imach/src/ChangeLog - view

File: [Local Repository] / imach / src / ChangeLog
Revision 1.67: download - view: text, annotated - select for diffs
Tue May 23 12:25:36 2023 UTC (12 months, 1 week ago) by brouard
Branches: MAIN
CVS tags: HEAD

*** empty log message ***

1: 2023-05-23 Nicolas Brouard <brouard@ined.fr> 2: 3: * imach.c (Module): Fixed PROB_r 4: 5: 2023-05-22 Nicolas Brouard <brouard@ined.fr> 6: 7: * imach.c (Module): In the ILK....txt file, the number of columns 8: before the covariates values is dependent of the number of states (16+nlstate): 0.99r46 9: 10: 2023-05-08 Nicolas Brouard <brouard@ined.fr> 11: 12: * (Module): Error V0 when result:. and model 1+age+V1: fixed 13: 14: 2023-04-29 Nicolas Brouard <brouard@ined.fr> 15: 16: * imach.c (Module): Inverting the model equation and fixingg bugs 17: in the drawings 18: "1+age+V7*V4*age+V6*V4*age+V7*V3*age+V6*V3*age+V6*V2*age+V7*age+V6*age+V4*age+V3*age+V2*age+V7*V4+V6*V4+V7*V3+V6*V3+V7*V2+V6*V2+V7+V6+V4+V3+V2\000\0003+V2" 19: 20: 2023-04-24 Nicolas Brouard <brouard@ined.fr> 21: 22: * imach.c (Module): some bugs in printinggnuplot 23: 24: 2022-09-19 Nicolas Brouard <brouard@ined.fr> 25: 26: * imach.c (Module): Version 0.99r42 needed a newer version of 27: Gnuplot. But newer version 0.99r43 should run with the Gnuplot 28: version 5.0 or 5.1 distributed with IMaCh. 29: 30: 2022-09-18 Nicolas Brouard <brouard@ined.fr> 31: 32: * imach.c (Module): Fixing when a state in the data is 0 or higher 33: than lstate+ndeath. Fixing the plot of contribution to Likelihood. 34: 35: 2022-09-16 Nicolas Brouard <brouard@ined.fr> 36: 37: * imach.c (Module): 0.99r41 Was an error when product of timevarying and fixed. Using FixedV[of name] now. Thank you Feinuo 38: 39: 2022-09-14 Nicolas Brouard <brouard@ined.fr> 40: 41: * imach.c (Module): Fixing names of variables in T_ (thanks to Feinuo) 42: 43: 2022-09-14 Nicolas Brouard <brouard@ined.fr> 44: 45: * imach.c (Module): Version 0.99r39 with colored dummy covariates 46: (fixed or time varying), using new last columns of 47: ILK_parameter.txt file. 48: 49: 2022-09-11 Nicolas Brouard <brouard@ined.fr> 50: 51: * imach.c (Module): Adding timevarying products of any kinds, 52: should work before shifting cotvar from ncovcol+nqv columns in 53: order to have a correspondance between the column of cotvar and 54: the id of column. 55: (Module): Some cleaning and adding covariates in ILK.txt 56: 57: 2022-09-09 Nicolas Brouard <brouard@ined.fr> 58: 59: * imach.c (Module): Many improvements for fixing products of fixed 60: timevarying as well as fixed * fixed, and test with quantitative 61: covariate. 62: 63: 2022-09-04 Nicolas Brouard <brouard@ined.fr> 64: 65: * imach.c (Module): Now the easy runs i.e. without result or 66: model=1+age only did not work. The defautl combination should be 1 67: and not 0 because everything hasn't been tranformed yet. 68: 69: 2022-09-02 Nicolas Brouard <brouard@ined.fr> 70: 71: * imach.c: Version 0.99r35 because it outputs same results with 72: 1+age+V1+V1*age for females and 1+age for females only 73: (education=1 noweight) 74: 75: 2022-08-31 Nicolas Brouard <brouard@ined.fr> 76: 77: * imach.c (Module): Some improvments in fichtm and many verifications 0.99r34 78: 79: 2022-08-21 Nicolas Brouard <brouard@ined.fr> 80: 81: * imach.c (Module): Version 0.99r33 A lot of changes in 82: reassigning covariates: my first idea was that people will always 83: use the first covariate V1 into the model but in fact they are 84: producing data with many covariates and can use an equation model 85: with some of the covariate; it means that in a model V2+V3 instead 86: of codtabm(k,Tvaraff[j]) which calculates for combination k, for 87: three covariates (V1, V2, V3) the value of Tvaraff[j], but in fact 88: the equation model is restricted to two variables only (V2, V3) 89: and the combination for V2 should be codtabm(k,1) instead of 90: (codtabm(k,2), and the code should be 91: codtabm(k,TnsdVar[Tvaraff[j]]. Many many changes have been 92: made. All of these should be simplified once a day like we did in 93: hpxij() for example by using precov[nres] which is computed in 94: decoderesult for each nres of each resultline. Loop should be done 95: on the equation model globally by distinguishing only product with 96: age (which are changing with age) and no more on type of 97: covariates, single dummies, single covariates. 98: 99: 2022-08-06 Nicolas Brouard <brouard@ined.fr> 100: 101: * imach.c (Module): Version of imach using partly decoderesult to rebuild xpxij function 102: 103: 2022-08-03 Nicolas Brouard <brouard@ined.fr> 104: 105: * imach.c (Module): Many errors in graphs fixed with Vn*age covariates. 106: 107: 2022-07-25 Brouard Nicolas <brouard@brouard.name> 108: 109: * imach.c (Module): Error cptcovn instead of nsd in bmij (was 110: coredumped, revealed by Feiuno, thank you. 111: 112: 2022-07-23 Nicolas Brouard <brouard@ined.fr> 113: 114: * r29 W and not sqrt(Wald) 115: 116: 2022-07-22 Nicolas Brouard <brouard@ined.fr> 117: 118: * imach.c (Module): Output of Wald test in the htm file and not only in the log. 119: 120: 2022-06-02 Brouard Nicolas <brouard@brouard.name> 121: 122: * imach.c (Module): Adding the Wald tests from the log to the main 123: htm for better display of the maximum likelihood estimators. 124: 125: 2022-05-30 Brouard Nicolas <brouard@brouard.name> 126: 127: * imach.c: With products of covariates (age or dummies or 128: quantitatives), estimates of parameters were good but when 129: estimating variances the positions of newly created covariates 130: were wrongly assigned and results were wrong. Thank to Feinua_Sun! 131: 132: 2022-05-24 Nicolas Brouard <brouard@ined.fr> 133: 134: * imach.c (Module): Some attempts to find a bug of wrong estimates 135: of confidencce intervals with product in the equation modelC 136: 137: 2022-05-15 Nicolas Brouard <brouard@ined.fr> 138: 139: * imach.c (Module): Some minor improvements 140: 141: 2022-04-13 Brouard Nicolas <brouard@brouard.name> 142: 143: * imach.c (Module): Adding link to text data files 144: 145: 2022-04-11 Nicolas Brouard <brouard@ined.fr> 146: 147: * imach.c (Module): Error in rewriting the 'r' file with yearsfproj or yearsbproj fixed 148: 149: 2022-04-05 Brouard Nicolas <brouard@ined.fr> 150: 151: * imach.c (Module): Fixed covariates (dummy or quantitative) 152: with missing values have never been allowed but are ERRORS and 153: program quits. Standard deviations of fixed covariates were 154: wrongly computed. Mean and standard deviations of time varying 155: covariates are still not computed. 156: 157: 2022-03-17 Brouard Nicolas <brouard@ined.fr> 158: 159: * 99r25 Improvements in fixing discrepancies between covariates 160: missing in result line but in model. 161: 162: *Wed Mar 31 2021 Nicolas Brouard <brouard@ined.fr> 163: * imach.c (Module): Still bugs in the result loop. Thank to Holly Benett 164: 165: *2021-03-08 Nicolas Brouard <brouard@ined.fr> 166: 167: * ./ (Module): Fixed bug on result: 168: 169: *2021-02-20 Nicolas Brouard <brouard@ined.fr> 170: 171: * imach.c (Module): Fix bug on quitting after result lines! 172: (Module): Version 0.99r21 173: 174: 2021-02-12 Nicolas Brouard <brouard@ined.fr> 175: 176: * imach.c (Module): The use of a Windows BOM (huge) file is now an error 177: 178: 179: 2021-02-11 Nicolas Brouard <brouard@ined.fr> 180: 181: * (Module): imach.c Someone entered 'results:' instead of 'result:'. Now it is an error which is printed. 