covariance wrong links and 598: varian-covariance of ej. is needed (Saito). 599: 600: 2006-02-27 Brouard Nicolas <brouard@localhost> 601: 602: * imach.c (Module): One freematrix added in mlikeli! 603: 604: 2006-02-26 Brouard Nicolas <brouard@localhost> 605: 606: * imach.c (Module): Some improvements in processing parameter 607: filename with strsep. 608: 609: 2006-02-24 Brouard Nicolas <brouard@localhost> 610: 611: * imach.c (Module): Memory leaks checks with valgrind and: 612: datafile was not closed, some imatrix were not freed and on matrix 613: allocation too. 614: 615: 2006-02-09 LIEVRE Agnes <lievre@PC_00697.ined.fr> 616: 617: * strsep.c (Module): Inclusion because not in mingw32!!! 618: 619: * setup.iss.in (Module): IMACHSETUPVERSION added 620: 621: * noreg-setup.iss (Module): added to cvs tree 622: 623: * Makefile (Module): IMACHSETUPVERSION added 624: 625: 2006-01-30 BROUARD Nicolas <brouard@localhost> 626: 627: * Makefile (Module, Module): Latest Makefile 628: 629: * imach.c (Module): Back to gnuplot.exe instead of wgnuplot.exe 630: 631: 2006-01-27 BROUARD Nicolas <brouard@localhost> 632: 633: * noreg-setup.iss (Module): ADDED 634: 635: 2006-01-24 BROUARD Nicolas <brouard@localhost> 636: 637: * imach.c (Module): Comments (lines starting with a #) are allowed in data. 638: 639: 2005-10-25 Nicolas Brouard <brouard@dhcp171.recherche.ined.fr> 640: 641: * Makefile (Module): Added Imach98.pmsp and howto crete a dmg 642: 643: * createdmg.sh (Module): Creates a dmg disk for MaC OS/X 644: 645: 2005-09-30 <lievre@PC_00595> 646: 647: * imach.c (Module): sump fixed, loop imx fixed, and simplifications. 648: (Module): If the status is missing at the last wave but we know 649: that the person is alive, then we can code his/her status as -2 650: (instead of missing=-1 in earlier versions) and his/her 651: contributions to the likelihood is 1 - Prob of dying from last 652: health status (= 1-p13= p11+p12 in the easiest case of somebody in 653: the healthy state at last known wave). Version is 0.98 654: 655: 2004-05-20 Brouard Nicolas <brouard@localhost> 656: 657: * imach.c (Repository): 658: Agnes added a direct estimation of mortality (without the need of 659: computing period prevalence and differential mortality). Thus here 660: is version 0.97a which has been distributed to some people at 661: REVES 16 in Brugge using an Inno setup.exe for PCs. Estimates of 662: mortality using covariates is not done today. Estimating direct 663: mortality is a very different process because it doesn't need 664: interpolation because it is easy to get the lx from the force of 665: the mortality mux in the simplest case as for a Gompertz (log mux 666: = a + b*x . But we have been able to incorporate the new code 667: within former imach program (0.96d) without deteriorating too much 668: the understanding of the program. 669: 670: 2003-06-25 <brouard@BROUARD> 671: 672: * imach.c (Module): On windows (cygwin) function asctime_r doesn't 673: exist so I changed back to asctime which exists. 674: (Module): Version 0.96b 675: 676: 2003-06-24 <brouard@BROUARD> 677: 678: * imach.c (Module): Some bugs corrected for windows. Also, when 679: mle=-1 a template is output in file "or"mypar.txt with the design 680: of the covariance matrix to be input. 681: 682: 2003-06-25 Brouard Nicolas <brouard@homebrou> 683: 684: * imach.c (Repository): Duplicated warning errors corrected. 685: (Repository): Elapsed time after each iteration is now output. It 686: helps to forecast when convergence will be reached. Elapsed time 687: is stamped in powell. We created a new html file for the graphs 688: concerning matrix of covariance. It has extension -cov.htm. 689: 690: 2003-06-23 Brouard Nicolas <brouard@homebrou> 691: 692: * 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. 693: 694: 2003-06-18 Brouard Nicolas <brouard@homebrou> 695: 696: * imach.c (Repository): Suppress abusive calls to append to file html (solution was to put fichtm as a global variable. Version 0.96 697: 698: 2003-06-17 Brouard Nicolas <brouard@homebrou> 699: 700: 701: * imach.c (Repository): Check when date of death was earlier that 702: current date of interview. It may happen when the death was just 703: prior to the death. In this case, dh was negative and likelihood 704: was wrong (infinity). We still send an "Error" but patch by 705: assuming that the date of death was just one stepm after the 706: interview. 707: (Repository): Because some people have very long ID (first column) 708: we changed int to long in num[] and we added a new lvector for 709: memory allocation. But we also truncated to 8 characters (left 710: truncation) 711: 712: (Repository): No more line truncation errors. 713: 714: 2003-06-14 Brouard Nicolas <brouard@homebrou> 715: 716: * imach.c (Repository): Add of a routine likelione (likelihood 717: only once) which prints on a text file 718: (ilk) the contributions to the likelihood for each 719: individual/wave. 720: 721: 2003-06-13 Brouard Nicolas <brouard@homebrou> 722: * imach.c (Repository): Replace "freqsummary" at a correct 723: place. It differs from routine "prevalence" which may be called 724: many times. Probs is memory consuming and must be used with 725: parcimony. 726: 727: 2003-06-17 <brouard@BROUARD> 728: 729: * timeval.h (Module): Added included file to make use of 730: gettimeofday working on win32 with cygwin. 731: 732: 2003-05-16 Brouard Nicolas <brouard@brouard> 733: * imach.c (Module): Insert of a warning if the delay between two 734: waves is negative. 735: 736: * imach.c (Module): 737: 738: 2003-05-03 <brouard@BROUARD> 739: 740: * imach.c: Some cleaning 741: 742: 2003-03-28 <brouard@BROUARD> 743: * imach.c (Module): In version up to 0.92 likelihood was computed 744: as if date of death was unknown. Death was treated as any other 745: health state: the date of the interview describes the actual state 746: and not the date of a change in health state. The former idea was 747: to consider that at each interview the state was recorded 748: (healthy, disable or death) and IMaCh was corrected; but when we 749: introduced the exact date of death then we should have modified 750: the contribution of an exact death to the likelihood. This new 751: contribution is smaller and very dependent of the step unit 752: stepm. It is no more the probability to die between last interview 753: and month of death but the probability to survive from last 754: interview up to one month before death multiplied by the 755: probability to die within a month. Thanks to Chris 756: Jackson for correcting this bug. Former versions increased 757: mortality artificially. The bad side is that we add another loop 758: which slows down the processing. The difference can be up to 10% 759: lower mortality. 760: 761: 2002-05-30 <brouard@BROUARD> 762: * 763: * imach.c (Module): Add correlation matrix of one-step 764: probabilities and covariance matrix 765: 766: 767: 768: 769: