imach/src/ChangeLog - view

File: [Local Repository] / imach / src / ChangeLog
Revision 1.70: download - view: text, annotated - select for diffs
Sun May 12 20:28:58 2024 UTC (6 weeks, 2 days ago) by brouard
Branches: MAIN
CVS tags: HEAD

Summary: Version 0.99s5

1: 2024-05-12 Nicolas Brouard <brouard@ined.fr> 2: 3: * imach.c Version 0.99s5 In fact, the covariance of total life 4: expectancy e.. with a partial life expectancy e.j is high, 5: therefore the complete matrix of variance covariance has to be 6: included in the formula of the standard error of the proportion of 7: total life expectancy spent in a specific state: 8: var(X/Y)=mu_x^2/mu_y^2*(sigma_x^2/mu_x^2 -2 9: sigma_xy/mu_x/mu_y+sigma^2/mu_y^2). Also an error with mle=-3 10: made the program core dump. It is fixed in this version. 11: 12: 2024-04-30 Nicolas Brouard <brouard@ined.fr> 13: 14: * (Module): In version 0.99s4, we incorporated the calculation of 15: the std error of the proportion of total life expectancy spent in 16: a specific state Var(e.j/e..) using the formula of Var(X/Y) 17: depending only of the variances of X and Y and expectancies. 18: 19: 2024-04-24 Nicolas Brouard <brouard@ined.fr> 20: 21: * (Module): This version comes late after having tested 22: successfully the praxis C version of Buckhardt. But Buckardt's 23: version was difficult to read and Gegenfurtner's version had a few 24: typos which made its results less reliable than Buckhardt's 25: results. The most important work consisted in retyping the Brent 26: original PRAXIS program written in Algol W (published with errors, 27: ommitting the transposition of matrix V before its QR reduction 28: from Golub. I used the recent "awe" compiler from Gkynn Webster. 29: The awe library had errors, for example in arc tangent function 30: which have been fixed. 31: 32: The main objective was to get identical results with the three 33: versions: (1) Algol W, (2) Buckhardt'C version as well (3) 34: Gegenfürtner C versions on the various test functions published by 35: Brent in 1973 in Algol W. 36: 37: Also, in order to compare them, the random function had to produce 38: the same sequence for the 3 softwares. The random function used in 39: imach corresponds to original Brent's random function written in 40: Algol W. Other point, in Algol W, the arrays of dimension n are 41: 'normal' mathematical arrays starting from 1 to n. But this is a 42: real issue in C where, by default, arrays are starting from 0 to 43: n-1. In Buckhardt, as well as in Gegenfürtner C code, it can be 44: seen that authors while trying to mimick original Brent Algol W 45: code are hesitating by changing either a loop originally from 1 to 46: n in a loop from 0 to n-1, or keeping Brent's loop from 1 to n and 47: shifting the index from original X(I) in Algol W to x[i-1] in C. 48: But as IMaCh is using, since the beginning, the Numerical Recipes 49: functions vector or matrix, I changed Geggenfürtner code to mimick 50: the original Algol W arrays. Thus the X(I) is translated in C as 51: x[i] which minimizes the errors. The Golub QR algorithm was 52: published in Algol with overflow errors which were reproduced in 53: Brent's Algol W code. Buckhardt code fixed these errors which are 54: much more problematic in C than in Algol W. Thus Buckhardt code 55: seems very safe, but i haven't chosen it for IMaCh because the C 56: style is horrible and almost unreadable compared to Gegenfürtner 57: CO code which is very close to Brent's original. Also what makes 58: Buckhardt code more difficult to read is, instead of passing the 59: minimum of parameters in the functions calls, as it is in Algol 60: Brent's code or Gegenfürtner's code, the list of parameters is 61: high. For example, the flin function LONG REAL PROCEDURE FLIN 62: (LONG REAL VALUE L) has only one parameter in Algol W, the 63: Gegenfürtner flin function had two parameters: static double 64: flin(l, j) double l; { int i; double tflin[N];} but Buckhardt 65: function has 14 parameters which makes the code unreadable and 66: useless. Gegenfürtner used a lot of static variables or functions 67: which I tried to minimize. Also in Gegefürtner, array dimensions 68: were fixed to N. In my adaptation the flin is static double 69: flin(double l, int j) and the parameter used are global variables. 70: 71: 2023-06-14 Nicolas Brouard <brouard@ined.fr> 72: 73: * imach.c (Module): Testing if conjugate gradient could be quicker 74: when lot of variables POWELLORIGINCONJUGATE 75: 76: 2023-05-23 Nicolas Brouard <brouard@ined.fr> 77: 78: * imach.c (Module): Fixed PROB_r 79: 80: 2023-05-22 Nicolas Brouard <brouard@ined.fr> 81: 82: * imach.c (Module): In the ILK....txt file, the number of columns 83: before the covariates values is dependent of the number of states (16+nlstate): 0.99r46 84: 85: 2023-05-08 Nicolas Brouard <brouard@ined.fr> 86: 87: * (Module): Error V0 when result:. and model 1+age+V1: fixed 88: 89: 2023-04-29 Nicolas Brouard <brouard@ined.fr> 90: 91: * imach.c (Module): Inverting the model equation and fixingg bugs 92: in the drawings 93: "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" 94: 95: 2023-04-24 Nicolas Brouard <brouard@ined.fr> 96: 97: * imach.c (Module): some bugs in printinggnuplot 98: 99: 2022-09-19 Nicolas Brouard <brouard@ined.fr> 100: 101: * imach.c (Module): Version 0.99r42 needed a newer version of 102: Gnuplot. But newer version 0.99r43 should run with the Gnuplot 103: version 5.0 or 5.1 distributed with IMaCh. 104: 105: 2022-09-18 Nicolas Brouard <brouard@ined.fr> 106: 107: * imach.c (Module): Fixing when a state in the data is 0 or higher 108: than lstate+ndeath. Fixing the plot of contribution to Likelihood. 109: 110: 2022-09-16 Nicolas Brouard <brouard@ined.fr> 111: 112: * imach.c (Module): 0.99r41 Was an error when product of timevarying and fixed. Using FixedV[of name] now. Thank you Feinuo 113: 114: 2022-09-14 Nicolas Brouard <brouard@ined.fr> 115: 116: * imach.c (Module): Fixing names of variables in T_ (thanks to Feinuo) 117: 118: 2022-09-14 Nicolas Brouard <brouard@ined.fr> 119: 120: * imach.c (Module): Version 0.99r39 with colored dummy covariates 121: (fixed or time varying), using new last columns of 122: ILK_parameter.txt file. 123: 124: 2022-09-11 Nicolas Brouard <brouard@ined.fr> 125: 126: * imach.c (Module): Adding timevarying products of any kinds, 127: should work before shifting cotvar from ncovcol+nqv columns in 128: order to have a correspondance between the column of cotvar and 129: the id of column. 130: (Module): Some cleaning and adding covariates in ILK.txt 131: 132: 2022-09-09 Nicolas Brouard <brouard@ined.fr> 133: 134: * imach.c (Module): Many improvements for fixing products of fixed 135: timevarying as well as fixed * fixed, and test with quantitative 136: covariate. 137: 138: 2022-09-04 Nicolas Brouard <brouard@ined.fr> 139: 140: * imach.c (Module): Now the easy runs i.e. without result or 141: model=1+age only did not work. The defautl combination should be 1 142: and not 0 because everything hasn't been tranformed yet. 143: 144: 2022-09-02 Nicolas Brouard <brouard@ined.fr> 145: 146: * imach.c: Version 0.99r35 because it outputs same results with 147: 1+age+V1+V1*age for females and 1+age for females only 148: (education=1 noweight) 149: 150: 2022-08-31 Nicolas Brouard <brouard@ined.fr> 151: 152: * imach.c (Module): Some improvments in fichtm and many verifications 0.99r34 153: 154: 2022-08-21 Nicolas Brouard <brouard@ined.fr> 155: 156: * imach.c (Module): Version 0.99r33 A lot of changes in 157: reassigning covariates: my first idea was that people will always 158: use the first covariate V1 into the model but in fact they are 159: producing data with many covariates and can use an equation model 160: with some of the covariate; it means that in a model V2+V3 instead 161: of codtabm(k,Tvaraff[j]) which calculates for combination k, for 162: three covariates (V1, V2, V3) the value of Tvaraff[j], but in fact 163: the equation model is restricted to two variables only (V2, V3) 164: and the combination for V2 should be codtabm(k,1) instead of 165: (codtabm(k,2), and the code should be 166: codtabm(k,TnsdVar[Tvaraff[j]]. Many many changes have been 167: made. All of these should be simplified once a day like we did in 168: hpxij() for example by using precov[nres] which is computed in 169: decoderesult for each nres of each resultline. Loop should be done 170: on the equation model globally by distinguishing only product with 171: age (which are changing with age) and no more on type of 172: covariates, single dummies, single covariates. 173: 174: 2022-08-06 Nicolas Brouard <brouard@ined.fr> 175: 176: * imach.c (Module): Version of imach using partly decoderesult to rebuild xpxij function 177: 178: 2022-08-03 Nicolas Brouard <brouard@ined.fr> 179: 180: * imach.c (Module): Many errors in graphs fixed with Vn*age covariates. 