182: 183: 2020-02-22 Brouard Nicolas <brouard@ined.fr> 184: 185: * (Module): imach.c Update mle=-3 (for computing Life expectancy 186: and life table from the data without any state) 187: 188: 2019-05-20 Brouard Nicolas <brouard@ined.fr> 189: 190: * version.h: Summary: version 0.99.r19 191: 192: * imach.c: Summary: Projection syntax simplified 193: We can now start projections, forward or backward, from the mean date 194: of inteviews up to or down to a number of years of projection: 195: prevforecast=1 yearsfproj=15.3 mobil_average=0 196: or 197: prevforecast=1 starting-proj-date=1/1/2007 final-proj-date=12/31/2017 mobil_average=0 198: or 199: prevbackcast=1 yearsbproj=12.3 mobil_average=1 200: or 201: prevbackcast=1 starting-back-date=1/10/1999 final-back-date=1/1/1985 mobil_average=1 202: 203: 2019-05-18 Brouard Nicolas <brouard@ined.fr> 204: 205: * imach.c: Summary: doxygen tex bug 206: 207: 2019-05-16 Brouard Nicolas <brouard@ined.fr> 208: 209: * imach.c: Summary: There was some wrong lines added 210: 211: 2019-05-09 Brouard Nicolas <brouard@ined.fr> 212: 213: * Makefile, imach.c: *** empty log message *** 214: 215: * ChangeLog: Summary: C= 216: 217: * imach.c: Summary: Some updates 218: 219: * imach.c: Summary: Before ncovmax 220: 221: * version.h: *** empty log message *** 222: 223: * imach.c: Summary: 0.99r18 unlimited number of individuals 224: 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. 225: 226: 2018-12-13 Brouard Nicolas <brouard@ined.fr> 227: 228: * imach.c: Summary: Bug for young ages (<-30) will be in r17 229: 230: 2018-12-05 Brouard Nicolas <brouard@ined.fr> 231: 232: * Makefile: Summary: 0.99r16 233: 234: 2018-05-02 Brouard Nicolas <brouard@ined.fr> 235: 236: * imach.c: Summary: Some bugs fixed 237: 238: 2018-05-02 Brouard Nicolas <brouard@ined.fr> 239: 240: * imach.c: Summary: Bug for young ages (<-30) will be in r17 241: 242: 2018-05-02 Brouard Nicolas <brouard@ined.fr> 243: 244: * imach.c: Summary: Some bugs fixed 245: 246: 2018-05-01 Brouard Nicolas <brouard@ined.fr> 247: 248: * imach.c: 249: Summary: Bug fixed by providing frequencies only for non missing covariates 250: 251: 2018-04-27 Brouard Nicolas <brouard@ined.fr> 252: 253: * imach.c: Summary: some minor bugs 254: 255: 2018-04-21 Brouard Nicolas <brouard@ined.fr> 256: 257: * README.txt: *** empty log message *** 258: 259: * imach.c: Summary: Some bugs fixed, valgrind tested 260: 261: 2018-04-20 Brouard Nicolas <brouard@ined.fr> 262: 263: * Makefile, README.txt, setup.iss: Summary: imach 0.99r16 264: 265: * imach.c: 266: Summary: Computing mean and stdeviation of fixed quantitative variables 267: 268: 2018-04-19 Brouard Nicolas <brouard@ined.fr> 269: 270: * imach.c: Summary: Some minor bugs fixed 271: 272: * version.h: *** empty log message *** 273: 274: 2018-02-27 Brouard Nicolas <brouard@ined.fr> 275: 276: * imach.c: *** empty log message *** 277: 278: * imach.c: Summary: Adding second argument for quitting 279: 280: 2018-02-21 Brouard Nicolas <brouard@ined.fr> 281: 282: * Makefile, README.txt, imach.c: Summary: 0.99r15 283: New Makefile with recent VirtualBox 5.26. Bug in sqrt negatve in imach.c 284: 285: 2017-07-20 Brouard Nicolas <brouard@ined.fr> 286: 287: * imach.c: Summary: temporary working 288: 289: 2017-07-19 Brouard Nicolas <brouard@ined.fr> 290: 291: * imach.c: Summary: Bug for mobil_average=0 and prevforecast fixed(?) 292: 293: 2017-07-17 Brouard Nicolas <brouard@ined.fr> 294: 295: * imach.c: Summary: BOM files can be read now 296: 297: 2017-06-30 Brouard Nicolas <brouard@ined.fr> 298: 299: * imach.c: Summary: Graphs improvements 300: 301: * imach.c: Summary: Saito's color 302: 303: 2017-06-29 Brouard Nicolas <brouard@ined.fr> 304: 305: * imach.c: Summary: Version 0.99r14 306: 307: 2017-06-27 Brouard Nicolas <brouard@ined.fr> 308: 309: * imach.c: Summary: More documentation on projections 310: 311: * imach.c: Summary: Color of backprojection changed from 6 to 5(yellow) 312: 313: * imach.c: Summary: Some bug with rint 314: 315: 2017-05-24 Brouard Nicolas <brouard@ined.fr> 316: 317: * imach.c: *** empty log message *** 318: 319: 2017-05-23 Brouard Nicolas <brouard@ined.fr> 320: 321: * imach.c: Summary: Code into subroutine, cleanings 