Diff for /imach096d/doc/imach.htm between versions 1.9 and 1.12

version 1.9, 2002/03/11 15:24:05 version 1.12, 2002/03/13 17:27:44
Line 37  color="#00006A">INED</font></a><font col Line 37  color="#00006A">INED</font></a><font col
 href="http://euroreves.ined.fr"><font color="#00006A">EUROREVES</font></a></h3>  href="http://euroreves.ined.fr"><font color="#00006A">EUROREVES</font></a></h3>
   
 <p align="center"><font color="#00006A" size="4"><strong>Version  <p align="center"><font color="#00006A" size="4"><strong>Version
 0.71a, March 2002</strong></font></p>  0.8, March 2002</strong></font></p>
   
 <hr size="3" color="#EC5E5E">  <hr size="3" color="#EC5E5E">
   
Line 279  weights or covariates, you must fill the Line 279  weights or covariates, you must fill the
 <h2><font color="#00006A">Your first example parameter file</font><a  <h2><font color="#00006A">Your first example parameter file</font><a
 href="http://euroreves.ined.fr/imach"></a><a name="uio"></a></h2>  href="http://euroreves.ined.fr/imach"></a><a name="uio"></a></h2>
   
 <h2><a name="biaspar"></a>#Imach version 0.71a, March 2002,  <h2><a name="biaspar"></a>#Imach version 0.8, March 2002,
 INED-EUROREVES </h2>  INED-EUROREVES </h2>
   
 <p>This is a comment. Comments start with a '#'.</p>  <p>This is a comment. Comments start with a '#'.</p>
Line 311  INED-EUROREVES </h2> Line 311  INED-EUROREVES </h2>
 <h4><a name="biaspar-2"><font color="#FF0000">Second uncommented  <h4><a name="biaspar-2"><font color="#FF0000">Second uncommented
 line</font></a></h4>  line</font></a></h4>
   
 <pre>ftol=1.e-08 stepm=1 ncov=2 nlstate=2 ndeath=1 maxwav=4 mle=1 weight=0</pre>  <pre>ftol=1.e-08 stepm=1 ncovcol=2 nlstate=2 ndeath=1 maxwav=4 mle=1 weight=0</pre>
   
 <ul>  <ul>
     <li><b>ftol=1e-8</b> Convergence tolerance on the function      <li><b>ftol=1e-8</b> Convergence tolerance on the function
Line 327  line</font></a></h4> Line 327  line</font></a></h4>
             <li>... </li>              <li>... </li>
         </ul>          </ul>
     </li>      </li>
     <li><b>ncov=2</b> Number of covariates in the datafile. </li>      <li><b>ncovcol=2</b> Number of covariate columns in the datafile
       which precede the date of birth. Here you can put variables that
       won't necessary be used during the run. It is not the number of
       covariates that will be specified by the model. The 'model'
       syntax describe the covariates to take into account. </li>
     <li><b>nlstate=2</b> Number of non-absorbing (alive) states.      <li><b>nlstate=2</b> Number of non-absorbing (alive) states.
         Here we have two alive states: disability-free is coded 1          Here we have two alive states: disability-free is coded 1
         and disability is coded 2. </li>          and disability is coded 2. </li>
Line 374  Additional covariates can be included wi Line 378  Additional covariates can be included wi
 </ul>  </ul>
   
 <p>In this example, we have two covariates in the data file  <p>In this example, we have two covariates in the data file
 (fields 2 and 3). The number of covariates is defined with  (fields 2 and 3). The number of covariates included in the data file
 statement ncov=2. If now you have 3 covariates in the datafile  between the id and the date of birth is ncovcol=2 (it was named ncov
 (fields 2, 3 and 4), you have to set ncov=3. Then you can run the  in version prior to 0.8). If you have 3 covariates in the datafile
   (fields 2, 3 and 4), you will set ncovcol=3. Then you can run the
 programme with a new parametrisation taking into account the  programme with a new parametrisation taking into account the
 third covariate. For example, <strong>model=V1+V3 </strong>estimates  third covariate. For example, <strong>model=V1+V3 </strong>estimates
 a model with the first and third covariates. More complicated  a model with the first and third covariates. More complicated
Line 394  optimization. The number of parameters, Line 399  optimization. The number of parameters,
 number of absorbing states and non-absorbing states and on the  number of absorbing states and non-absorbing states and on the
 number of covariates. <br>  number of covariates. <br>
 <em>N</em> is given by the formula <em>N</em>=(<em>nlstate</em> +  <em>N</em> is given by the formula <em>N</em>=(<em>nlstate</em> +
 <em>ndeath</em>-1)*<em>nlstate</em>*<em>ncov</em>&nbsp;. <br>  <em>ndeath</em>-1)*<em>nlstate</em>*<em>ncovmodel</em>&nbsp;. <br>
 <br>  <br>
 Thus in the simple case with 2 covariates (the model is log  Thus in the simple case with 2 covariates (the model is log
 (pij/pii) = aij + bij * age where intercept and age are the two  (pij/pii) = aij + bij * age where intercept and age are the two
Line 430  a large stepm i.e stepm=12 or 24 and the Line 435  a large stepm i.e stepm=12 or 24 and the
 stepm=1 month. If newstepm is the new shorter stepm and stepm can be  stepm=1 month. If newstepm is the new shorter stepm and stepm can be
 expressed as a multiple of newstepm, like newstepm=n stepm, then the  expressed as a multiple of newstepm, like newstepm=n stepm, then the
 following approximation holds:  following approximation holds:
 <pre>aij(n stepm) = aij(stepm) +ln(n)  <pre>aij(stepm) = aij(n . stepm) - ln(n)
 </pre> and  </pre> and
 <pre>bij(n stepm) = bij(stepm) .</pre>  <pre>bij(stepm) = bij(n . stepm) .</pre>
   
   <p> For example if you already ran for a 6 months interval and
   got:<br>
    <pre># Parameters
   12 -13.390179  0.126133
   13  -7.493460  0.048069
   21   0.575975 -0.041322
   23  -4.748678  0.030626
   </pre>
   If you now want to get the monthly estimates, you can guess the aij by
   substracting ln(6)= 1,7917<br> and running<br>
   <pre>12 -15.18193847  0.126133
   13 -9.285219469  0.048069
   21 -1.215784469 -0.041322
   23 -6.540437469  0.030626
   </pre>
   and get<br>
   <pre>12 -15.029768 0.124347
   13 -8.472981 0.036599
   21 -1.472527 -0.038394
   23 -6.553602 0.029856
   </br>
   which is closer to the results. The approximation is probably useful
   only for very small intervals and we don't have enough experience to
   know if you will speed up the convergence or not.
   <pre>         -ln(12)= -2.484
    -ln(6/1)=-ln(6)= -1.791
    -ln(3/1)=-ln(3)= -1.0986
   -ln(12/6)=-ln(2)= -0.693
   </pre>
   
 <h4><font color="#FF0000">Guess values for computing variances</font></h4>  <h4><font color="#FF0000">Guess values for computing variances</font></h4>
   
 <p>This is an output if <a href="#mle">mle</a>=1. But it can be  <p>This is an output if <a href="#mle">mle</a>=1. But it can be
Line 446  matrix of the parameters, that is the in Line 482  matrix of the parameters, that is the in
 matrix, and the variances of health expectancies. Each line  matrix, and the variances of health expectancies. Each line
 consists in indices &quot;ij&quot; followed by the initial scales  consists in indices &quot;ij&quot; followed by the initial scales
 (zero to simplify) associated with aij and bij. </p>  (zero to simplify) associated with aij and bij. </p>
   <ul> <li>If mle=1 you can enter zeros:</li>
 <ul>  <blockquote><pre># Scales (for hessian or gradient estimation)
     <li>If mle=1 you can enter zeros:</li>  
 </ul>  
   
 <blockquote>  
     <pre># Scales (for hessian or gradient estimation)  
 12 0. 0.  12 0. 0.
 13 0. 0.  13 0. 0.
 21 0. 0.  21 0. 0.
 23 0. 0. </pre>  23 0. 0. </pre>
 </blockquote>  </blockquote>
   
 <ul>  
     <li>If mle=0 you must enter a covariance matrix (usually      <li>If mle=0 you must enter a covariance matrix (usually
         obtained from an earlier run).</li>          obtained from an earlier run).</li>
 </ul>  </ul>
Line 469  consists in indices &quot;ij&quot; follo Line 498  consists in indices &quot;ij&quot; follo
 <p>This is an output if <a href="#mle">mle</a>=1. But it can be  <p>This is an output if <a href="#mle">mle</a>=1. But it can be
 used as an input to get the various output data files (Health  used as an input to get the various output data files (Health
 expectancies, stationary prevalence etc.) and figures without  expectancies, stationary prevalence etc.) and figures without
 rerunning the rather long maximisation phase (mle=0). </p>  rerunning the rather long maximisation phase (mle=0). <br>
   Each line starts with indices &quot;ijk&quot; followed by the
 <p>Each line starts with indices &quot;ijk&quot; followed by the  covariances between aij and bij:<br>
 covariances between aij and bij: </p>  
   
 <pre>  <pre>
    121 Var(a12)     121 Var(a12)
    122 Cov(b12,a12)  Var(b12)     122 Cov(b12,a12)  Var(b12)
           ...            ...
    232 Cov(b23,a12)  Cov(b23,b12) ... Var (b23) </pre>     232 Cov(b23,a12)  Cov(b23,b12) ... Var (b23) </pre>
   
 <ul>  <ul>
     <li>If mle=1 you can enter zeros. </li>      <li>If mle=1 you can enter zeros. </li>
 </ul>  
   
 <blockquote>  
     <pre># Covariance matrix      <pre># Covariance matrix
 121 0.  121 0.
 122 0. 0.  122 0. 0.
Line 494  covariances between aij and bij: </p> Line 517  covariances between aij and bij: </p>
 212 0. 0. 0. 0. 0. 0.  212 0. 0. 0. 0. 0. 0.
 231 0. 0. 0. 0. 0. 0. 0.  231 0. 0. 0. 0. 0. 0. 0.
 232 0. 0. 0. 0. 0. 0. 0. 0.</pre>  232 0. 0. 0. 0. 0. 0. 0. 0.</pre>
 </blockquote>  
   
 <ul>  
     <li>If mle=0 you must enter a covariance matrix (usually      <li>If mle=0 you must enter a covariance matrix (usually
         obtained from an earlier run).<br>          obtained from an earlier run). </li>
         </li>  
 </ul>  </ul>
   
 <h4><font color="#FF0000">Age range for calculation of stationary  <h4><font color="#FF0000">Age range for calculation of stationary
Line 507  prevalences and health expectancies</fon Line 526  prevalences and health expectancies</fon
   
 <pre>agemin=70 agemax=100 bage=50 fage=100</pre>  <pre>agemin=70 agemax=100 bage=50 fage=100</pre>
   
 <p>Once we obtained the estimated parameters, the program is able  <br>Once we obtained the estimated parameters, the program is able
 to calculated stationary prevalence, transitions probabilities  to calculated stationary prevalence, transitions probabilities
 and life expectancies at any age. Choice of age range is useful  and life expectancies at any age. Choice of age range is useful
 for extrapolation. In our data file, ages varies from age 70 to  for extrapolation. In our data file, ages varies from age 70 to
 102. It is possible to get extrapolated stationary prevalence by  102. It is possible to get extrapolated stationary prevalence by
 age ranging from agemin to agemax. </p>  age ranging from agemin to agemax.
   
 <p>Setting bage=50 (begin age) and fage=100 (final age), makes  <br>Setting bage=50 (begin age) and fage=100 (final age), makes
 the program computing life expectancy from age 'bage' to age  the program computing life expectancy from age 'bage' to age
 'fage'. As we use a model, we can interessingly compute life  'fage'. As we use a model, we can interessingly compute life
 expectancy on a wider age range than the age range from the data.  expectancy on a wider age range than the age range from the data.
 But the model can be rather wrong on much larger intervals.  But the model can be rather wrong on much larger intervals.
 Program is limited to around 120 for upper age!</p>  Program is limited to around 120 for upper age!
   
 <ul>  <ul>
     <li><b>agemin=</b> Minimum age for calculation of the      <li><b>agemin=</b> Minimum age for calculation of the
         stationary prevalence </li>          stationary prevalence </li>
Line 537  color="#FF0000"> the observed prevalence Line 555  color="#FF0000"> the observed prevalence
   
 <pre>begin-prev-date=1/1/1984 end-prev-date=1/6/1988 </pre>  <pre>begin-prev-date=1/1/1984 end-prev-date=1/6/1988 </pre>
   
 <p>Statements 'begin-prev-date' and 'end-prev-date' allow to  <br>Statements 'begin-prev-date' and 'end-prev-date' allow to
 select the period in which we calculate the observed prevalences  select the period in which we calculate the observed prevalences
 in each state. In this example, the prevalences are calculated on  in each state. In this example, the prevalences are calculated on
 data survey collected between 1 january 1984 and 1 june 1988. </p>  data survey collected between 1 january 1984 and 1 june 1988.
   
 <ul>  <ul>
     <li><strong>begin-prev-date= </strong>Starting date      <li><strong>begin-prev-date= </strong>Starting date
         (day/month/year)</li>          (day/month/year)</li>
Line 569  age.<br> Line 586  age.<br>
 Some other people would like to use the cross-sectional  Some other people would like to use the cross-sectional
 prevalences (the &quot;Sullivan prevalences&quot;) observed at  prevalences (the &quot;Sullivan prevalences&quot;) observed at
 the initial age during a period of time <a href="#Computing">defined  the initial age during a period of time <a href="#Computing">defined
 just above</a>. </p>  just above</a>. <br>
   
 <ul>  <ul>
     <li><strong>popbased= 0 </strong>Health expectancies are      <li><strong>popbased= 0 </strong>Health expectancies are
Line 594  programme computes one forecasted preval Line 611  programme computes one forecasted preval
 starting date (1 january of 1989 in this example) to a final date  starting date (1 january of 1989 in this example) to a final date
 (1 january 1992). The statement mov_average allows to compute  (1 january 1992). The statement mov_average allows to compute
 smoothed forecasted prevalences with a five-age moving average  smoothed forecasted prevalences with a five-age moving average
 centered at the mid-age of the five-age period. </p>  centered at the mid-age of the five-age period. <br>
   
 <ul>  <ul>
     <li><strong>starting-proj-date</strong>= starting date      <li><strong>starting-proj-date</strong>= starting date
Line 618  including age and number of persons aliv Line 635  including age and number of persons aliv
 &#145;popfiledate&#146;, you can forecast the number of persons  &#145;popfiledate&#146;, you can forecast the number of persons
 in each state until date &#145;last-popfiledate&#146;. In this  in each state until date &#145;last-popfiledate&#146;. In this
 example, the popfile <a href="pyram.txt"><b>pyram.txt</b></a>  example, the popfile <a href="pyram.txt"><b>pyram.txt</b></a>
 includes real data which are the Japanese population in 1989.</p>  includes real data which are the Japanese population in 1989.<br>
   
 <ul type="disc">  <ul type="disc">
     <li class="MsoNormal"      <li class="MsoNormal"
Line 641  includes real data which are the Japanes Line 658  includes real data which are the Japanes
 <h2><a name="running"></a><font color="#00006A">Running Imach  <h2><a name="running"></a><font color="#00006A">Running Imach
 with this example</font></h2>  with this example</font></h2>
   
 <p>We assume that you entered your <a href="biaspar.imach">1st_example  We assume that you typed in your <a href="biaspar.imach">1st_example
 parameter file</a> as explained <a href="#biaspar">above</a>. To  parameter file</a> as explained <a href="#biaspar">above</a>.
 run the program you should click on the imach.exe icon and enter  <br>To run the program you should either:
   <ul> <li> click on the imach.exe icon and enter
 the name of the parameter file which is for example <a  the name of the parameter file which is for example <a
 href="C:\usr\imach\mle\biaspar.txt">C:\usr\imach\mle\biaspar.txt</a>  href="C:\usr\imach\mle\biaspar.imach">C:\usr\imach\mle\biaspar.imach</a>
 (you also can click on the biaspar.txt icon located in <br>  <li> You also can locate the biaspar.imach icon in
 <a href="C:\usr\imach\mle">C:\usr\imach\mle</a> and put it with  <a href="C:\usr\imach\mle">C:\usr\imach\mle</a> with your mouse and drag it with
 the mouse on the imach window).<br>  the mouse on the imach window).
 </p>  <li> With latest version (0.7 and higher) if you setup windows in order to
   understand ".imach" extension you can right click the
   biaspar.imach icon and either edit with notepad the parameter file or
   execute it with imach or whatever.
   </ul>  
   
 <p>The time to converge depends on the step unit that you used (1  The time to converge depends on the step unit that you used (1
 month is cpu consuming), on the number of cases, and on the  month is cpu consuming), on the number of cases, and on the
 number of variables.</p>  number of variables.
   
 <p>The program outputs many files. Most of them are files which  <br>The program outputs many files. Most of them are files which
 will be plotted for better understanding.</p>  will be plotted for better understanding.
   
 <hr>  <hr>
   
Line 668  with a grapher. We use Gnuplot which is Line 690  with a grapher. We use Gnuplot which is
 program copyrighted but freely distributed. A gnuplot reference  program copyrighted but freely distributed. A gnuplot reference
 manual is available <a href="http://www.gnuplot.info/">here</a>. <br>  manual is available <a href="http://www.gnuplot.info/">here</a>. <br>
 When the running is finished, the user should enter a caracter  When the running is finished, the user should enter a caracter
 for plotting and output editing. </p>  for plotting and output editing.
   
 <p>These caracters are:</p>  <br>These caracters are:<br>
   
 <ul>  <ul>
     <li>'c' to start again the program from the beginning.</li>      <li>'c' to start again the program from the beginning.</li>
Line 708  people aged 71 is 625+2=627. <br> Line 730  people aged 71 is 625+2=627. <br>
 </p>  </p>
   
 <h5><font color="#EC5E5E" size="3"><b>- Estimated parameters and  <h5><font color="#EC5E5E" size="3"><b>- Estimated parameters and
 covariance matrix</b></font><b>: </b><a href="rbiaspar.txt"><b>rbiaspar.txt</b></a></h5>  covariance matrix</b></font><b>: </b><a href="rbiaspar.txt"><b>rbiaspar.imach</b></a></h5>
   
 <p>This file contains all the maximisation results: </p>  <p>This file contains all the maximisation results: </p>
   
Line 1031  are in state 2. One year latter, 512892 Line 1053  are in state 2. One year latter, 512892
   
 <p>Since you know how to run the program, it is time to test it  <p>Since you know how to run the program, it is time to test it
 on your own computer. Try for example on a parameter file named <a  on your own computer. Try for example on a parameter file named <a
 href="..\mytry\imachpar.txt">imachpar.txt</a> which is a copy of <font  href="..\mytry\imachpar.imach">imachpar.imach</a> which is a copy of <font
 size="2" face="Courier New">mypar.txt</font> included in the  size="2" face="Courier New">mypar.imach</font> included in the
 subdirectory of imach, <font size="2" face="Courier New">mytry</font>.  subdirectory of imach, <font size="2" face="Courier New">mytry</font>.
 Edit it to change the name of the data file to <font size="2"  Edit it to change the name of the data file to <font size="2"
 face="Courier New">..\data\mydata.txt</font> if you don't want to  face="Courier New">..\data\mydata.txt</font> if you don't want to
Line 1044  question:'<strong>Enter the parameter fi Line 1066  question:'<strong>Enter the parameter fi
   
 <table border="1">  <table border="1">
     <tr>      <tr>
         <td width="100%"><strong>IMACH, Version 0.71</strong><p><strong>Enter          <td width="100%"><strong>IMACH, Version 0.8</strong><p><strong>Enter
         the parameter file name: ..\mytry\imachpar.txt</strong></p>          the parameter file name: ..\mytry\imachpar.imach</strong></p>
         </td>          </td>
     </tr>      </tr>
 </table>  </table>
Line 1063  href="imachrun.LOG">this Log file</a> Line 1085  href="imachrun.LOG">this Log file</a>
 #  #
   
 title=MLE datafile=..\data\mydata.txt lastobs=3000 firstpass=1 lastpass=3  title=MLE datafile=..\data\mydata.txt lastobs=3000 firstpass=1 lastpass=3
 ftol=1.000000e-008 stepm=24 ncov=2 nlstate=2 ndeath=1 maxwav=4 mle=1 weight=0</pre>  ftol=1.000000e-008 stepm=24 ncovcol=2 nlstate=2 ndeath=1 maxwav=4 mle=1 weight=0</pre>
     </li>      </li>
     <li><pre>Total number of individuals= 2965, Agemin = 70.00, Agemax= 100.92      <li><pre>Total number of individuals= 2965, Agemin = 70.00, Agemax= 100.92
   
Line 1168  edit the master file mypar.htm. </font>< Line 1190  edit the master file mypar.htm. </font><
         - Observed prevalence in each state: <a          - Observed prevalence in each state: <a
         href="..\mytry\prmypar.txt">pmypar.txt</a> <br>          href="..\mytry\prmypar.txt">pmypar.txt</a> <br>
         - Estimated parameters and the covariance matrix: <a          - Estimated parameters and the covariance matrix: <a
         href="..\mytry\rmypar.txt">rmypar.txt</a> <br>          href="..\mytry\rmypar.txt">rmypar.imach</a> <br>
         - Stationary prevalence in each state: <a          - Stationary prevalence in each state: <a
         href="..\mytry\plrmypar.txt">plrmypar.txt</a> <br>          href="..\mytry\plrmypar.txt">plrmypar.txt</a> <br>
         - Transition probabilities: <a          - Transition probabilities: <a
Line 1191  edit the master file mypar.htm. </font>< Line 1213  edit the master file mypar.htm. </font><
         </li>          </li>
     <li><u>Graphs</u> <br>      <li><u>Graphs</u> <br>
         <br>          <br>
         -<a href="../mytry/pemypar1.gif">One-step transition          -<a href="../mytry/pemypar1.gif">One-step transition probabilities</a><br>
         probabilities</a><br>          -<a href="../mytry/pmypar11.gif">Convergence to the stationary prevalence</a><br>
         -<a href="../mytry/pmypar11.gif">Convergence to the          -<a href="..\mytry\vmypar11.gif">Observed and stationary prevalence in state (1) with the confident interval</a> <br>
         stationary prevalence</a><br>          -<a href="..\mytry\vmypar21.gif">Observed and stationary prevalence in state (2) with the confident interval</a> <br>
         -<a href="..\mytry\vmypar11.gif">Observed and stationary          -<a href="..\mytry\expmypar11.gif">Health life expectancies by age and initial health state (1)</a> <br>
         prevalence in state (1) with the confident interval</a> <br>          -<a href="..\mytry\expmypar21.gif">Health life expectancies by age and initial health state (2)</a> <br>
         -<a href="..\mytry\vmypar21.gif">Observed and stationary          -<a href="..\mytry\emypar1.gif">Total life expectancy by age and health expectancies in states (1) and (2).</a> </li>
         prevalence in state (2) with the confident interval</a> <br>  
         -<a href="..\mytry\expmypar11.gif">Health life  
         expectancies by age and initial health state (1)</a> <br>  
         -<a href="..\mytry\expmypar21.gif">Health life  
         expectancies by age and initial health state (2)</a> <br>  
         -<a href="..\mytry\emypar1.gif">Total life expectancy by  
         age and health expectancies in states (1) and (2).</a> </li>  
 </ul>  </ul>
   
 <p>This software have been partly granted by <a  <p>This software have been partly granted by <a
Line 1217  simple justification (name, email, insti Line 1232  simple justification (name, email, insti
 href="mailto:brouard@ined.fr">mailto:brouard@ined.fr</a> and <a  href="mailto:brouard@ined.fr">mailto:brouard@ined.fr</a> and <a
 href="mailto:lievre@ined.fr">mailto:lievre@ined.fr</a> .</p>  href="mailto:lievre@ined.fr">mailto:lievre@ined.fr</a> .</p>
   
 <p>Latest version (0.71a of March 2002) can be accessed at <a  <p>Latest version (0.8 of March 2002) can be accessed at <a
 href="http://euroreves.ined.fr/imach">http://euroreves.ined.fr/imach</a><br>  href="http://euroreves.ined.fr/imach">http://euroreves.ined.fr/imach</a><br>
 </p>  </p>
 </body>  </body>

Removed from v.1.9  
changed lines
  Added in v.1.12


FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>