imach/src/ChangeLog - view

File: [Local Repository] / imach / src / ChangeLog
Revision 1.66: download - view: text, annotated - select for diffs
Mon May 8 18:48:01 2023 UTC (17 months, 4 weeks ago) by brouard
Branches: MAIN
CVS tags: HEAD

*** empty log message ***

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