322: 323: 2017-05-18 Brouard Nicolas <brouard@ined.fr> 324: 325: * imach.c: 326: Summary: backprojection and confidence intervals of backprevalence 327: 328: 2017-05-13 Brouard Nicolas <brouard@ined.fr> 329: 330: * imach.c: Summary: temporary save for backprojection 331: 332: * imach.c: Summary: Version 0.99r13 (improvements and bugs fixed) 333: 334: 2017-04-26 Brouard Nicolas <brouard@ined.fr> 335: 336: * imach.c: Summary: imach 0.99r13 Some bugs fixed 337: 338: * imach.c: Summary: Labels in graphs 339: 340: 2017-04-24 Brouard Nicolas <brouard@ined.fr> 341: 342: * imach.c: Summary: to save 343: 344: 2017-04-18 Brouard Nicolas <brouard@ined.fr> 345: 346: * imach.c: *** empty log message *** 347: 348: 2017-04-05 Brouard Nicolas <brouard@ined.fr> 349: 350: * imach.c: Summary: Bug in E_ as well as in T_ fixed nres-1 vs k1-1 351: 352: 2017-04-04 Brouard Nicolas <brouard@ined.fr> 353: 354: * imach.c: Summary: Gnuplot indexations fixed (humm) 355: 356: * imach.c: 357: Summary: Some errors to warnings only if date of death is unknown but status is death we could set to pi3 358: 359: 2017-04-03 Brouard Nicolas <brouard@ined.fr> 360: 361: * imach.c: Summary: Version 0.99r12 362: Some cleanings, conformed with updated documentation. 363: 364: 2017-03-30 Brouard Nicolas <brouard@ined.fr> 365: 366: * version.h: *** empty log message *** 367: 368: * version.h: Summary:0.99r11 369: 370: 2017-03-29 Brouard Nicolas <brouard@ined.fr> 371: 372: * imach.c: Summary: Temp 373: 374: 2017-03-27 Brouard Nicolas <brouard@ined.fr> 375: 376: * imach.c: Summary: Temporary 377: 378: 2017-03-08 Brouard Nicolas <brouard@ined.fr> 379: 380: * imach.c: Summary: IMaCh version 0.99r10 bugs in gnuplot fixed 381: 382: * imach.c: Summary: Fixing data parameter line 383: 384: 2016-12-15 Brouard Nicolas <brouard@ined.fr> 385: 386: * imach.c: Summary: 0.99 in progress 387: 388: 2016-09-15 Brouard Nicolas <brouard@ined.fr> 389: 390: * imach.c: *** empty log message *** 391: 392: * imach.c: Summary: not working 393: 394: 2016-09-08 Brouard Nicolas <brouard@ined.fr> 395: 396: * imach.c: Summary: continue 397: 398: 2016-09-07 Brouard Nicolas <brouard@ined.fr> 399: 400: * imach.c: Summary: Starting values from frequencies 401: 402: * imach.c: *** empty log message *** 403: 404: 2016-09-02 Brouard Nicolas <brouard@ined.fr> 405: 406: * imach.c: *** empty log message *** 407: 408: 2016-08-30 Brouard Nicolas <brouard@ined.fr> 409: 410: * imach.c: Summary: Fixing a lots 411: 412: 2016-08-29 Brouard Nicolas <brouard@ined.fr> 413: 414: * imach.c: Summary: gnuplot problem in Back projection to fix 415: 416: * imach.c: Summary: Better 417: 418: 2016-08-26 Brouard Nicolas <brouard@ined.fr> 419: 420: * imach.c: 421: Summary: Improvement in Powell output in order to copy and paste 422: 423: * imach.c: Summary: Starting tests of 0.99 424: 425: * imach.c: Summary: to valgrind 426: 427: 2016-08-25 Brouard Nicolas <brouard@ined.fr> 428: 429: * imach.c: *** empty log message *** 430: 431: 2016-08-23 Brouard Nicolas <brouard@ined.fr> 432: 433: * imach.c: *** empty log message *** 434: 435: * imach.c: Summary: not working 436: 437: 2016-08-22 Brouard Nicolas <brouard@ined.fr> 438: 439: * imach.c: Summary: not working 440: 441: * imach.c: Summary: Not working 442: 443: 2016-07-23 Brouard Nicolas <brouard@ined.fr> 444: 445: * imach.c: Summary: Completing for func too 446: 447: 2016-07-22 Brouard Nicolas <brouard@ined.fr> 448: 449: * imach.c: Summary: Fixing some arrays, still debugging 450: 451: 2016-07-21 Brouard Nicolas <brouard@ined.fr> 452: 453: * imach.c: 454: Summary: 0.99 working (more or less) for Asian Workshop on multitate methods 455: 456: 2016-07-12 Brouard Nicolas <brouard@ined.fr> 457: 458: * imach.c: Summary: temp 459: 460: * imach.c: Summary: saving but not running 461: 462: 2016-07-01 Brouard Nicolas <brouard@ined.fr> 463: 464: * imach.c: Summary: Fixes 465: 466: 