imach/src/ChangeLog - view

File: [Local Repository] / imach / src / ChangeLog
Revision 1.57: download - view: text, annotated - select for diffs
Sun Aug 21 09:37:34 2022 UTC (2 years, 2 months ago) by brouard
Branches: MAIN
CVS tags: HEAD

*** empty log message ***

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