imach/src/ChangeLog - view

File: [Local Repository] / imach / src / ChangeLog
Revision 1.62: download - view: text, annotated - select for diffs
Mon Sep 19 23:55:25 2022 UTC (21 months ago) by brouard
Branches: MAIN
CVS tags: HEAD

Summary: version 0.99r43

1: 2022-09-19 Nicolas Brouard <brouard@ined.fr> 2: 3: * imach.c (Module): Version 0.99r42 needed a newer version of 4: Gnuplot. But newer version 0.99r43 should run with the Gnuplot 5: version 5.0 or 5.1 distributed with IMaCh. 6: 7: 2022-09-18 Nicolas Brouard <brouard@ined.fr> 8: 9: * imach.c (Module): Fixing when a state in the data is 0 or higher 10: than lstate+ndeath. Fixing the plot of contribution to Likelihood. 11: 12: 2022-09-14 Nicolas Brouard <brouard@ined.fr> 13: 14: * imach.c (Module): Version 0.99r39 with colored dummy covariates 15: (fixed or time varying), using new last columns of 16: ILK_parameter.txt file. 17: 18: 2022-09-11 Nicolas Brouard <brouard@ined.fr> 19: 20: * imach.c (Module): Adding timevarying products of any kinds, 21: should work before shifting cotvar from ncovcol+nqv columns in 22: order to have a correspondance between the column of cotvar and 23: the id of column. 24: (Module): Some cleaning and adding covariates in ILK.txt 25: 26: 2022-09-09 Nicolas Brouard <brouard@ined.fr> 27: 28: * imach.c (Module): Many improvements for fixing products of fixed 29: timevarying as well as fixed * fixed, and test with quantitative 30: covariate. 31: 32: 2022-09-04 Nicolas Brouard <brouard@ined.fr> 33: 34: * imach.c (Module): Now the easy runs i.e. without result or 35: model=1+age only did not work. The defautl combination should be 1 36: and not 0 because everything hasn't been tranformed yet. 37: 38: 2022-09-02 Nicolas Brouard <brouard@ined.fr> 39: 40: * imach.c: Version 0.99r35 because it outputs same results with 41: 1+age+V1+V1*age for females and 1+age for females only 42: (education=1 noweight) 43: 44: 2022-08-31 Nicolas Brouard <brouard@ined.fr> 45: 46: * imach.c (Module): Some improvments in fichtm and many verifications 0.99r34 47: 48: 2022-08-21 Nicolas Brouard <brouard@ined.fr> 49: 50: * imach.c (Module): Version 0.99r33 A lot of changes in 51: reassigning covariates: my first idea was that people will always 52: use the first covariate V1 into the model but in fact they are 53: producing data with many covariates and can use an equation model 54: with some of the covariate; it means that in a model V2+V3 instead 55: of codtabm(k,Tvaraff[j]) which calculates for combination k, for 56: three covariates (V1, V2, V3) the value of Tvaraff[j], but in fact 57: the equation model is restricted to two variables only (V2, V3) 58: and the combination for V2 should be codtabm(k,1) instead of 59: (codtabm(k,2), and the code should be 60: codtabm(k,TnsdVar[Tvaraff[j]]. Many many changes have been 61: made. All of these should be simplified once a day like we did in 62: hpxij() for example by using precov[nres] which is computed in 63: decoderesult for each nres of each resultline. Loop should be done 64: on the equation model globally by distinguishing only product with 65: age (which are changing with age) and no more on type of 66: covariates, single dummies, single covariates. 67: 68: 2022-08-06 Nicolas Brouard <brouard@ined.fr> 69: 70: * imach.c (Module): Version of imach using partly decoderesult to rebuild xpxij function 71: 72: 2022-08-03 Nicolas Brouard <brouard@ined.fr> 73: 74: * imach.c (Module): Many errors in graphs fixed with Vn*age covariates. 75: 76: 2022-07-25 Brouard Nicolas <brouard@brouard.name> 77: 78: * imach.c (Module): Error cptcovn instead of nsd in bmij (was 79: coredumped, revealed by Feiuno, thank you. 80: 81: 2022-07-23 Nicolas Brouard <brouard@ined.fr> 82: 83: * r29 W and not sqrt(Wald) 84: 85: 2022-07-22 Nicolas Brouard <brouard@ined.fr> 86: 87: * imach.c (Module): Output of Wald test in the htm file and not only in the log. 88: 89: 2022-06-02 Brouard Nicolas <brouard@brouard.name> 90: 91: * imach.c (Module): Adding the Wald tests from the log to the main 92: htm for better display of the maximum likelihood estimators. 93: 94: 2022-05-30 Brouard Nicolas <brouard@brouard.name> 95: 96: * imach.c: With products of covariates (age or dummies or 97: quantitatives), estimates of parameters were good but when 98: estimating variances the positions of newly created covariates 99: were wrongly assigned and results were wrong. Thank to Feinua_Sun! 100: 101: 2022-05-24 Nicolas Brouard <brouard@ined.fr> 102: 103: * imach.c (Module): Some attempts to find a bug of wrong estimates 104: of confidencce intervals with product in the equation modelC 105: 106: 2022-05-15 Nicolas Brouard <brouard@ined.fr> 107: 108: * imach.c (Module): Some minor improvements 109: 110: 2022-04-13 Brouard Nicolas <brouard@brouard.name> 111: 112: * imach.c (Module): Adding link to text data files 113: 114: 2022-04-11 Nicolas Brouard <brouard@ined.fr> 115: 116: * imach.c (Module): Error in rewriting the 'r' file with yearsfproj or yearsbproj fixed 117: 118: 2022-04-05 Brouard Nicolas <brouard@ined.fr> 119: 120: * imach.c (Module): Fixed covariates (dummy or quantitative) 121: with missing values have never been allowed but are ERRORS and 122: program quits. Standard deviations of fixed covariates were 123: wrongly computed. Mean and standard deviations of time varying 124: covariates are still not computed. 125: 126: 2022-03-17 Brouard Nicolas <brouard@ined.fr> 127: 128: * 99r25 Improvements in fixing discrepancies between covariates 129: missing in result line but in model. 130: 131: *Wed Mar 31 2021 Nicolas Brouard <brouard@ined.fr> 132: * imach.c (Module): Still bugs in the result loop. Thank to Holly Benett 133: 134: *2021-03-08 Nicolas Brouard <brouard@ined.fr> 135: 136: * ./ (Module): Fixed bug on result: 137: 138: *2021-02-20 Nicolas Brouard <brouard@ined.fr> 139: 140: * imach.c (Module): Fix bug on quitting after result lines! 141: (Module): Version 0.99r21 142: 143: 2021-02-12 Nicolas Brouard <brouard@ined.fr> 144: 145: * imach.c (Module): The use of a Windows BOM (huge) file is now an error 146: 147: 148: 2021-02-11 Nicolas Brouard <brouard@ined.fr> 149: 150: * (Module): imach.c Someone entered 'results:' instead of 'result:'. Now it is an error which is printed. 151: 152: 2020-02-22 Brouard Nicolas <brouard@ined.fr> 153: 154: * (Module): imach.c Update mle=-3 (for computing Life expectancy 155: and life table from the data without any state) 156: 157: 2019-05-20 Brouard Nicolas <brouard@ined.fr> 158: 159: * version.h: Summary: version 0.99.r19 160: 161: * imach.c: Summary: Projection syntax simplified 162: We can now start projections, forward or backward, from the mean date 163: of inteviews up to or down to a number of years of projection: 164: prevforecast=1 yearsfproj=15.3 mobil_average=0 165: or 166: prevforecast=1 starting-proj-date=1/1/2007 final-proj-date=12/31/2017 mobil_average=0 167: or 168: prevbackcast=1 yearsbproj=12.3 mobil_average=1 169: or 170: prevbackcast=1 starting-back-date=1/10/1999 final-back-date=1/1/1985 mobil_average=1 171: 172: 2019-05-18 Brouard Nicolas <brouard@ined.fr> 173: 174: * imach.c: Summary: doxygen tex bug 175: 176: 2019-05-16 Brouard Nicolas <brouard@ined.fr> 177: 178: * imach.c: Summary: There was some wrong lines added 179: 180: 2019-05-09 Brouard Nicolas <brouard@ined.fr> 181: 182: * Makefile, imach.c: *** empty log message *** 183: 184: * ChangeLog: Summary: C= 185: 186: * imach.c: Summary: Some updates 187: 188: * imach.c: Summary: Before ncovmax 189: 190: * version.h: *** empty log message *** 191: 192: * imach.c: Summary: 0.99r18 unlimited number of individuals 193: 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. 194: 195: 2018-12-13 Brouard Nicolas <brouard@ined.fr> 196: 197: * imach.c: Summary: Bug for young ages (<-30) will be in r17 198: 199: 2018-12-05 Brouard Nicolas <brouard@ined.fr> 200: 201: * Makefile: Summary: 0.99r16 202: 203: 2018-05-02 Brouard Nicolas <brouard@ined.fr> 204: 205: * imach.c: Summary: Some bugs fixed 206: 207: 2018-05-02 Brouard Nicolas <brouard@ined.fr> 208: 209: * imach.c: Summary: Bug for young ages (<-30) will be in r17 210: 211: 2018-05-02 Brouard Nicolas <brouard@ined.fr> 212: 213: * imach.c: Summary: Some bugs fixed 214: 215: 2018-05-01 Brouard Nicolas <brouard@ined.fr> 216: 217: * imach.c: 218: Summary: Bug fixed by providing frequencies only for non missing covariates 219: 220: 2018-04-27 Brouard Nicolas <brouard@ined.fr> 221: 222: * imach.c: Summary: some minor bugs 223: 224: 2018-04-21 Brouard Nicolas <brouard@ined.fr> 225: 226: * README.txt: *** empty log message *** 227: 228: * imach.c: Summary: Some bugs fixed, valgrind tested 229: 230: 2018-04-20 Brouard Nicolas <brouard@ined.fr> 231: 232: * Makefile, README.txt, setup.iss: Summary: imach 0.99r16 233: 234: * imach.c: 235: Summary: Computing mean and stdeviation of fixed quantitative variables 236: 237: 2018-04-19 Brouard Nicolas <brouard@ined.fr> 238: 239: * imach.c: Summary: Some minor bugs fixed 240: 241: * version.h: *** empty log message *** 242: 243: 2018-02-27 Brouard Nicolas <brouard@ined.fr> 244: 245: * imach.c: *** empty log message *** 246: 247: * imach.c: Summary: Adding second argument for quitting 248: 249: 2018-02-21 Brouard Nicolas <brouard@ined.fr> 250: 251: * Makefile, README.txt, imach.c: Summary: 0.99r15 252: New Makefile with recent VirtualBox 5.26. Bug in sqrt negatve in imach.c 253: 254: 2017-07-20 Brouard Nicolas <brouard@ined.fr> 255: 256: * imach.c: Summary: temporary working 257: 258: 2017-07-19 Brouard Nicolas <brouard@ined.fr> 259: 260: * imach.c: Summary: Bug for mobil_average=0 and prevforecast fixed(?) 261: 262: 2017-07-17 Brouard Nicolas <brouard@ined.fr> 263: 264: * imach.c: Summary: BOM files can be read now 265: 266: 2017-06-30 Brouard Nicolas <brouard@ined.fr> 267: 268: * imach.c: Summary: Graphs improvements 269: 270: * imach.c: Summary: Saito's color 271: 272: 2017-06-29 Brouard Nicolas <brouard@ined.fr> 273: 274: * imach.c: Summary: Version 0.99r14 275: 276: 2017-06-27 Brouard Nicolas <brouard@ined.fr> 277: 278: * imach.c: Summary: More documentation on projections 279: 280: * imach.c: Summary: Color of backprojection changed from 6 to 5(yellow) 281: 282: * imach.c: Summary: Some bug with rint 283: 284: 2017-05-24 Brouard Nicolas <brouard@ined.fr> 285: 286: * imach.c: *** empty log message *** 287: 288: 2017-05-23 Brouard Nicolas <brouard@ined.fr> 289: 290: * imach.c: Summary: Code into subroutine, cleanings 291: 292: 2017-05-18 Brouard Nicolas <brouard@ined.fr> 293: 294: * imach.c: 295: Summary: backprojection and confidence intervals of backprevalence 296: 297: 2017-05-13 Brouard Nicolas <brouard@ined.fr> 298: 299: * imach.c: Summary: temporary save for backprojection 300: 301: * imach.c: Summary: Version 0.99r13 (improvements and bugs fixed) 302: 303: 2017-04-26 Brouard Nicolas <brouard@ined.fr> 304: 305: * imach.c: Summary: imach 0.99r13 Some bugs fixed 306: 307: * imach.c: Summary: Labels in graphs 308: 309: 2017-04-24 Brouard Nicolas <brouard@ined.fr> 310: 311: * imach.c: Summary: to save 312: 313: 2017-04-18 Brouard Nicolas <brouard@ined.fr> 314: 315: * imach.c: *** empty log message *** 316: 317: 2017-04-05 Brouard Nicolas <brouard@ined.fr> 318: 319: * imach.c: Summary: Bug in E_ as well as in T_ fixed nres-1 vs k1-1 320: 321: 2017-04-04 Brouard Nicolas <brouard@ined.fr> 322: 323: * imach.c: Summary: Gnuplot indexations fixed (humm) 324: 325: * imach.c: 326: Summary: Some errors to warnings only if date of death is unknown but status is death we could set to pi3 327: 328: 2017-04-03 Brouard Nicolas <brouard@ined.fr> 329: 330: * imach.c: Summary: Version 0.99r12 331: Some cleanings, conformed with updated documentation. 332: 333: 2017-03-30 Brouard Nicolas <brouard@ined.fr> 334: 335: * version.h: *** empty log message *** 336: 337: * version.h: Summary:0.99r11 338: 339: 2017-03-29 Brouard Nicolas <brouard@ined.fr> 340: 341: * imach.c: Summary: Temp 342: 343: 2017-03-27 Brouard Nicolas <brouard@ined.fr> 344: 345: * imach.c: Summary: Temporary 346: 347: 2017-03-08 Brouard Nicolas <brouard@ined.fr> 348: 349: * imach.c: Summary: IMaCh version 0.99r10 bugs in gnuplot fixed 350: 351: * imach.c: Summary: Fixing data parameter line 352: 353: 2016-12-15 Brouard Nicolas <brouard@ined.fr> 354: 355: * imach.c: Summary: 0.99 in progress 356: 357: 2016-09-15 Brouard Nicolas <brouard@ined.fr> 358: 359: * imach.c: *** empty log message *** 360: 361: * imach.c: Summary: not working 362: 363: 2016-09-08 Brouard Nicolas <brouard@ined.fr> 364: 365: * imach.c: Summary: continue 366: 367: 2016-09-07 Brouard Nicolas <brouard@ined.fr> 368: 369: * imach.c: Summary: Starting values from frequencies 370: 371: * imach.c: *** empty log message *** 372: 373: 2016-09-02 Brouard Nicolas <brouard@ined.fr> 374: 375: * imach.c: *** empty log message *** 376: 377: 2016-08-30 Brouard Nicolas <brouard@ined.fr> 378: 379: * imach.c: Summary: Fixing a lots 380: 381: 2016-08-29 Brouard Nicolas <brouard@ined.fr> 382: 383: * imach.c: Summary: gnuplot problem in Back projection to fix 384: 385: * imach.c: Summary: Better 386: 387: 2016-08-26 Brouard Nicolas <brouard@ined.fr> 388: 389: * imach.c: 390: Summary: Improvement in Powell output in order to copy and paste 391: 392: * imach.c: Summary: Starting tests of 0.99 393: 394: * imach.c: Summary: to valgrind 395: 396: 2016-08-25 Brouard Nicolas <brouard@ined.fr> 397: 398: * imach.c: *** empty log message *** 399: 400: 2016-08-23 Brouard Nicolas <brouard@ined.fr> 401: 402: * imach.c: *** empty log message *** 403: 404: * imach.c: Summary: not working 405: 406: 2016-08-22 Brouard Nicolas <brouard@ined.fr> 407: 408: * imach.c: Summary: not working 409: 410: * imach.c: Summary: Not working 411: 412: 2016-07-23 Brouard Nicolas <brouard@ined.fr> 413: 414: * imach.c: Summary: Completing for func too 415: 416: 2016-07-22 Brouard Nicolas <brouard@ined.fr> 417: 418: * imach.c: Summary: Fixing some arrays, still debugging 419: 420: 2016-07-21 Brouard Nicolas <brouard@ined.fr> 421: 422: * imach.c: 423: Summary: 0.99 working (more or less) for Asian Workshop on multitate methods 424: 425: 2016-07-12 Brouard Nicolas <brouard@ined.fr> 426: 427: * imach.c: Summary: temp 428: 429: * imach.c: Summary: saving but not running 430: 431: 2016-07-01 Brouard Nicolas <brouard@ined.fr> 432: 433: * imach.c: Summary: Fixes 434: 435: 2016-02-19 Brouard Nicolas <brouard@ined.fr> 436: 437: * imach-0.98r.c: Summary: Kind of 0.98r? series, starting with r7 438: 439: * setup.iss, Makefile, version.h: *** empty log message *** 440: 441: * imach.c: Summary: temporary 442: 443: 2016-02-17 Brouard Nicolas <brouard@ined.fr> 444: 445: * imach.c: Summary: Probably last 0.98 stable version 0.98r6 446: 447: 2016-02-16 Brouard Nicolas <brouard@ined.fr> 448: 449: * imach.c: Summary: minor bug 450: 451: * imach.c: Summary: 0.99r2 452: 453: 2016-02-15 Brouard Nicolas <brouard@ined.fr> 454: 455: * imach.c: *** empty log message *** 456: 457: 2016-02-12 Brouard Nicolas <brouard@ined.fr> 458: 459: * imach.c: Summary: 0.99 Back projections 460: 461: 2015-12-23 Brouard Nicolas <brouard@ined.fr> 462: 463: * imach.c: Summary: Experimental backcast 464: 465: 2015-12-18 Brouard Nicolas <brouard@ined.fr> 466: 467: * imach.c: Summary: 0.98r4 Warning and status=-2 468: 469: Version 0.98r4 is now: 470: - displaying an error when status is -1, date of interview unknown and date of death known; 471: - permitting a status -2 when the vital status is unknown at a known date of right truncation. 472: Older changes concerning s=-2, dating from 2005 have been supersed. 473: 474: * Makefile: *** empty log message *** 475: 476: 2015-12-16 Brouard Nicolas <brouard@ined.fr> 477: 478: * Makefile: *** empty log message *** 479: 480: * imach.c: Summary: 0.98r4 working 481: 482: * Makefile: Summary: linuxrpm added 483: 484: * Makefile: *** empty log message *** 485: 486: * imach.c: Summary: temporary not working 487: 488: 2015-12-11 Brouard Nicolas <brouard@ined.fr> 489: 490: * imach.c: Summary: 0.98r4 491: 492: 2015-12-08 Brouard Nicolas <brouard@ined.fr> 493: 494: * Makefile: *** empty log message *** 495: 496: 2015-11-21 Brouard Nicolas <brouard@ined.fr> 497: 498: * Makefile: 499: Summary: VBoxManage change from execute --image to run --exe and --wait-exit doesn't exist any more 500: 501: * imach.c: Summary: minor typo 502: 503: * imach.c: Summary: 0.98r3 with some graph of projected cross-sectional 504: 505: Author: Nicolas Brouard 506: 507: 2015-11-18 Brouard Nicolas <brouard@ined.fr> 508: 509: * imach.c: Summary: Start working on projected prevalences 510: 511: 2015-11-17 Brouard Nicolas <brouard@ined.fr> 512: 513: * imach.c: Summary: Adding ftolpl parameter 514: Author: N Brouard 515: 516: We had difficulties to get smoothed confidence intervals. It was due 517: to the period prevalence which wasn't computed accurately. The inner 518: parameter ftolpl is now an outer parameter of the .imach parameter 519: file after estepm. If ftolpl is small 1.e-4 and estepm too, 520: computation are long. 521: 522: * version.h: *** empty log message *** 523: 524: * imach.c: Summary: temporary 525: 526: 2015-10-27 Brouard Nicolas <brouard@ined.fr> 527: 528: * Makefile: *** empty log message *** 529: 530: * setup.iss.in: Summary: some new subdirs 531: 532: * imach.c: *** empty log message *** 533: 534: * setup.iss.in: 535: Summary: Adding gnuplot 5.1 with bin and etc for pango fonts 536: 537: 2015-10-24 Brouard Nicolas <brouard@ined.fr> 538: 539: * imach.c: *** empty log message *** 540: 541: 2015-10-23 Brouard Nicolas <brouard@ined.fr> 542: 543: * imach.c: 544: Summary: 0.98r3 some clarification for graphs on likelihood contributions 545: 546: 2015-10-01 Brouard Nicolas <brouard@ined.fr> 547: 548: * imach.c: Summary: Some new graphs of contribution to likelihood 549: 550: 2015-09-30 Brouard Nicolas <brouard@ined.fr> 551: 552: * Makefile: 553: Summary: Version read from version.h, itself read with cmake 554: 555: * imach.c: Summary: looking at better estimation of the hessian 556: 557: Also a better criteria for convergence to the period prevalence And 558: therefore adding the number of years needed to converge. (The 559: prevalence in any alive state shold sum to one 560: 561: * Makefile: *** empty log message *** 562: 563: 2015-09-22 Brouard Nicolas <brouard@ined.fr> 564: 565: * imach.c: 566: Summary: Adding some overall graph on contribution to likelihood. Might change 567: 568: 2015-09-15 Brouard Nicolas <brouard@ined.fr> 569: 570: * Makefile: *** empty log message *** 571: 572: * imach.c: Summary: 0.98r0 573: 574: - Some new graphs like survival functions 575: - Some bugs fixed like model=1+age+V2. 576: 577: * ChangeLog, Makefile: Summary: 0.98r0 578: 579: * CMakeLists.txt: Summary: Some tests for setup.iss 580: 581: 2015-09-15 Nicolas J Brouard <nbrouard@tugault.ined.fr> 582: 583: * (Module): 0.98r0 Some new graphs, some bugs fixed: model=1+age+V2. etc 584: 585: 2015-08-18 Nicolas J Brouard <nbrouard@tugault.local> 586: 587: * (Module): Adding error when the covariance matrix doesn't contain the exact number of lines required by the model line. 588: 589: 2015-08-03 Nicolas J Brouard <nbrouard@tugault.ined.fr> 590: 591: * (Module): Changing Variance of one-step probabilities into Standard deviation (thanks to Yao-Chi Shih) 592: 593: 2014-12-16 Nicolas J Brouard <nbrouard@tugault.local> 594: 595: * imach.c (Module): Merging 1.61 to 1.162 596: 597: 2014-09-02 Nicolas J Brouard <nbrouard@njbrouard.ined.fr> 598: 599: * prevlim.h (Module): 600: 601: 2014-01-26 Nicolas J Brouard <nbrouard@ledermann-2.local> 602: 603: * imach.c (Module): Trying to merge old staffs together while being at Tokyo. Not tested... 604: (Module): Version 0.98nR Running ok, but output format still only works for three covariates. 605: 606: 2010-04-29 brouard <brouard@ined.fr> 607: 608: * imach.c (Module): Checking covariates for more complex models 609: than V1+V2. A lot of change to be done. Unstable. 610: 611: 2010-04-26 brouard <brouard@ined.fr> 612: 613: * imach.c (Module): merging some libgsl code. Fixing computation 614: of likelione (using inter/intrapolation if mle = 0) in order to 615: get same likelihood as if mle=1. 616: Some cleaning of code and comments added. 617: 618: 2009-10-29 brouard <brouard@ined.fr> 619: 620: * imach.c (Module): Now imach stops if date of birth, at least year of birth, is not given. Some cleaning of the code. 621: 622: 2006-06-30 Brouard Nicolas <brouard@localhost> 623: 624: * imach.c (Module): Clarifications on computing e.j 625: 626: 2006-04-28 Brouard Nicolas <brouard@localhost> 627: 628: * imach.c (Module): Yes the sum of survivors was wrong since 629: imach-114 because nhstepm was no more computed in the age 630: loop. Now we define nhstepma in the age loop. 631: (Module): In order to speed up (in case of numerous covariates) we 632: compute health expectancies (without variances) in a first step 633: and then all the health expectancies with variances or standard 634: deviation (needs data from the Hessian matrices) which slows the 635: computation. 636: In the future we should be able to stop the program is only health 637: expectancies and graph are needed without standard deviations. 638: 639: 2006-04-04 LIEVRE Agnes <lievre@PC_00697.ined.fr> 640: 641: * imach.iss (Module): 642: 643: * imach.c (Module): bugs in evsi + population file added in htm output file 644: 645: 2006-03-22 LIEVRE Agnes <lievre@PC_00697.ined.fr> 646: 647: * imach.c (Module): 648: 649: 2006-03-20 Brouard Nicolas <brouard@localhost> 650: 651: * imach.c (Module): <title> changed, corresponds to .htm file 652: name. <head> headers where missing. 653: 654: * Makefile (Module): 0.98g 655: 656: * imach.c (Module): Weights can have a decimal point as for 657: English (a comma might work with a correct LC_NUMERIC environment, 658: otherwise the weight is truncated). 659: Modification of warning when the covariates values are not 0 or 660: 1. 661: Version 0.98g 662: 663: 2006-03-16 LIEVRE Agnes <lievre@PC_00697.ined.fr> 664: 665: * imach.c (Module): Comments concerning covariates added 666: 667: * noreg-setup.iss (Module): Version 0.98f 668: 669: * Makefile (Module): Version 0.98f make _windows=1 imachcyg-setup 670: 671: * imach.c (Module): refinements in the computation of lli if 672: status=-2 in order to have more reliable computation if stepm is 673: not 1 month. Version 0.98f 674: 675: 2006-03-15 Brouard Nicolas <brouard@localhost> 676: 677: * imach.c (Module): Bug if status = -2, the loglikelihood was 678: computed as likelihood omitting the logarithm. Version O.98e 679: 680: 2006-03-14 Brouard Nicolas <brouard@localhost> 681: 682: * imach.c (Module): varevsij Comments added explaining the second 683: table of variances if popbased=1 . 684: (Module): Covariances of eij, ekl added, graphs fixed, new html link. 685: (Module): Function pstamp added 686: (Module): Version 0.98d 687: 688: 2006-03-06 Brouard Nicolas <brouard@localhost> 689: 690: * imach.c (Module): Variance-covariance wrong links and 691: varian-covariance of ej. is needed (Saito). 692: 693: 2006-02-27 Brouard Nicolas <brouard@localhost> 694: 695: * imach.c (Module): One freematrix added in mlikeli! 696: 697: 2006-02-26 Brouard Nicolas <brouard@localhost> 698: 699: * imach.c (Module): Some improvements in processing parameter 700: filename with strsep. 701: 702: 2006-02-24 Brouard Nicolas <brouard@localhost> 703: 704: * imach.c (Module): Memory leaks checks with valgrind and: 705: datafile was not closed, some imatrix were not freed and on matrix 706: allocation too. 707: 708: 2006-02-09 LIEVRE Agnes <lievre@PC_00697.ined.fr> 709: 710: * strsep.c (Module): Inclusion because not in mingw32!!! 711: 712: * setup.iss.in (Module): IMACHSETUPVERSION added 713: 714: * noreg-setup.iss (Module): added to cvs tree 715: 716: * Makefile (Module): IMACHSETUPVERSION added 717: 718: 2006-01-30 BROUARD Nicolas <brouard@localhost> 719: 720: * Makefile (Module, Module): Latest Makefile 721: 722: * imach.c (Module): Back to gnuplot.exe instead of wgnuplot.exe 723: 724: 2006-01-27 BROUARD Nicolas <brouard@localhost> 725: 726: * noreg-setup.iss (Module): ADDED 727: 728: 2006-01-24 BROUARD Nicolas <brouard@localhost> 729: 730: * imach.c (Module): Comments (lines starting with a #) are allowed in data. 731: 732: 2005-10-25 Nicolas Brouard <brouard@dhcp171.recherche.ined.fr> 733: 734: * Makefile (Module): Added Imach98.pmsp and howto crete a dmg 735: 736: * createdmg.sh (Module): Creates a dmg disk for MaC OS/X 737: 738: 2005-09-30 <lievre@PC_00595> 739: 740: * imach.c (Module): sump fixed, loop imx fixed, and simplifications. 741: (Module): If the status is missing at the last wave but we know 742: that the person is alive, then we can code his/her status as -2 743: (instead of missing=-1 in earlier versions) and his/her 744: contributions to the likelihood is 1 - Prob of dying from last 745: health status (= 1-p13= p11+p12 in the easiest case of somebody in 746: the healthy state at last known wave). Version is 0.98 747: 748: 2004-05-20 Brouard Nicolas <brouard@localhost> 749: 750: * imach.c (Repository): 751: Agnes added a direct estimation of mortality (without the need of 752: computing period prevalence and differential mortality). Thus here 753: is version 0.97a which has been distributed to some people at 754: REVES 16 in Brugge using an Inno setup.exe for PCs. Estimates of 755: mortality using covariates is not done today. Estimating direct 756: mortality is a very different process because it doesn't need 757: interpolation because it is easy to get the lx from the force of 758: the mortality mux in the simplest case as for a Gompertz (log mux 759: = a + b*x . But we have been able to incorporate the new code 760: within former imach program (0.96d) without deteriorating too much 761: the understanding of the program. 762: 763: 2003-06-25 <brouard@BROUARD> 764: 765: * imach.c (Module): On windows (cygwin) function asctime_r doesn't 766: exist so I changed back to asctime which exists. 767: (Module): Version 0.96b 768: 769: 2003-06-24 <brouard@BROUARD> 770: 771: * imach.c (Module): Some bugs corrected for windows. Also, when 772: mle=-1 a template is output in file "or"mypar.txt with the design 773: of the covariance matrix to be input. 774: 775: 2003-06-25 Brouard Nicolas <brouard@homebrou> 776: 777: * imach.c (Repository): Duplicated warning errors corrected. 778: (Repository): Elapsed time after each iteration is now output. It 779: helps to forecast when convergence will be reached. Elapsed time 780: is stamped in powell. We created a new html file for the graphs 781: concerning matrix of covariance. It has extension -cov.htm. 782: 783: 2003-06-23 Brouard Nicolas <brouard@homebrou> 784: 785: * 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. 786: 787: 2003-06-18 Brouard Nicolas <brouard@homebrou> 788: 789: * imach.c (Repository): Suppress abusive calls to append to file html (solution was to put fichtm as a global variable. Version 0.96 790: 791: 2003-06-17 Brouard Nicolas <brouard@homebrou> 792: 793: 794: * imach.c (Repository): Check when date of death was earlier that 795: current date of interview. It may happen when the death was just 796: prior to the death. In this case, dh was negative and likelihood 797: was wrong (infinity). We still send an "Error" but patch by 798: assuming that the date of death was just one stepm after the 799: interview. 800: (Repository): Because some people have very long ID (first column) 801: we changed int to long in num[] and we added a new lvector for 802: memory allocation. But we also truncated to 8 characters (left 803: truncation) 804: 805: (Repository): No more line truncation errors. 806: 807: 2003-06-14 Brouard Nicolas <brouard@homebrou> 808: 809: * imach.c (Repository): Add of a routine likelione (likelihood 810: only once) which prints on a text file 811: (ilk) the contributions to the likelihood for each 812: individual/wave. 813: 814: 2003-06-13 Brouard Nicolas <brouard@homebrou> 815: * imach.c (Repository): Replace "freqsummary" at a correct 816: place. It differs from routine "prevalence" which may be called 817: many times. Probs is memory consuming and must be used with 818: parcimony. 819: 820: 2003-06-17 <brouard@BROUARD> 821: 822: * timeval.h (Module): Added included file to make use of 823: gettimeofday working on win32 with cygwin. 824: 825: 2003-05-16 Brouard Nicolas <brouard@brouard> 826: * imach.c (Module): Insert of a warning if the delay between two 827: waves is negative. 828: 829: * imach.c (Module): 830: 831: 2003-05-03 <brouard@BROUARD> 832: 833: * imach.c: Some cleaning 834: 835: 2003-03-28 <brouard@BROUARD> 836: * imach.c (Module): In version up to 0.92 likelihood was computed 837: as if date of death was unknown. Death was treated as any other 838: health state: the date of the interview describes the actual state 839: and not the date of a change in health state. The former idea was 840: to consider that at each interview the state was recorded 841: (healthy, disable or death) and IMaCh was corrected; but when we 842: introduced the exact date of death then we should have modified 843: the contribution of an exact death to the likelihood. This new 844: contribution is smaller and very dependent of the step unit 845: stepm. It is no more the probability to die between last interview 846: and month of death but the probability to survive from last 847: interview up to one month before death multiplied by the 848: probability to die within a month. Thanks to Chris 849: Jackson for correcting this bug. Former versions increased 850: mortality artificially. The bad side is that we add another loop 851: which slows down the processing. The difference can be up to 10% 852: lower mortality. 853: 854: 2002-05-30 <brouard@BROUARD> 855: 856: * imach.c (Module): Add correlation matrix of one-step 857: probabilities and covariance matrix 858: