imach/src/ChangeLog - view

File: [Local Repository] / imach / src / ChangeLog
Revision 1.53: download - view: text, annotated - select for diffs
Fri Jul 22 12:03:53 2022 UTC (2 years, 3 months ago) by brouard
Branches: MAIN
CVS tags: HEAD

*** empty log message ***

1: 2022-07-22 Nicolas Brouard <brouard@ined.fr> 2: 3: * imach.c (Module): Output of Wald test in the htm file and not only in the log. 4: 5: 2022-05-30 Brouard Nicolas <brouard@brouard.name> 6: 7: * imach.c: With products of covariates (age or dummies or 8: quantitatives), estimates of parameters were good but when 9: estimating variances the positions of newly created covariates 10: were wrongly assigned and results were wrong. Thank to Feinua_Sun! 11: 12: 2022-05-24 Nicolas Brouard <brouard@ined.fr> 13: 14: * imach.c (Module): Some attempts to find a bug of wrong estimates 15: of confidencce intervals with product in the equation modelC 16: 17: 2022-05-15 Nicolas Brouard <brouard@ined.fr> 18: 19: * imach.c (Module): Some minor improvements 20: 21: 2022-04-13 Brouard Nicolas <brouard@brouard.name> 22: 23: * imach.c (Module): Adding link to text data files 24: 25: 2022-04-11 Nicolas Brouard <brouard@ined.fr> 26: 27: * imach.c (Module): Error in rewriting the 'r' file with yearsfproj or yearsbproj fixed 28: 29: 2022-04-05 Brouard Nicolas <brouard@ined.fr> 30: 31: * imach.c (Module): Fixed covariates (dummy or quantitative) 32: with missing values have never been allowed but are ERRORS and 33: program quits. Standard deviations of fixed covariates were 34: wrongly computed. Mean and standard deviations of time varying 35: covariates are still not computed. 36: 37: 2022-03-17 Brouard Nicolas <brouard@ined.fr> 38: 39: * 99r25 Improvements in fixing discrepancies between covariates 40: missing in result line but in model. 41: 42: *Wed Mar 31 2021 Nicolas Brouard <brouard@ined.fr> 43: * imach.c (Module): Still bugs in the result loop. Thank to Holly Benett 44: 45: *2021-03-08 Nicolas Brouard <brouard@ined.fr> 46: 47: * ./ (Module): Fixed bug on result: 48: 49: *2021-02-20 Nicolas Brouard <brouard@ined.fr> 50: 51: * imach.c (Module): Fix bug on quitting after result lines! 52: (Module): Version 0.99r21 53: 54: 2021-02-12 Nicolas Brouard <brouard@ined.fr> 55: 56: * imach.c (Module): The use of a Windows BOM (huge) file is now an error 57: 58: 59: 2021-02-11 Nicolas Brouard <brouard@ined.fr> 60: 61: * (Module): imach.c Someone entered 'results:' instead of 'result:'. Now it is an error which is printed. 62: 63: 2020-02-22 Brouard Nicolas <brouard@ined.fr> 64: 65: * (Module): imach.c Update mle=-3 (for computing Life expectancy 66: and life table from the data without any state) 67: 68: 2019-05-20 Brouard Nicolas <brouard@ined.fr> 69: 70: * version.h: Summary: version 0.99.r19 71: 72: * imach.c: Summary: Projection syntax simplified 73: We can now start projections, forward or backward, from the mean date 74: of inteviews up to or down to a number of years of projection: 75: prevforecast=1 yearsfproj=15.3 mobil_average=0 76: or 77: prevforecast=1 starting-proj-date=1/1/2007 final-proj-date=12/31/2017 mobil_average=0 78: or 79: prevbackcast=1 yearsbproj=12.3 mobil_average=1 80: or 81: prevbackcast=1 starting-back-date=1/10/1999 final-back-date=1/1/1985 mobil_average=1 82: 83: 2019-05-18 Brouard Nicolas <brouard@ined.fr> 84: 85: * imach.c: Summary: doxygen tex bug 86: 87: 2019-05-16 Brouard Nicolas <brouard@ined.fr> 88: 89: * imach.c: Summary: There was some wrong lines added 90: 91: 2019-05-09 Brouard Nicolas <brouard@ined.fr> 92: 93: * Makefile, imach.c: *** empty log message *** 94: 95: * ChangeLog: Summary: C= 96: 97: * imach.c: Summary: Some updates 98: 99: * imach.c: Summary: Before ncovmax 100: 101: * version.h: *** empty log message *** 102: 103: * imach.c: Summary: 0.99r18 unlimited number of individuals 104: 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. 105: 106: 2018-12-13 Brouard Nicolas <brouard@ined.fr> 107: 108: * imach.c: Summary: Bug for young ages (<-30) will be in r17 109: 110: 2018-12-05 Brouard Nicolas <brouard@ined.fr> 111: 112: * Makefile: Summary: 0.99r16 113: 114: 2018-05-02 Brouard Nicolas <brouard@ined.fr> 115: 116: * imach.c: Summary: Some bugs fixed 117: 118: 2018-05-02 Brouard Nicolas <brouard@ined.fr> 119: 120: * imach.c: Summary: Bug for young ages (<-30) will be in r17 121: 122: 2018-05-02 Brouard Nicolas <brouard@ined.fr> 123: 124: * imach.c: Summary: Some bugs fixed 125: 126: 2018-05-01 Brouard Nicolas <brouard@ined.fr> 127: 128: * imach.c: 129: Summary: Bug fixed by providing frequencies only for non missing covariates 130: 131: 2018-04-27 Brouard Nicolas <brouard@ined.fr> 132: 133: * imach.c: Summary: some minor bugs 134: 135: 2018-04-21 Brouard Nicolas <brouard@ined.fr> 136: 137: * README.txt: *** empty log message *** 138: 139: * imach.c: Summary: Some bugs fixed, valgrind tested 140: 141: 2018-04-20 Brouard Nicolas <brouard@ined.fr> 142: 143: * Makefile, README.txt, setup.iss: Summary: imach 0.99r16 144: 145: * imach.c: 146: Summary: Computing mean and stdeviation of fixed quantitative variables 147: 148: 2018-04-19 Brouard Nicolas <brouard@ined.fr> 149: 150: * imach.c: Summary: Some minor bugs fixed 151: 152: * version.h: *** empty log message *** 153: 154: 2018-02-27 Brouard Nicolas <brouard@ined.fr> 155: 156: * imach.c: *** empty log message *** 157: 158: * imach.c: Summary: Adding second argument for quitting 159: 160: 2018-02-21 Brouard Nicolas <brouard@ined.fr> 161: 162: * Makefile, README.txt, imach.c: Summary: 0.99r15 163: New Makefile with recent VirtualBox 5.26. Bug in sqrt negatve in imach.c 164: 165: 2017-07-20 Brouard Nicolas <brouard@ined.fr> 166: 167: * imach.c: Summary: temporary working 168: 169: 2017-07-19 Brouard Nicolas <brouard@ined.fr> 170: 171: * imach.c: Summary: Bug for mobil_average=0 and prevforecast fixed(?) 172: 173: 2017-07-17 Brouard Nicolas <brouard@ined.fr> 174: 175: * imach.c: Summary: BOM files can be read now 176: 177: 2017-06-30 Brouard Nicolas <brouard@ined.fr> 178: 179: * imach.c: Summary: Graphs improvements 180: 181: * imach.c: Summary: Saito's color 182: 183: 2017-06-29 Brouard Nicolas <brouard@ined.fr> 184: 185: * imach.c: Summary: Version 0.99r14 186: 187: 2017-06-27 Brouard Nicolas <brouard@ined.fr> 188: 189: * imach.c: Summary: More documentation on projections 190: 191: * imach.c: Summary: Color of backprojection changed from 6 to 5(yellow) 192: 193: * imach.c: Summary: Some bug with rint 194: 195: 2017-05-24 Brouard Nicolas <brouard@ined.fr> 196: 197: * imach.c: *** empty log message *** 198: 199: 2017-05-23 Brouard Nicolas <brouard@ined.fr> 200: 201: * imach.c: Summary: Code into subroutine, cleanings 202: 203: 2017-05-18 Brouard Nicolas <brouard@ined.fr> 204: 205: * imach.c: 206: Summary: backprojection and confidence intervals of backprevalence 207: 208: 2017-05-13 Brouard Nicolas <brouard@ined.fr> 209: 210: * imach.c: Summary: temporary save for backprojection 211: 212: * imach.c: Summary: Version 0.99r13 (improvements and bugs fixed) 213: 214: 2017-04-26 Brouard Nicolas <brouard@ined.fr> 215: 216: * imach.c: Summary: imach 0.99r13 Some bugs fixed 217: 218: * imach.c: Summary: Labels in graphs 219: 220: 2017-04-24 Brouard Nicolas <brouard@ined.fr> 221: 222: * imach.c: Summary: to save 223: 224: 2017-04-18 Brouard Nicolas <brouard@ined.fr> 225: 226: * imach.c: *** empty log message *** 227: 228: 2017-04-05 Brouard Nicolas <brouard@ined.fr> 229: 230: * imach.c: Summary: Bug in E_ as well as in T_ fixed nres-1 vs k1-1 231: 232: 2017-04-04 Brouard Nicolas <brouard@ined.fr> 233: 234: * imach.c: Summary: Gnuplot indexations fixed (humm) 235: 236: * imach.c: 237: Summary: Some errors to warnings only if date of death is unknown but status is death we could set to pi3 238: 239: 2017-04-03 Brouard Nicolas <brouard@ined.fr> 240: 241: * imach.c: Summary: Version 0.99r12 242: Some cleanings, conformed with updated documentation. 243: 244: 2017-03-30 Brouard Nicolas <brouard@ined.fr> 245: 246: * version.h: *** empty log message *** 247: 248: * version.h: Summary:0.99r11 249: 250: 2017-03-29 Brouard Nicolas <brouard@ined.fr> 251: 252: * imach.c: Summary: Temp 253: 254: 2017-03-27 Brouard Nicolas <brouard@ined.fr> 255: 256: * imach.c: Summary: Temporary 257: 258: 2017-03-08 Brouard Nicolas <brouard@ined.fr> 259: 260: * imach.c: Summary: IMaCh version 0.99r10 bugs in gnuplot fixed 261: 262: * imach.c: Summary: Fixing data parameter line 263: 264: 2016-12-15 Brouard Nicolas <brouard@ined.fr> 265: 266: * imach.c: Summary: 0.99 in progress 267: 268: 2016-09-15 Brouard Nicolas <brouard@ined.fr> 269: 270: * imach.c: *** empty log message *** 271: 272: * imach.c: Summary: not working 273: 274: 2016-09-08 Brouard Nicolas <brouard@ined.fr> 275: 276: * imach.c: Summary: continue 277: 278: 2016-09-07 Brouard Nicolas <brouard@ined.fr> 279: 280: * imach.c: Summary: Starting values from frequencies 281: 282: * imach.c: *** empty log message *** 283: 284: 2016-09-02 Brouard Nicolas <brouard@ined.fr> 285: 286: * imach.c: *** empty log message *** 287: 288: 2016-08-30 Brouard Nicolas <brouard@ined.fr> 289: 290: * imach.c: Summary: Fixing a lots 291: 292: 2016-08-29 Brouard Nicolas <brouard@ined.fr> 293: 294: * imach.c: Summary: gnuplot problem in Back projection to fix 295: 296: * imach.c: Summary: Better 297: 298: 2016-08-26 Brouard Nicolas <brouard@ined.fr> 299: 300: * imach.c: 301: Summary: Improvement in Powell output in order to copy and paste 302: 303: * imach.c: Summary: Starting tests of 0.99 304: 305: * imach.c: Summary: to valgrind 306: 307: 2016-08-25 Brouard Nicolas <brouard@ined.fr> 308: 309: * imach.c: *** empty log message *** 310: 311: 2016-08-23 Brouard Nicolas <brouard@ined.fr> 312: 313: * imach.c: *** empty log message *** 314: 315: * imach.c: Summary: not working 316: 317: 2016-08-22 Brouard Nicolas <brouard@ined.fr> 318: 319: * imach.c: Summary: not working 320: 321: * imach.c: Summary: Not working 322: 323: 2016-07-23 Brouard Nicolas <brouard@ined.fr> 324: 325: * imach.c: Summary: Completing for func too 326: 327: 2016-07-22 Brouard Nicolas <brouard@ined.fr> 328: 329: * imach.c: Summary: Fixing some arrays, still debugging 330: 331: 2016-07-21 Brouard Nicolas <brouard@ined.fr> 332: 333: * imach.c: 334: Summary: 0.99 working (more or less) for Asian Workshop on multitate methods 335: 336: 2016-07-12 Brouard Nicolas <brouard@ined.fr> 337: 338: * imach.c: Summary: temp 339: 340: * imach.c: Summary: saving but not running 341: 342: 2016-07-01 Brouard Nicolas <brouard@ined.fr> 343: 344: * imach.c: Summary: Fixes 345: 346: 2016-02-19 Brouard Nicolas <brouard@ined.fr> 347: 348: * imach-0.98r.c: Summary: Kind of 0.98r? series, starting with r7 349: 350: * setup.iss, Makefile, version.h: *** empty log message *** 351: 352: * imach.c: Summary: temporary 353: 354: 2016-02-17 Brouard Nicolas <brouard@ined.fr> 355: 356: * imach.c: Summary: Probably last 0.98 stable version 0.98r6 357: 358: 2016-02-16 Brouard Nicolas <brouard@ined.fr> 359: 360: * imach.c: Summary: minor bug 361: 362: * imach.c: Summary: 0.99r2 363: 364: 2016-02-15 Brouard Nicolas <brouard@ined.fr> 365: 366: * imach.c: *** empty log message *** 367: 368: 2016-02-12 Brouard Nicolas <brouard@ined.fr> 369: 370: * imach.c: Summary: 0.99 Back projections 371: 372: 2015-12-23 Brouard Nicolas <brouard@ined.fr> 373: 374: * imach.c: Summary: Experimental backcast 375: 376: 2015-12-18 Brouard Nicolas <brouard@ined.fr> 377: 378: * imach.c: Summary: 0.98r4 Warning and status=-2 379: 380: Version 0.98r4 is now: 381: - displaying an error when status is -1, date of interview unknown and date of death known; 382: - permitting a status -2 when the vital status is unknown at a known date of right truncation. 