imach/src/ChangeLog - view

File: [Local Repository] / imach / src / ChangeLog
Revision 1.59: download - view: text, annotated - select for diffs
Sun Sep 4 17:40:02 2022 UTC (21 months, 3 weeks ago) by brouard
Branches: MAIN
CVS tags: HEAD

*** empty log message ***

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