Dear Ross,

A year ago I tried to reproduce this code and I got the same effect. I
stopped working on the code but maybe this is my opportunity for retaking
the project (time allowing). Meanwhile, I would be very very interested in
knowing about the results of your enquire and see the code you are using (I
program in Lisp-Stat but I guess I could read S)


At 16:45 22/11/2000 +0000, you wrote:
>
>I have tried to reproduce the example on page 176 of Schafer's book.
>I have used both Joe  Schafer's "norm" package and my own code that follows 
>the psuedocode given on page 168.
>
>The results are below. Both these agree but neither agree with Table 5.1 b
>which  quotes esimates that converge much faster than the former.
>
>I would be interested in hearing from anyone who has looked at this.
>
>Cheers
>
>Ross Darnell
>
>My version of the psuedocode (in R) gives
> 
>        t       mu_3    sigma_3         rho_13          rho_23 
>       -----------------------------------------------------------
>          0 200.000     50.0000         0.000000        0.000000 
>          1 214.571     45.8580         0.280948        0.411372 
>          2 219.173     43.8167         0.372608        0.609371 
>          3 220.892     43.4985         0.398496        0.691951 
>          4 221.618     43.6750         0.404261        0.723726 
>          5 221.946     43.8818         0.404878        0.735815 
>          6 222.100     44.0216         0.404501        0.740493 
>          7 222.172     44.1014         0.404109        0.742351 
>          8 222.206     44.1433         0.403854        0.743110 
>          9 222.223     44.1644         0.403711        0.743428 
>         10 222.230     44.1747         0.403636        0.743564 
>         11 222.234     44.1796         0.403598        0.743623 
>         12 222.236     44.1820         0.403580        0.743649 
>         13 222.236     44.1831         0.403571        0.743661 
>         14 222.237     44.1836         0.403566        0.743667 
>         15 222.237     44.1839         0.403564        0.743669 
>         16 222.237     44.1840         0.403563        0.743670 
>         17 222.237     44.1840         0.403563        0.743671 
>
>       -----------------------------------------------------------
>
>
>Schafers norm code gives this
>
>        t       mu_3    sigma_3         rho_13          rho_23 
>       -----------------------------------------------------------
>          0 200.000     50.0000         0.000000        0.000000 
>          1 214.571     45.8580         0.280948        0.411372 
>          2 219.173     43.8167         0.372608        0.609371 
>          3 220.892     43.4985         0.398496        0.691951 
>          4 221.618     43.6750         0.404261        0.723726 
>          5 221.946     43.8818         0.404878        0.735815 
>          6 222.100     44.0216         0.404501        0.740493 
>          7 222.172     44.1014         0.404109        0.742351 
>          8 222.206     44.1433         0.403854        0.743110 
>          9 222.223     44.1644         0.403711        0.743428 
>         10 222.230     44.1747         0.403636        0.743564 
>         11 222.234     44.1796         0.403598        0.743623 
>         12 222.236     44.1820         0.403580        0.743649 
>         13 222.236     44.1831         0.403571        0.743661 
>         14 222.236     44.1831         0.403571        0.743661 
>         15 222.236     44.1831         0.403571        0.743661 
>         16 222.236     44.1831         0.403571        0.743661 
>
>       ------------------------------------------------------------
>
>
>
==========================================================
Dr. Pedro M. Valero-Mora.                       WWW: http://www.uv.es/~valerop
Director M?todos de Investigaci?n               Phone: +34 96 3393880
Universitat de Val?ncia
INTRAS-Instituto de Tr?fico y Seg. Vial.
INTRAS-Institut of Traffic and Road Safety.
C/ Hugo de Moncada 4. Entresuelo.
Valencia, 46010, Espa?a (Spain).
==========================================================

Reply via email to