383: Older changes concerning s=-2, dating from 2005 have been supersed. 384: 385: * Makefile: *** empty log message *** 386: 387: 2015-12-16 Brouard Nicolas <brouard@ined.fr> 388: 389: * Makefile: *** empty log message *** 390: 391: * imach.c: Summary: 0.98r4 working 392: 393: * Makefile: Summary: linuxrpm added 394: 395: * Makefile: *** empty log message *** 396: 397: * imach.c: Summary: temporary not working 398: 399: 2015-12-11 Brouard Nicolas <brouard@ined.fr> 400: 401: * imach.c: Summary: 0.98r4 402: 403: 2015-12-08 Brouard Nicolas <brouard@ined.fr> 404: 405: * Makefile: *** empty log message *** 406: 407: 2015-11-21 Brouard Nicolas <brouard@ined.fr> 408: 409: * Makefile: 410: Summary: VBoxManage change from execute --image to run --exe and --wait-exit doesn't exist any more 411: 412: * imach.c: Summary: minor typo 413: 414: * imach.c: Summary: 0.98r3 with some graph of projected cross-sectional 415: 416: Author: Nicolas Brouard 417: 418: 2015-11-18 Brouard Nicolas <brouard@ined.fr> 419: 420: * imach.c: Summary: Start working on projected prevalences 421: 422: 2015-11-17 Brouard Nicolas <brouard@ined.fr> 423: 424: * imach.c: Summary: Adding ftolpl parameter 425: Author: N Brouard 426: 427: We had difficulties to get smoothed confidence intervals. It was due 428: to the period prevalence which wasn't computed accurately. The inner 429: parameter ftolpl is now an outer parameter of the .imach parameter 430: file after estepm. If ftolpl is small 1.e-4 and estepm too, 431: computation are long. 432: 433: * version.h: *** empty log message *** 434: 435: * imach.c: Summary: temporary 436: 437: 2015-10-27 Brouard Nicolas <brouard@ined.fr> 438: 439: * Makefile: *** empty log message *** 440: 441: * setup.iss.in: Summary: some new subdirs 442: 443: * imach.c: *** empty log message *** 444: 445: * setup.iss.in: 446: Summary: Adding gnuplot 5.1 with bin and etc for pango fonts 447: 448: 2015-10-24 Brouard Nicolas <brouard@ined.fr> 449: 450: * imach.c: *** empty log message *** 451: 452: 2015-10-23 Brouard Nicolas <brouard@ined.fr> 453: 454: * imach.c: 455: Summary: 0.98r3 some clarification for graphs on likelihood contributions 456: 457: 2015-10-01 Brouard Nicolas <brouard@ined.fr> 458: 459: * imach.c: Summary: Some new graphs of contribution to likelihood 460: 461: 2015-09-30 Brouard Nicolas <brouard@ined.fr> 462: 463: * Makefile: 464: Summary: Version read from version.h, itself read with cmake 465: 466: * imach.c: Summary: looking at better estimation of the hessian 467: 468: Also a better criteria for convergence to the period prevalence And 469: therefore adding the number of years needed to converge. (The 470: prevalence in any alive state shold sum to one 471: 472: * Makefile: *** empty log message *** 473: 474: 2015-09-22 Brouard Nicolas <brouard@ined.fr> 475: 476: * imach.c: 477: Summary: Adding some overall graph on contribution to likelihood. Might change 478: 479: 2015-09-15 Brouard Nicolas <brouard@ined.fr> 480: 481: * Makefile: *** empty log message *** 482: 483: * imach.c: Summary: 0.98r0 484: 485: - Some new graphs like survival functions 486: - Some bugs fixed like model=1+age+V2. 487: 488: * ChangeLog, Makefile: Summary: 0.98r0 489: 490: * CMakeLists.txt: Summary: Some tests for setup.iss 491: 492: 2015-09-15 Nicolas J Brouard <nbrouard@tugault.ined.fr> 493: 494: * (Module): 0.98r0 Some new graphs, some bugs fixed: model=1+age+V2. etc 495: 496: 2015-08-18 Nicolas J Brouard <nbrouard@tugault.local> 497: 498: * (Module): Adding error when the covariance matrix doesn't contain the exact number of lines required by the model line. 499: 500: 2015-08-03 Nicolas J Brouard <nbrouard@tugault.ined.fr> 501: 502: * (Module): Changing Variance of one-step probabilities into Standard deviation (thanks to Yao-Chi Shih) 503: 504: 2014-12-16 Nicolas J Brouard <nbrouard@tugault.local> 505: 506: * imach.c (Module): Merging 1.61 to 1.162 507: 508: 2014-09-02 Nicolas J Brouard <nbrouard@njbrouard.ined.fr> 509: 510: * prevlim.h (Module): 511: 512: 2014-01-26 Nicolas J Brouard <nbrouard@ledermann-2.local> 513: 514: * imach.c (Module): Trying to merge old staffs together while being at Tokyo. Not tested... 515: (Module): Version 0.98nR Running ok, but output format still only works for three covariates. 516: 517: 2010-04-29 brouard <brouard@ined.fr> 518: 519: * imach.c (Module): Checking covariates for more complex models 520: than V1+V2. A lot of change to be done. Unstable. 521: 522: 2010-04-26 brouard <brouard@ined.fr> 523: 524: * imach.c (Module): merging some libgsl code. Fixing computation 525: of likelione (using inter/intrapolation if mle = 0) in order to 526: get same likelihood as if mle=1. 527: Some cleaning of code and comments added. 528: 529: 2009-10-29 brouard <brouard@ined.fr> 530: 531: * imach.c (Module): Now imach stops if date of birth, at least year of birth, is not given. Some cleaning of the code. 532: 533: 2006-06-30 Brouard Nicolas <brouard@localhost> 534: 535: * imach.c (Module): Clarifications on computing e.j 536: 537: 2006-04-28 Brouard Nicolas <brouard@localhost> 538: 539: * imach.c (Module): Yes the sum of survivors was wrong since 540: imach-114 because nhstepm was no more computed in the age 541: loop. Now we define nhstepma in the age loop. 542: (Module): In order to speed up (in case of numerous covariates) we 543: compute health expectancies (without variances) in a first step 544: and then all the health expectancies with variances or standard 545: deviation (needs data from the Hessian matrices) which slows the 546: computation. 547: In the future we should be able to stop the program is only health 548: expectancies and graph are needed without standard deviations. 549: 550: 2006-04-04 LIEVRE Agnes <lievre@PC_00697.ined.fr> 551: 552: * imach.iss (Module): 553: 554: * imach.c (Module): bugs in evsi + population file added in htm output file 555: 556: 2006-03-22 LIEVRE Agnes <lievre@PC_00697.ined.fr> 557: 558: * imach.c (Module): 559: 560: 2006-03-20 Brouard Nicolas <brouard@localhost> 561: 562: * imach.c (Module): <title> changed, corresponds to .htm file 563: name. <head> headers where missing. 564: 565: * Makefile (Module): 0.98g 566: 567: * imach.c (Module): Weights can have a decimal point as for 568: English (a comma might work with a correct LC_NUMERIC environment, 569: otherwise the weight is truncated). 570: Modification of warning when the covariates values are not 0 or 571: 1. 572: Version 0.98g 573: 574: 2006-03-16 LIEVRE Agnes <lievre@PC_00697.ined.fr> 575: 576: * imach.c (Module): Comments concerning covariates added 577: 578: * noreg-setup.iss (Module): Version 0.98f 579: 580: * Makefile (Module): Version 0.98f make _windows=1 imachcyg-setup 581: 582: * imach.c (Module): refinements in the computation of lli if 583: status=-2 in order to have more reliable computation if stepm is 584: not 1 month. Version 0.98f 585: 586: 2006-03-15 Brouard Nicolas <brouard@localhost> 587: 588: * imach.c (Module): Bug if status = -2, the loglikelihood was 589: computed as likelihood omitting the logarithm. Version O.98e 590: 591: 2006-03-14 Brouard Nicolas <brouard@localhost> 592: 593: * imach.c (Module): varevsij Comments added explaining the second 594: table of variances if popbased=1 . 595: (Module): Covariances of eij, ekl added, graphs fixed, new html link. 596: (Module): Function pstamp added 597: (Module): Version 0.98d 598: 599: 2006-03-06 Brouard Nicolas <brouard@localhost> 600: 601: * imach.c (Module): Variance-covariance wrong links and 602: varian-covariance of ej. is needed (Saito). 603: 604: 2006-02-27 Brouard Nicolas <brouard@localhost> 605: 606: * imach.c (Module): One freematrix added in mlikeli! 607: 608: 2006-02-26 Brouard Nicolas <brouard@localhost> 609: 610: * imach.c (Module): Some improvements in processing parameter 611: filename with strsep. 612: 613: 2006-02-24 Brouard Nicolas <brouard@localhost> 614: 615: * imach.c (Module): Memory leaks checks with valgrind and: 616: datafile was not closed, some imatrix were not freed and on matrix 617: allocation too. 618: 619: 2006-02-09 LIEVRE Agnes <lievre@PC_00697.ined.fr> 620: 621: * strsep.c (Module): Inclusion because not in mingw32!!! 622: 623: * setup.iss.in (Module): IMACHSETUPVERSION added 624: 625: * noreg-setup.iss (Module): added to cvs tree 626: 627: * Makefile (Module): IMACHSETUPVERSION added 628: 629: 2006-01-30 BROUARD Nicolas <brouard@localhost> 630: 631: * Makefile (Module, Module): Latest Makefile 632: 633: * imach.c (Module): Back to gnuplot.exe instead of wgnuplot.exe 634: 635: 2006-01-27 BROUARD Nicolas <brouard@localhost> 636: 637: * noreg-setup.iss (Module): ADDED 638: 639: 2006-01-24 BROUARD Nicolas <brouard@localhost> 640: 641: * imach.c (Module): Comments (lines starting with a #) are allowed in data. 642: 643: 2005-10-25 Nicolas Brouard <brouard@dhcp171.recherche.ined.fr> 644: 645: * Makefile (Module): Added Imach98.pmsp and howto crete a dmg 646: 647: * createdmg.sh (Module): Creates a dmg disk for MaC OS/X 648: 649: 2005-09-30 <lievre@PC_00595> 650: 651: * imach.c (Module): sump fixed, loop imx fixed, and simplifications. 652: (Module): If the status is missing at the last wave but we know 653: that the person is alive, then we can code his/her status as -2 654: (instead of missing=-1 in earlier versions) and his/her 655: contributions to the likelihood is 1 - Prob of dying from last 656: health status (= 1-p13= p11+p12 in the easiest case of somebody in 657: the healthy state at last known wave). Version is 0.98 658: 659: 2004-05-20 Brouard Nicolas <brouard@localhost> 660: 661: * imach.c (Repository): 662: Agnes added a direct estimation of mortality (without the need of 663: computing period prevalence and differential mortality). Thus here 664: is version 0.97a which has been distributed to some people at 665: REVES 16 in Brugge using an Inno setup.exe for PCs. Estimates of 666: mortality using covariates is not done today. Estimating direct 667: mortality is a very different process because it doesn't need 668: interpolation because it is easy to get the lx from the force of 669: the mortality mux in the simplest case as for a Gompertz (log mux 670: = a + b*x . But we have been able to incorporate the new code 671: within former imach program (0.96d) without deteriorating too much 672: the understanding of the program. 673: 674: 2003-06-25 <brouard@BROUARD> 675: 676: * imach.c (Module): On windows (cygwin) function asctime_r doesn't 677: exist so I changed back to asctime which exists. 678: (Module): Version 0.96b 679: 680: 2003-06-24 <brouard@BROUARD> 681: 682: * imach.c (Module): Some bugs corrected for windows. Also, when 683: mle=-1 a template is output in file "or"mypar.txt with the design 684: of the covariance matrix to be input. 685: 686: 2003-06-25 Brouard Nicolas <brouard@homebrou> 687: 688: * imach.c (Repository): Duplicated warning errors corrected. 689: (Repository): Elapsed time after each iteration is now output. It 690: helps to forecast when convergence will be reached. Elapsed time 691: is stamped in powell. We created a new html file for the graphs 692: concerning matrix of covariance. It has extension -cov.htm. 693: 694: 2003-06-23 Brouard Nicolas <brouard@homebrou> 695: 696: * 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. 697: 698: 2003-06-18 Brouard Nicolas <brouard@homebrou> 699: 700: * imach.c (Repository): Suppress abusive calls to append to file html (solution was to put fichtm as a global variable. Version 0.96 701: 702: 2003-06-17 Brouard Nicolas <brouard@homebrou> 703: 704: 705: * imach.c (Repository): Check when date of death was earlier that 706: current date of interview. It may happen when the death was just 707: prior to the death. In this case, dh was negative and likelihood 708: was wrong (infinity). We still send an "Error" but patch by 709: assuming that the date of death was just one stepm after the 710: interview. 711: (Repository): Because some people have very long ID (first column) 712: we changed int to long in num[] and we added a new lvector for 713: memory allocation. But we also truncated to 8 characters (left 714: truncation) 715: 716: (Repository): No more line truncation errors. 717: 718: 2003-06-14 Brouard Nicolas <brouard@homebrou> 719: 720: * imach.c (Repository): Add of a routine likelione (likelihood 721: only once) which prints on a text file 722: (ilk) the contributions to the likelihood for each 723: individual/wave. 724: 725: 2003-06-13 Brouard Nicolas <brouard@homebrou> 726: * imach.c (Repository): Replace "freqsummary" at a correct 727: place. It differs from routine "prevalence" which may be called 728: many times. Probs is memory consuming and must be used with 729: parcimony. 730: 731: 2003-06-17 <brouard@BROUARD> 732: 733: * timeval.h (Module): Added included file to make use of 734: gettimeofday working on win32 with cygwin. 735: 736: 2003-05-16 Brouard Nicolas <brouard@brouard> 737: * imach.c (Module): Insert of a warning if the delay between two 738: waves is negative. 739: 740: * imach.c (Module): 741: 742: 2003-05-03 <brouard@BROUARD> 743: 744: * imach.c: Some cleaning 745: 746: 2003-03-28 <brouard@BROUARD> 747: * imach.c (Module): In version up to 0.92 likelihood was computed 748: as if date of death was unknown. Death was treated as any other 749: health state: the date of the interview describes the actual state 750: and not the date of a change in health state. The former idea was 751: to consider that at each interview the state was recorded 752: (healthy, disable or death) and IMaCh was corrected; but when we 753: introduced the exact date of death then we should have modified 754: the contribution of an exact death to the likelihood. This new 755: contribution is smaller and very dependent of the step unit 756: stepm. It is no more the probability to die between last interview 757: and month of death but the probability to survive from last 758: interview up to one month before death multiplied by the 759: probability to die within a month. Thanks to Chris 760: Jackson for correcting this bug. Former versions increased 761: mortality artificially. The bad side is that we add another loop 762: which slows down the processing. The difference can be up to 10% 763: lower mortality. 764: 765: 2002-05-30 <brouard@BROUARD> 766: * 767: * imach.c (Module): Add correlation matrix of one-step 768: probabilities and covariance matrix 769: 770: 771: 772: 773: