imach/src/ChangeLog - view

File: [Local Repository] / imach / src / ChangeLog
Revision 1.60: download - view: text, annotated - select for diffs
Sun Sep 11 07:57:18 2022 UTC (21 months, 2 weeks ago) by brouard
Branches: MAIN
CVS tags: HEAD

Summary: 0.99r37

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