2016-02-19 Brouard Nicolas <brouard@ined.fr> 467: 468: * imach-0.98r.c: Summary: Kind of 0.98r? series, starting with r7 469: 470: * setup.iss, Makefile, version.h: *** empty log message *** 471: 472: * imach.c: Summary: temporary 473: 474: 2016-02-17 Brouard Nicolas <brouard@ined.fr> 475: 476: * imach.c: Summary: Probably last 0.98 stable version 0.98r6 477: 478: 2016-02-16 Brouard Nicolas <brouard@ined.fr> 479: 480: * imach.c: Summary: minor bug 481: 482: * imach.c: Summary: 0.99r2 483: 484: 2016-02-15 Brouard Nicolas <brouard@ined.fr> 485: 486: * imach.c: *** empty log message *** 487: 488: 2016-02-12 Brouard Nicolas <brouard@ined.fr> 489: 490: * imach.c: Summary: 0.99 Back projections 491: 492: 2015-12-23 Brouard Nicolas <brouard@ined.fr> 493: 494: * imach.c: Summary: Experimental backcast 495: 496: 2015-12-18 Brouard Nicolas <brouard@ined.fr> 497: 498: * imach.c: Summary: 0.98r4 Warning and status=-2 499: 500: Version 0.98r4 is now: 501: - displaying an error when status is -1, date of interview unknown and date of death known; 502: - permitting a status -2 when the vital status is unknown at a known date of right truncation. 503: Older changes concerning s=-2, dating from 2005 have been supersed. 504: 505: * Makefile: *** empty log message *** 506: 507: 2015-12-16 Brouard Nicolas <brouard@ined.fr> 508: 509: * Makefile: *** empty log message *** 510: 511: * imach.c: Summary: 0.98r4 working 512: 513: * Makefile: Summary: linuxrpm added 514: 515: * Makefile: *** empty log message *** 516: 517: * imach.c: Summary: temporary not working 518: 519: 2015-12-11 Brouard Nicolas <brouard@ined.fr> 520: 521: * imach.c: Summary: 0.98r4 522: 523: 2015-12-08 Brouard Nicolas <brouard@ined.fr> 524: 525: * Makefile: *** empty log message *** 526: 527: 2015-11-21 Brouard Nicolas <brouard@ined.fr> 528: 529: * Makefile: 530: Summary: VBoxManage change from execute --image to run --exe and --wait-exit doesn't exist any more 531: 532: * imach.c: Summary: minor typo 533: 534: * imach.c: Summary: 0.98r3 with some graph of projected cross-sectional 535: 536: Author: Nicolas Brouard 537: 538: 2015-11-18 Brouard Nicolas <brouard@ined.fr> 539: 540: * imach.c: Summary: Start working on projected prevalences 541: 542: 2015-11-17 Brouard Nicolas <brouard@ined.fr> 543: 544: * imach.c: Summary: Adding ftolpl parameter 545: Author: N Brouard 546: 547: We had difficulties to get smoothed confidence intervals. It was due 548: to the period prevalence which wasn't computed accurately. The inner 549: parameter ftolpl is now an outer parameter of the .imach parameter 550: file after estepm. If ftolpl is small 1.e-4 and estepm too, 551: computation are long. 552: 553: * version.h: *** empty log message *** 554: 555: * imach.c: Summary: temporary 556: 557: 2015-10-27 Brouard Nicolas <brouard@ined.fr> 558: 559: * Makefile: *** empty log message *** 560: 561: * setup.iss.in: Summary: some new subdirs 562: 563: * imach.c: *** empty log message *** 564: 565: * setup.iss.in: 566: Summary: Adding gnuplot 5.1 with bin and etc for pango fonts 567: 568: 2015-10-24 Brouard Nicolas <brouard@ined.fr> 569: 570: * imach.c: *** empty log message *** 571: 572: 2015-10-23 Brouard Nicolas <brouard@ined.fr> 573: 574: * imach.c: 575: Summary: 0.98r3 some clarification for graphs on likelihood contributions 576: 577: 2015-10-01 Brouard Nicolas <brouard@ined.fr> 578: 579: * imach.c: Summary: Some new graphs of contribution to likelihood 580: 581: 2015-09-30 Brouard Nicolas <brouard@ined.fr> 582: 583: * Makefile: 584: Summary: Version read from version.h, itself read with cmake 585: 586: * imach.c: Summary: looking at better estimation of the hessian 587: 588: Also a better criteria for convergence to the period prevalence And 589: therefore adding the number of years needed to converge. (The 590: prevalence in any alive state shold sum to one 591: 592: * Makefile: *** empty log message *** 593: 594: 2015-09-22 Brouard Nicolas <brouard@ined.fr> 595: 596: * imach.c: 597: Summary: Adding some overall graph on contribution to likelihood. Might change 598: 599: 2015-09-15 Brouard Nicolas <brouard@ined.fr> 600: 601: * Makefile: *** empty log message *** 602: 603: * imach.c: Summary: 0.98r0 604: 605: - Some new graphs like survival functions 606: - Some bugs fixed like model=1+age+V2. 607: 608: * ChangeLog, Makefile: Summary: 0.98r0 609: 610: * CMakeLists.txt: Summary: Some tests for setup.iss 611: 612: 2015-09-15 Nicolas J Brouard <nbrouard@tugault.ined.fr> 613: 614: * (Module): 0.98r0 Some new graphs, some bugs fixed: model=1+age+V2. etc 615: 616: 2015-08-18 Nicolas J Brouard <nbrouard@tugault.local> 617: 618: * (Module): Adding error when the covariance matrix doesn't contain the exact number of lines required by the model line. 619: 620: 2015-08-03 Nicolas J Brouard <nbrouard@tugault.ined.fr> 621: 622: * (Module): Changing Variance of one-step probabilities into Standard deviation (thanks to Yao-Chi Shih) 623: 624: 2014-12-16 Nicolas J Brouard <nbrouard@tugault.local> 625: 626: * imach.c (Module): Merging 1.61 to 1.162 627: 628: 2014-09-02 Nicolas J Brouard <nbrouard@njbrouard.ined.fr> 629: 630: * prevlim.h (Module): 631: 632: 2014-01-26 Nicolas J Brouard <nbrouard@ledermann-2.local> 633: 634: * imach.c (Module): Trying to merge old staffs together while being at Tokyo. Not tested... 635: (Module): Version 0.98nR Running ok, but output format still only works for three covariates. 636: 637: 2010-04-29 brouard <brouard@ined.fr> 638: 639: * imach.c (Module): Checking covariates for more complex models 640: than V1+V2. A lot of change to be done. Unstable. 641: 642: 2010-04-26 brouard <brouard@ined.fr> 643: 644: * imach.c (Module): merging some libgsl code. Fixing computation 645: of likelione (using inter/intrapolation if mle = 0) in order to 646: get same likelihood as if mle=1. 647: Some cleaning of code and comments added. 648: 649: 2009-10-29 brouard <brouard@ined.fr> 650: 651: * imach.c (Module): Now imach stops if date of birth, at least year of birth, is not given. Some cleaning of the code. 652: 653: 2006-06-30 Brouard Nicolas <brouard@localhost> 654: 655: * imach.c (Module): Clarifications on computing e.j 656: 657: 2006-04-28 Brouard Nicolas <brouard@localhost> 658: 659: * imach.c (Module): Yes the sum of survivors was wrong since 660: imach-114 because nhstepm was no more computed in the age 661: loop. Now we define nhstepma in the age loop. 662: (Module): In order to speed up (in case of numerous covariates) we 663: compute health expectancies (without variances) in a first step 664: and then all the health expectancies with variances or standard 665: deviation (needs data from the Hessian matrices) which slows the 666: computation. 667: In the future we should be able to stop the program is only health 668: expectancies and graph are needed without standard deviations. 669: 670: 2006-04-04 LIEVRE Agnes <lievre@PC_00697.ined.fr> 671: 672: * imach.iss (Module): 673: 674: * imach.c (Module): bugs in evsi + population file added in htm output file 675: 676: 2006-03-22 LIEVRE Agnes <lievre@PC_00697.ined.fr> 677: 678: * imach.c (Module): 679: 680: 2006-03-20 Brouard Nicolas <brouard@localhost> 681: 682: * imach.c (Module): <title> changed, corresponds to .htm file 683: name. <head> headers where missing. 684: 685: * Makefile (Module): 0.98g 686: 687: * imach.c (Module): Weights can have a decimal point as for 688: English (a comma might work with a correct LC_NUMERIC environment, 689: otherwise the weight is truncated). 690: Modification of warning when the covariates values are not 0 or 691: 1. 692: Version 0.98g 693: 694: 2006-03-16 LIEVRE Agnes <lievre@PC_00697.ined.fr> 695: 696: * imach.c (Module): Comments concerning covariates added 697: 698: * noreg-setup.iss (Module): Version 0.98f 699: 700: * Makefile (Module): Version 0.98f make _windows=1 imachcyg-setup 701: 702: * imach.c (Module): refinements in the computation of lli if 703: status=-2 in order to have more reliable computation if stepm is 704: not 1 month. Version 0.98f 705: 706: 2006-03-15 Brouard Nicolas <brouard@localhost> 707: 708: * imach.c (Module): Bug if status = -2, the loglikelihood was 709: computed as likelihood omitting the logarithm. Version O.98e 710: 711: 2006-03-14 Brouard Nicolas <brouard@localhost> 712: 713: * imach.c (Module): varevsij Comments added explaining the second 714: table of variances if popbased=1 . 715: (Module): Covariances of eij, ekl added, graphs fixed, new html link. 716: (Module): Function pstamp added 717: (Module): Version 0.98d 718: 719: 2006-03-06 Brouard Nicolas <brouard@localhost> 720: 721: * imach.c (Module): Variance-covariance wrong links and 722: varian-covariance of ej. is needed (Saito). 723: 724: 2006-02-27 Brouard Nicolas <brouard@localhost> 725: 726: * imach.c (Module): One freematrix added in mlikeli! 727: 728: 2006-02-26 Brouard Nicolas <brouard@localhost> 729: 730: * imach.c (Module): Some improvements in processing parameter 731: filename with strsep. 732: 733: 2006-02-24 Brouard Nicolas <brouard@localhost> 734: 735: * imach.c (Module): Memory leaks checks with valgrind and: 736: datafile was not closed, some imatrix were not freed and on matrix 737: allocation too. 738: 739: 2006-02-09 LIEVRE Agnes <lievre@PC_00697.ined.fr> 740: 741: * strsep.c (Module): Inclusion because not in mingw32!!! 742: 743: * setup.iss.in (Module): IMACHSETUPVERSION added 744: 745: * noreg-setup.iss (Module): added to cvs tree 746: 747: * Makefile (Module): IMACHSETUPVERSION added 748: 749: 2006-01-30 BROUARD Nicolas <brouard@localhost> 750: 751: * Makefile (Module, Module): Latest Makefile 752: 753: * imach.c (Module): Back to gnuplot.exe instead of wgnuplot.exe 754: 755: 2006-01-27 BROUARD Nicolas <brouard@localhost> 756: 757: * noreg-setup.iss (Module): ADDED 758: 759: 2006-01-24 BROUARD Nicolas <brouard@localhost> 760: 761: * imach.c (Module): Comments (lines starting with a #) are allowed in data. 762: 763: 2005-10-25 Nicolas Brouard <brouard@dhcp171.recherche.ined.fr> 764: 765: * Makefile (Module): Added Imach98.pmsp and howto crete a dmg 766: 767: * createdmg.sh (Module): Creates a dmg disk for MaC OS/X 768: 769: 2005-09-30 <lievre@PC_00595> 770: 771: * imach.c (Module): sump fixed, loop imx fixed, and simplifications. 772: (Module): If the status is missing at the last wave but we know 773: that the person is alive, then we can code his/her status as -2 774: (instead of missing=-1 in earlier versions) and his/her 775: contributions to the likelihood is 1 - Prob of dying from last 776: health status (= 1-p13= p11+p12 in the easiest case of somebody in 777: the healthy state at last known wave). Version is 0.98 778: 779: 2004-05-20 Brouard Nicolas <brouard@localhost> 780: 781: * imach.c (Repository): 782: Agnes added a direct estimation of mortality (without the need of 783: computing period prevalence and differential mortality). Thus here 784: is version 0.97a which has been distributed to some people at 785: REVES 16 in Brugge using an Inno setup.exe for PCs. Estimates of 786: mortality using covariates is not done today. Estimating direct 787: mortality is a very different process because it doesn't need 788: interpolation because it is easy to get the lx from the force of 789: the mortality mux in the simplest case as for a Gompertz (log mux 790: = a + b*x . But we have been able to incorporate the new code 791: within former imach program (0.96d) without deteriorating too much 792: the understanding of the program. 793: 794: 2003-06-25 <brouard@BROUARD> 795: 796: * imach.c (Module): On windows (cygwin) function asctime_r doesn't 797: exist so I changed back to asctime which exists. 798: (Module): Version 0.96b 799: 800: 2003-06-24 <brouard@BROUARD> 801: 802: * imach.c (Module): Some bugs corrected for windows. Also, when 803: mle=-1 a template is output in file "or"mypar.txt with the design 804: of the covariance matrix to be input. 805: 806: 2003-06-25 Brouard Nicolas <brouard@homebrou> 807: 808: * imach.c (Repository): Duplicated warning errors corrected. 809: (Repository): Elapsed time after each iteration is now output. It 810: helps to forecast when convergence will be reached. Elapsed time 811: is stamped in powell. We created a new html file for the graphs 812: concerning matrix of covariance. It has extension -cov.htm. 813: 814: 2003-06-23 Brouard Nicolas <brouard@homebrou> 815: 816: * 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. 817: 818: 2003-06-18 Brouard Nicolas <brouard@homebrou> 819: 820: * imach.c (Repository): Suppress abusive calls to append to file html (solution was to put fichtm as a global variable. Version 0.96 821: 822: 2003-06-17 Brouard Nicolas <brouard@homebrou> 823: 824: 825: * imach.c (Repository): Check when date of death was earlier that 826: current date of interview. It may happen when the death was just 827: prior to the death. In this case, dh was negative and likelihood 828: was wrong (infinity). We still send an "Error" but patch by 829: assuming that the date of death was just one stepm after the 830: interview. 831: (Repository): Because some people have very long ID (first column) 832: we changed int to long in num[] and we added a new lvector for 833: memory allocation. But we also truncated to 8 characters (left 834: truncation) 835: 836: (Repository): No more line truncation errors. 837: 838: 2003-06-14 Brouard Nicolas <brouard@homebrou> 839: 840: * imach.c (Repository): Add of a routine likelione (likelihood 841: only once) which prints on a text file 842: (ilk) the contributions to the likelihood for each 843: individual/wave. 844: 845: 2003-06-13 Brouard Nicolas <brouard@homebrou> 846: * imach.c (Repository): Replace "freqsummary" at a correct 847: place. It differs from routine "prevalence" which may be called 848: many times. Probs is memory consuming and must be used with 849: parcimony. 850: 851: 2003-06-17 <brouard@BROUARD> 852: 853: * timeval.h (Module): Added included file to make use of 854: gettimeofday working on win32 with cygwin. 855: 856: 2003-05-16 Brouard Nicolas <brouard@brouard> 857: * imach.c (Module): Insert of a warning if the delay between two 858: waves is negative. 859: 860: * imach.c (Module): 861: 862: 2003-05-03 <brouard@BROUARD> 863: 864: * imach.c: Some cleaning 865: 866: 2003-03-28 <brouard@BROUARD> 867: * imach.c (Module): In version up to 0.92 likelihood was computed 868: as if date of death was unknown. Death was treated as any other 869: health state: the date of the interview describes the actual state 870: and not the date of a change in health state. The former idea was 871: to consider that at each interview the state was recorded 872: (healthy, disable or death) and IMaCh was corrected; but when we 873: introduced the exact date of death then we should have modified 874: the contribution of an exact death to the likelihood. This new 875: contribution is smaller and very dependent of the step unit 876: stepm. It is no more the probability to die between last interview 877: and month of death but the probability to survive from last 878: interview up to one month before death multiplied by the 879: probability to die within a month. Thanks to Chris 880: Jackson for correcting this bug. Former versions increased 881: mortality artificially. The bad side is that we add another loop 882: which slows down the processing. The difference can be up to 10% 883: lower mortality. 884: 885: 2002-05-30 <brouard@BROUARD> 886: 887: * imach.c (Module): Add correlation matrix of one-step 888: probabilities and covariance matrix 889: