Return to biaspar.imach CVS log

Up to [Local Repository] / imach096d / doc

CHANGE ncov to ncovcol
There was a confusion with older ncov parameter. In fact it was the
number of columns, between id and date of birth, which can be used for
covariates. In the program we use ncovmodel for the real number of
covariates. Version 0.8 !

    1: # $Id: biaspar.imach,v 1.4 2002/03/13 17:28:11 brouard Exp $ Imach version 0.8 2002, INED-EUROREVES 
    2: title=1st_example datafile=data1.txt lastobs=8600 firstpass=1 lastpass=4
    3: ftol=1.000000e-008 stepm=1 ncovcol=2 nlstate=2 ndeath=1 maxwav=4 mle=1 weight=0
    4: model=.
    5: # Parameters (nlstate+ndeath-1)*nlstate*ncovmodel a12*1 + b12 * age + ...
    6: 12 0. 0.
    7: 13 0. 0.
    8: 21 0. 0.
    9: 23 0. 0.
   10: # Scales (for hessian or gradient estimation)
   11: 12 0. 0. 
   12: 13 0. 0. 
   13: 21 0. 0. 
   14: 23 0. 0. 
   15: # covariance matrix 
   16: # 121 Var(a12) 
   17: # 122 Cov(b12,a12)  Var(b12) 
   18: #       ...
   19: # 232 Cov(b23,a12)  Cov(b23,b12) ... Var (b23)
   20: 121 0.
   21: 122 0. 0.
   22: 131 0. 0. 0. 
   23: 132 0. 0. 0. 0. 
   24: 211 0. 0. 0. 0. 0. 
   25: 212 0. 0. 0. 0. 0. 0. 
   26: 231 0. 0. 0. 0. 0. 0. 0. 
   27: 232 0. 0. 0. 0. 0. 0. 0. 0.
   28: # agemin agemax for life expectancy, bage fage (if mle==0 ie no data nor Max likelihood).
   29: agemin=70 agemax=95 bage=65 fage=95
   30: # Observed prevalence period
   31: begin-prev-date=1/1/1984 end-prev-date=1/6/1988
   32: # Health expectancies computed from stationary prevalence (pop_based=0) or population based (1)
   33: pop_based=0
   34: # Prevalence forecasting
   35: starting-proj-date=1/1/1989 final-proj-date=1/1/1990 mov_average=0
   36: # Population forecasting
   37: popforecast=1 popfile=pyram.txt popfiledate=1/1/1989 last-popfiledate=1/1/1992