181: 182: 2022-07-25 Brouard Nicolas <brouard@brouard.name> 183: 184: * imach.c (Module): Error cptcovn instead of nsd in bmij (was 185: coredumped, revealed by Feiuno, thank you. 186: 187: 2022-07-23 Nicolas Brouard <brouard@ined.fr> 188: 189: * r29 W and not sqrt(Wald) 190: 191: 2022-07-22 Nicolas Brouard <brouard@ined.fr> 192: 193: * imach.c (Module): Output of Wald test in the htm file and not only in the log. 194: 195: 2022-06-02 Brouard Nicolas <brouard@brouard.name> 196: 197: * imach.c (Module): Adding the Wald tests from the log to the main 198: htm for better display of the maximum likelihood estimators. 199: 200: 2022-05-30 Brouard Nicolas <brouard@brouard.name> 201: 202: * imach.c: With products of covariates (age or dummies or 203: quantitatives), estimates of parameters were good but when 204: estimating variances the positions of newly created covariates 205: were wrongly assigned and results were wrong. Thank to Feinua_Sun! 206: 207: 2022-05-24 Nicolas Brouard <brouard@ined.fr> 208: 209: * imach.c (Module): Some attempts to find a bug of wrong estimates 210: of confidencce intervals with product in the equation modelC 211: 212: 2022-05-15 Nicolas Brouard <brouard@ined.fr> 213: 214: * imach.c (Module): Some minor improvements 215: 216: 2022-04-13 Brouard Nicolas <brouard@brouard.name> 217: 218: * imach.c (Module): Adding link to text data files 219: 220: 2022-04-11 Nicolas Brouard <brouard@ined.fr> 221: 222: * imach.c (Module): Error in rewriting the 'r' file with yearsfproj or yearsbproj fixed 223: 224: 2022-04-05 Brouard Nicolas <brouard@ined.fr> 225: 226: * imach.c (Module): Fixed covariates (dummy or quantitative) 227: with missing values have never been allowed but are ERRORS and 228: program quits. Standard deviations of fixed covariates were 229: wrongly computed. Mean and standard deviations of time varying 230: covariates are still not computed. 231: 232: 2022-03-17 Brouard Nicolas <brouard@ined.fr> 233: 234: * 99r25 Improvements in fixing discrepancies between covariates 235: missing in result line but in model. 236: 237: *Wed Mar 31 2021 Nicolas Brouard <brouard@ined.fr> 238: * imach.c (Module): Still bugs in the result loop. Thank to Holly Benett 239: 240: *2021-03-08 Nicolas Brouard <brouard@ined.fr> 241: 242: * ./ (Module): Fixed bug on result: 243: 244: *2021-02-20 Nicolas Brouard <brouard@ined.fr> 245: 246: * imach.c (Module): Fix bug on quitting after result lines! 247: (Module): Version 0.99r21 248: 249: 2021-02-12 Nicolas Brouard <brouard@ined.fr> 250: 251: * imach.c (Module): The use of a Windows BOM (huge) file is now an error 252: 253: 254: 2021-02-11 Nicolas Brouard <brouard@ined.fr> 255: 256: * (Module): imach.c Someone entered 'results:' instead of 'result:'. Now it is an error which is printed. 257: 258: 2020-02-22 Brouard Nicolas <brouard@ined.fr> 259: 260: * (Module): imach.c Update mle=-3 (for computing Life expectancy 261: and life table from the data without any state) 262: 263: 2019-05-20 Brouard Nicolas <brouard@ined.fr> 264: 265: * version.h: Summary: version 0.99.r19 266: 267: * imach.c: Summary: Projection syntax simplified 268: We can now start projections, forward or backward, from the mean date 269: of inteviews up to or down to a number of years of projection: 270: prevforecast=1 yearsfproj=15.3 mobil_average=0 271: or 272: prevforecast=1 starting-proj-date=1/1/2007 final-proj-date=12/31/2017 mobil_average=0 273: or 274: prevbackcast=1 yearsbproj=12.3 mobil_average=1 275: or 276: prevbackcast=1 starting-back-date=1/10/1999 final-back-date=1/1/1985 mobil_average=1 277: 278: 2019-05-18 Brouard Nicolas <brouard@ined.fr> 279: 280: * imach.c: Summary: doxygen tex bug 281: 282: 2019-05-16 Brouard Nicolas <brouard@ined.fr> 283: 284: * imach.c: Summary: There was some wrong lines added 285: 286: 2019-05-09 Brouard Nicolas <brouard@ined.fr> 287: 288: * Makefile, imach.c: *** empty log message *** 289: 290: * ChangeLog: Summary: C= 291: 292: * imach.c: Summary: Some updates 293: 294: * imach.c: Summary: Before ncovmax 295: 296: * version.h: *** empty log message *** 297: 298: * imach.c: Summary: 0.99r18 unlimited number of individuals 299: 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. 300: 301: 2018-12-13 Brouard Nicolas <brouard@ined.fr> 302: 303: * imach.c: Summary: Bug for young ages (<-30) will be in r17 304: 305: 2018-12-05 Brouard Nicolas <brouard@ined.fr> 306: 307: * Makefile: Summary: 0.99r16 308: 309: 2018-05-02 Brouard Nicolas <brouard@ined.fr> 310: 311: * imach.c: Summary: Some bugs fixed 312: 313: 2018-05-02 Brouard Nicolas <brouard@ined.fr> 314: 315: * imach.c: Summary: Bug for young ages (<-30) will be in r17 316: 317: 2018-05-02 Brouard Nicolas <brouard@ined.fr> 318: 319: * imach.c: Summary: Some bugs fixed 320: 321: 2018-05-01 Brouard Nicolas <brouard@ined.fr> 322: 323: * imach.c: 324: Summary: Bug fixed by providing frequencies only for non missing covariates 325: 326: 2018-04-27 Brouard Nicolas <brouard@ined.fr> 327: 328: * imach.c: Summary: some minor bugs 329: 330: 2018-04-21 Brouard Nicolas <brouard@ined.fr> 331: 332: * README.txt: *** empty log message *** 333: 334: * imach.c: Summary: Some bugs fixed, valgrind tested 335: 336: 2018-04-20 Brouard Nicolas <brouard@ined.fr> 337: 338: * Makefile, README.txt, setup.iss: Summary: imach 0.99r16 339: 340: * imach.c: 341: Summary: Computing mean and stdeviation of fixed quantitative variables 342: 343: 2018-04-19 Brouard Nicolas <brouard@ined.fr> 344: 345: * imach.c: Summary: Some minor bugs fixed 346: 347: * version.h: *** empty log message *** 348: 349: 2018-02-27 Brouard Nicolas <brouard@ined.fr> 350: 351: * imach.c: *** empty log message *** 352: 353: * imach.c: Summary: Adding second argument for quitting 354: 355: 2018-02-21 Brouard Nicolas <brouard@ined.fr> 356: 357: * Makefile, README.txt, imach.c: Summary: 0.99r15 358: New Makefile with recent VirtualBox 5.26. Bug in sqrt negatve in imach.c 359: 360: 2017-07-20 Brouard Nicolas <brouard@ined.fr> 361: 362: * imach.c: Summary: temporary working 363: 364: 2017-07-19 Brouard Nicolas <brouard@ined.fr> 365: 366: * imach.c: Summary: Bug for mobil_average=0 and prevforecast fixed(?) 367: 368: 2017-07-17 Brouard Nicolas <brouard@ined.fr> 369: 370: * imach.c: Summary: BOM files can be read now 371: 372: 2017-06-30 Brouard Nicolas <brouard@ined.fr> 373: 374: * imach.c: Summary: Graphs improvements 375: 376: * imach.c: Summary: Saito's color 377: 378: 2017-06-29 Brouard Nicolas <brouard@ined.fr> 379: 380: * imach.c: Summary: Version 0.99r14 381: 382: 2017-06-27 Brouard Nicolas <brouard@ined.fr> 383: 384: * imach.c: Summary: More documentation on projections 385: 386: * imach.c: Summary: Color of backprojection changed from 6 to 5(yellow) 387: 388: * imach.c: Summary: Some bug with rint 389: 390: 2017-05-24 Brouard Nicolas <brouard@ined.fr> 391: 392: * imach.c: *** empty log message *** 393: 394: 2017-05-23 Brouard Nicolas <brouard@ined.fr> 395: 396: * imach.c: Summary: Code into subroutine, cleanings 397: 398: 2017-05-18 Brouard Nicolas <brouard@ined.fr> 399: 400: * imach.c: 401: Summary: backprojection and confidence intervals of backprevalence 402: 403: 2017-05-13 Brouard Nicolas <brouard@ined.fr> 404: 405: * imach.c: Summary: temporary save for backprojection 406: 407: * imach.c: Summary: Version 0.99r13 (improvements and bugs fixed) 408: 409: 2017-04-26 Brouard Nicolas <brouard@ined.fr> 410: 411: * imach.c: Summary: imach 0.99r13 Some bugs fixed 412: 413: * imach.c: Summary: Labels in graphs 414: 415: 2017-04-24 Brouard Nicolas <brouard@ined.fr> 416: 417: * imach.c: Summary: to save 418: 419: 2017-04-18 Brouard Nicolas <brouard@ined.fr> 420: 421: * imach.c: *** empty log message *** 422: 423: 2017-04-05 Brouard Nicolas <brouard@ined.fr> 424: 425: * imach.c: Summary: Bug in E_ as well as in T_ fixed nres-1 vs k1-1 426: 427: 2017-04-04 Brouard Nicolas <brouard@ined.fr> 428: 429: * imach.c: Summary: Gnuplot indexations fixed (humm) 430: 431: * imach.c: 432: Summary: Some errors to warnings only if date of death is unknown but status is death we could set to pi3 433: 434: 2017-04-03 Brouard Nicolas <brouard@ined.fr> 435: 436: * imach.c: Summary: Version 0.99r12 437: Some cleanings, conformed with updated documentation. 438: 439: 2017-03-30 Brouard Nicolas <brouard@ined.fr> 440: 441: * version.h: *** empty log message *** 442: 443: * version.h: Summary:0.99r11 444: 445: 2017-03-29 Brouard Nicolas <brouard@ined.fr> 446: 447: * imach.c: Summary: Temp 448: 449: 2017-03-27 Brouard Nicolas <brouard@ined.fr> 450: 451: * imach.c: Summary: Temporary 452: 453: 2017-03-08 Brouard Nicolas <brouard@ined.fr> 454: 455: * imach.c: Summary: IMaCh version 0.99r10 bugs in gnuplot fixed 456: 457: * imach.c: Summary: Fixing data parameter line 458: 459: 2016-12-15 Brouard Nicolas <brouard@ined.fr> 460: 461: * imach.c: Summary: 0.99 in progress 462: 463: 2016-09-15 Brouard Nicolas <brouard@ined.fr> 464: 465: * imach.c: *** empty log message *** 466: 467: * imach.c: Summary: not working 468: 469: 2016-09-08 Brouard Nicolas <brouard@ined.fr> 470: 471: * imach.c: Summary: continue 472: 473: 2016-09-07 Brouard Nicolas <brouard@ined.fr> 474: 475: * imach.c: Summary: Starting values from frequencies 476: 477: * imach.c: *** empty log message *** 478: 479: 2016-09-02 Brouard Nicolas <brouard@ined.fr> 480: 481: * imach.c: *** empty log message *** 482: 483: 2016-08-30 Brouard Nicolas <brouard@ined.fr> 484: 485: * imach.c: Summary: Fixing a lots 486: 487: 2016-08-29 Brouard Nicolas <brouard@ined.fr> 488: 489: * imach.c: Summary: gnuplot problem in Back projection to fix 490: 491: * imach.c: Summary: Better 492: 493: 2016-08-26 Brouard Nicolas <brouard@ined.fr> 494: 495: * imach.c: 496: Summary: Improvement in Powell output in order to copy and paste 497: 498: * imach.c: Summary: Starting tests of 0.99 499: 500: * imach.c: Summary: to valgrind 501: 502: 2016-08-25 Brouard Nicolas <brouard@ined.fr> 503: 504: * imach.c: *** empty log message *** 505: 506: 2016-08-23 Brouard Nicolas <brouard@ined.fr> 507: 508: * imach.c: *** empty log message *** 509: 510: * imach.c: Summary: not working 511: 512: 2016-08-22 Brouard Nicolas <brouard@ined.fr> 513: 514: * imach.c: Summary: not working 515: 516: * imach.c: Summary: Not working 517: 518: 2016-07-23 Brouard Nicolas <brouard@ined.fr> 519: 520: * imach.c: Summary: Completing for func too 521: 522: 2016-07-22 Brouard Nicolas <brouard@ined.fr> 523: 524: * imach.c: Summary: Fixing some arrays, still debugging 525: 526: 2016-07-21 Brouard Nicolas <brouard@ined.fr> 527: 528: * imach.c: 529: Summary: 0.99 working (more or less) for Asian Workshop on multitate methods 530: 531: 2016-07-12 Brouard Nicolas <brouard@ined.fr> 532: 533: * imach.c: Summary: temp 534: 535: * imach.c: Summary: saving but not running 536: 537: 2016-07-01 Brouard Nicolas <brouard@ined.fr> 538: 539: * imach.c: Summary: Fixes 540: 541: 2016-02-19 Brouard Nicolas <brouard@ined.fr> 542: 543: * imach-0.98r.c: Summary: Kind of 0.98r? series, starting with r7 544: 545: * setup.iss, Makefile, version.h: *** empty log message *** 546: 547: * imach.c: Summary: temporary 548: 549: 2016-02-17 Brouard Nicolas <brouard@ined.fr> 550: 551: * imach.c: Summary: Probably last 0.98 stable version 0.98r6 552: 553: 2016-02-16 Brouard Nicolas <brouard@ined.fr> 554: 555: * imach.c: Summary: minor bug 556: 557: * imach.c: Summary: 0.99r2 558: 559: 2016-02-15 Brouard Nicolas <brouard@ined.fr> 560: 561: * imach.c: *** empty log message *** 562: 563: 2016-02-12 Brouard Nicolas <brouard@ined.fr> 564: 565: * imach.c: Summary: 0.99 Back projections 566: 567: 2015-12-23 Brouard Nicolas <brouard@ined.fr> 568: 569: * imach.c: Summary: Experimental backcast 570: 571: 2015-12-18 Brouard Nicolas <brouard@ined.fr> 572: 573: * imach.c: Summary: 0.98r4 Warning and status=-2 574: 575: Version 0.98r4 is now: 576: - displaying an error when status is -1, date of interview unknown and date of death known; 577: - permitting a status -2 when the vital status is unknown at a known date of right truncation. 578: Older changes concerning s=-2, dating from 2005 have been supersed. 579: 580: * Makefile: *** empty log message *** 581: 582: 2015-12-16 Brouard Nicolas <brouard@ined.fr> 583: 584: * Makefile: *** empty log message *** 585: 586: * imach.c: Summary: 0.98r4 working 587: 588: * Makefile: Summary: linuxrpm added 589: 590: * Makefile: *** empty log message *** 591: 592: * imach.c: Summary: temporary not working 593: 594: 2015-12-11 Brouard Nicolas <brouard@ined.fr> 595: 596: * imach.c: Summary: 0.98r4 597: 598: 2015-12-08 Brouard Nicolas <brouard@ined.fr> 599: 600: * Makefile: *** empty log message *** 601: 602: 2015-11-21 Brouard Nicolas <brouard@ined.fr> 603: 604: * Makefile: 605: Summary: VBoxManage change from execute --image to run --exe and --wait-exit doesn't exist any more 606: 607: * imach.c: Summary: minor typo 608: 609: * imach.c: Summary: 0.98r3 with some graph of projected cross-sectional 610: 611: Author: Nicolas Brouard 612: 613: 2015-11-18 Brouard Nicolas <brouard@ined.fr> 614: 615: * imach.c: Summary: Start working on projected prevalences 616: 617: 2015-11-17 Brouard Nicolas <brouard@ined.fr> 618: 619: * imach.c: Summary: Adding ftolpl parameter 620: Author: N Brouard 621: 622: We had difficulties to get smoothed confidence intervals. It was due 623: to the period prevalence which wasn't computed accurately. The inner 624: parameter ftolpl is now an outer parameter of the .imach parameter 625: file after estepm. If ftolpl is small 1.e-4 and estepm too, 626: computation are long. 627: 628: * version.h: *** empty log message *** 629: 630: * imach.c: Summary: temporary 631: 632: 2015-10-27 Brouard Nicolas <brouard@ined.fr> 633: 634: * Makefile: *** empty log message *** 635: 636: * setup.iss.in: Summary: some new subdirs 637: 638: * imach.c: *** empty log message *** 639: 640: * setup.iss.in: 641: Summary: Adding gnuplot 5.1 with bin and etc for pango fonts 642: 643: 2015-10-24 Brouard Nicolas <brouard@ined.fr> 644: 645: * imach.c: *** empty log message *** 646: 647: 2015-10-23 Brouard Nicolas <brouard@ined.fr> 648: 649: * imach.c: 650: Summary: 0.98r3 some clarification for graphs on likelihood contributions 651: 652: 2015-10-01 Brouard Nicolas <brouard@ined.fr> 653: 654: * imach.c: Summary: Some new graphs of contribution to likelihood 655: 656: 2015-09-30 Brouard Nicolas <brouard@ined.fr> 657: 658: * Makefile: 659: Summary: Version read from version.h, itself read with cmake 660: 661: * imach.c: Summary: looking at better estimation of the hessian 662: 663: Also a better criteria for convergence to the period prevalence And 664: therefore adding the number of years needed to converge. (The 665: prevalence in any alive state shold sum to one 666: 667: * Makefile: *** empty log message *** 668: 669: 2015-09-22 Brouard Nicolas <brouard@ined.fr> 670: 671: * imach.c: 672: Summary: Adding some overall graph on contribution to likelihood. Might change 673: 674: 2015-09-15 Brouard Nicolas <brouard@ined.fr> 675: 676: * Makefile: *** empty log message *** 677: 678: * imach.c: Summary: 0.98r0 679: 680: - Some new graphs like survival functions 681: - Some bugs fixed like model=1+age+V2. 682: 683: * ChangeLog, Makefile: Summary: 0.98r0 684: 685: * CMakeLists.txt: Summary: Some tests for setup.iss 686: 687: 2015-09-15 Nicolas J Brouard <nbrouard@tugault.ined.fr> 688: 689: * (Module): 0.98r0 Some new graphs, some bugs fixed: model=1+age+V2. etc 690: 691: 2015-08-18 Nicolas J Brouard <nbrouard@tugault.local> 692: 693: * (Module): Adding error when the covariance matrix doesn't contain the exact number of lines required by the model line. 694: 695: 2015-08-03 Nicolas J Brouard <nbrouard@tugault.ined.fr> 696: 697: * (Module): Changing Variance of one-step probabilities into Standard deviation (thanks to Yao-Chi Shih) 698: 699: 2014-12-16 Nicolas J Brouard <nbrouard@tugault.local> 700: 701: * imach.c (Module): Merging 1.61 to 1.162 702: 703: 2014-09-02 Nicolas J Brouard <nbrouard@njbrouard.ined.fr> 704: 705: * prevlim.h (Module): 706: 707: 2014-01-26 Nicolas J Brouard <nbrouard@ledermann-2.local> 708: 709: * imach.c (Module): Trying to merge old staffs together while being at Tokyo. Not tested... 710: (Module): Version 0.98nR Running ok, but output format still only works for three covariates. 711: 712: 2010-04-29 brouard <brouard@ined.fr> 713: 714: * imach.c (Module): Checking covariates for more complex models 715: than V1+V2. A lot of change to be done. Unstable. 716: 717: 2010-04-26 brouard <brouard@ined.fr> 718: 719: * imach.c (Module): merging some libgsl code. Fixing computation 720: of likelione (using inter/intrapolation if mle = 0) in order to 721: get same likelihood as if mle=1. 722: Some cleaning of code and comments added. 723: 724: 2009-10-29 brouard <brouard@ined.fr> 725: 726: * imach.c (Module): Now imach stops if date of birth, at least year of birth, is not given. Some cleaning of the code. 727: 728: 2006-06-30 Brouard Nicolas <brouard@localhost> 729: 730: * imach.c (Module): Clarifications on computing e.j 731: 732: 2006-04-28 Brouard Nicolas <brouard@localhost> 733: 734: * imach.c (Module): Yes the sum of survivors was wrong since 735: imach-114 because nhstepm was no more computed in the age 736: loop. Now we define nhstepma in the age loop. 737: (Module): In order to speed up (in case of numerous covariates) we 738: compute health expectancies (without variances) in a first step 739: and then all the health expectancies with variances or standard 740: deviation (needs data from the Hessian matrices) which slows the 741: computation. 742: In the future we should be able to stop the program is only health 743: expectancies and graph are needed without standard deviations. 744: 745: 2006-04-04 LIEVRE Agnes <lievre@PC_00697.ined.fr> 746: 747: * imach.iss (Module): 748: 749: * imach.c (Module): bugs in evsi + population file added in htm output file 750: 751: 2006-03-22 LIEVRE Agnes <lievre@PC_00697.ined.fr> 752: 753: * imach.c (Module): 754: 755: 2006-03-20 Brouard Nicolas <brouard@localhost> 756: 757: * imach.c (Module): <title> changed, corresponds to .htm file 758: name. <head> headers where missing. 759: 760: * Makefile (Module): 0.98g 761: 762: * imach.c (Module): Weights can have a decimal point as for 763: English (a comma might work with a correct LC_NUMERIC environment, 764: otherwise the weight is truncated). 765: Modification of warning when the covariates values are not 0 or 766: 1. 767: Version 0.98g 768: 769: 2006-03-16 LIEVRE Agnes <lievre@PC_00697.ined.fr> 770: 771: * imach.c (Module): Comments concerning covariates added 772: 773: * noreg-setup.iss (Module): Version 0.98f 774: 775: * Makefile (Module): Version 0.98f make _windows=1 imachcyg-setup 776: 777: * imach.c (Module): refinements in the computation of lli if 778: status=-2 in order to have more reliable computation if stepm is 779: not 1 month. Version 0.98f 780: 781: 2006-03-15 Brouard Nicolas <brouard@localhost> 782: 783: * imach.c (Module): Bug if status = -2, the loglikelihood was 784: computed as likelihood omitting the logarithm. Version O.98e 785: 786: 2006-03-14 Brouard Nicolas <brouard@localhost> 787: 788: * imach.c (Module): varevsij Comments added explaining the second 789: table of variances if popbased=1 . 790: (Module): Covariances of eij, ekl added, graphs fixed, new html link. 791: (Module): Function pstamp added 792: (Module): Version 0.98d 793: 794: 2006-03-06 Brouard Nicolas <brouard@localhost> 795: 796: * imach.c (Module): Variance-covariance wrong links and 797: varian-covariance of ej. is needed (Saito). 798: 799: 2006-02-27 Brouard Nicolas <brouard@localhost> 800: 801: * imach.c (Module): One freematrix added in mlikeli! 802: 803: 2006-02-26 Brouard Nicolas <brouard@localhost> 804: 805: * imach.c (Module): Some improvements in processing parameter 806: filename with strsep. 807: 808: 2006-02-24 Brouard Nicolas <brouard@localhost> 809: 810: * imach.c (Module): Memory leaks checks with valgrind and: 811: datafile was not closed, some imatrix were not freed and on matrix 812: allocation too. 813: 814: 2006-02-09 LIEVRE Agnes <lievre@PC_00697.ined.fr> 815: 816: * strsep.c (Module): Inclusion because not in mingw32!!! 817: 818: * setup.iss.in (Module): IMACHSETUPVERSION added 819: 820: * noreg-setup.iss (Module): added to cvs tree 821: 822: * Makefile (Module): IMACHSETUPVERSION added 823: 824: 2006-01-30 BROUARD Nicolas <brouard@localhost> 825: 826: * Makefile (Module, Module): Latest Makefile 827: 828: * imach.c (Module): Back to gnuplot.exe instead of wgnuplot.exe 829: 830: 2006-01-27 BROUARD Nicolas <brouard@localhost> 831: 832: * noreg-setup.iss (Module): ADDED 833: 834: 2006-01-24 BROUARD Nicolas <brouard@localhost> 835: 836: * imach.c (Module): Comments (lines starting with a #) are allowed in data. 837: 838: 2005-10-25 Nicolas Brouard <brouard@dhcp171.recherche.ined.fr> 839: 840: * Makefile (Module): Added Imach98.pmsp and howto crete a dmg 841: 842: * createdmg.sh (Module): Creates a dmg disk for MaC OS/X 843: 844: 2005-09-30 <lievre@PC_00595> 845: 846: * imach.c (Module): sump fixed, loop imx fixed, and simplifications. 847: (Module): If the status is missing at the last wave but we know 848: that the person is alive, then we can code his/her status as -2 849: (instead of missing=-1 in earlier versions) and his/her 850: contributions to the likelihood is 1 - Prob of dying from last 851: health status (= 1-p13= p11+p12 in the easiest case of somebody in 852: the healthy state at last known wave). Version is 0.98 853: 854: 2004-05-20 Brouard Nicolas <brouard@localhost> 855: 856: * imach.c (Repository): 857: Agnes added a direct estimation of mortality (without the need of 858: computing period prevalence and differential mortality). Thus here 859: is version 0.97a which has been distributed to some people at 860: REVES 16 in Brugge using an Inno setup.exe for PCs. Estimates of 861: mortality using covariates is not done today. Estimating direct 862: mortality is a very different process because it doesn't need 863: interpolation because it is easy to get the lx from the force of 864: the mortality mux in the simplest case as for a Gompertz (log mux 865: = a + b*x . But we have been able to incorporate the new code 866: within former imach program (0.96d) without deteriorating too much 867: the understanding of the program. 868: 869: 2003-06-25 <brouard@BROUARD> 870: 871: * imach.c (Module): On windows (cygwin) function asctime_r doesn't 872: exist so I changed back to asctime which exists. 873: (Module): Version 0.96b 874: 875: 2003-06-24 <brouard@BROUARD> 876: 877: * imach.c (Module): Some bugs corrected for windows. Also, when 878: mle=-1 a template is output in file "or"mypar.txt with the design 879: of the covariance matrix to be input. 880: 881: 2003-06-25 Brouard Nicolas <brouard@homebrou> 882: 883: * imach.c (Repository): Duplicated warning errors corrected. 884: (Repository): Elapsed time after each iteration is now output. It 885: helps to forecast when convergence will be reached. Elapsed time 886: is stamped in powell. We created a new html file for the graphs 887: concerning matrix of covariance. It has extension -cov.htm. 888: 889: 2003-06-23 Brouard Nicolas <brouard@homebrou> 890: 891: * 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. 892: 893: 2003-06-18 Brouard Nicolas <brouard@homebrou> 894: 895: * imach.c (Repository): Suppress abusive calls to append to file html (solution was to put fichtm as a global variable. Version 0.96 896: 897: 2003-06-17 Brouard Nicolas <brouard@homebrou> 898: 899: 900: * imach.c (Repository): Check when date of death was earlier that 901: current date of interview. It may happen when the death was just 902: prior to the death. In this case, dh was negative and likelihood 903: was wrong (infinity). We still send an "Error" but patch by 904: assuming that the date of death was just one stepm after the 905: interview. 906: (Repository): Because some people have very long ID (first column) 907: we changed int to long in num[] and we added a new lvector for 908: memory allocation. But we also truncated to 8 characters (left 909: truncation) 910: 911: (Repository): No more line truncation errors. 912: 913: 2003-06-14 Brouard Nicolas <brouard@homebrou> 914: 915: * imach.c (Repository): Add of a routine likelione (likelihood 916: only once) which prints on a text file 917: (ilk) the contributions to the likelihood for each 918: individual/wave. 919: 920: 2003-06-13 Brouard Nicolas <brouard@homebrou> 921: * imach.c (Repository): Replace "freqsummary" at a correct 922: place. It differs from routine "prevalence" which may be called 923: many times. Probs is memory consuming and must be used with 924: parcimony. 925: 926: 2003-06-17 <brouard@BROUARD> 927: 928: * timeval.h (Module): Added included file to make use of 929: gettimeofday working on win32 with cygwin. 930: 931: 2003-05-16 Brouard Nicolas <brouard@brouard> 932: * imach.c (Module): Insert of a warning if the delay between two 933: waves is negative. 934: 935: * imach.c (Module): 936: 937: 2003-05-03 <brouard@BROUARD> 938: 939: * imach.c: Some cleaning 940: 941: 2003-03-28 <brouard@BROUARD> 942: * imach.c (Module): In version up to 0.92 likelihood was computed 943: as if date of death was unknown. Death was treated as any other 944: health state: the date of the interview describes the actual state 945: and not the date of a change in health state. The former idea was 946: to consider that at each interview the state was recorded 947: (healthy, disable or death) and IMaCh was corrected; but when we 948: introduced the exact date of death then we should have modified 949: the contribution of an exact death to the likelihood. This new 950: contribution is smaller and very dependent of the step unit 951: stepm. It is no more the probability to die between last interview 952: and month of death but the probability to survive from last 953: interview up to one month before death multiplied by the 954: probability to die within a month. Thanks to Chris 955: Jackson for correcting this bug. Former versions increased 956: mortality artificially. The bad side is that we add another loop 957: which slows down the processing. The difference can be up to 10% 958: lower mortality. 959: 960: 2002-05-30 <brouard@BROUARD> 961: 962: * imach.c (Module): Add correlation matrix of one-step 963: probabilities and covariance matrix 964: