Links not working

The links in the MCSIM page are not working.
Is there another way I can get the MCSim Sw.?
Thanks
Juan.

(no subject)

Is MCSim capable to do this?

Dear Fredric,

   This is a very simle question and I hope you can at least give me a
quick reply. 

   I know that MCSim is designed to deal with problems where the mean
function is implicitly given through an ordinary differential equation
of t.  

   Now, my mean function has one more complexity on top of that. It is
an integral of f(t,x)*g(x). Where g is an explicit function and f is the
solution of some ordinary differential equation. Can MCSim deal this
kind of model?

   You can probably already guess that we are trying to integrate out x
which represents the individual parameters. Indeed this is the case. And
we have to do this because we don't get data of each individual, we are
only given their average data. 

Thank you very much in advance

Yanyuan

I can not compile it

Objet : Help-mcsim digest, Vol 1 #134 - 1 msg

Dear Yanyuan

You want to integrate over x and t, right ? Could cast your problem as a system of partial differential
equations in t
and x. If yes, then you could use a line method to solve the PDEs. MCSim can solve well behaved PDE systems
(see the version 5 beta pde exemples, in the tar.gz file attached). If you need more sophisticated
integration you
may want to try doing it throught a statistical model and MCMC simulations. You may need to code some bits by hand
though.

Frederic

---- original message -----
Date: Tue, 15 Oct 2002 12:54:17 -0400
From: Yanyuan Ma <yma <at> unity.ncsu.edu>
Organization: NC State University
To: fredomatic <at> free.fr, help-mcsim <at> gnu.org 
Subject: Is MCSim capable to do this?

Dear Fredric,

   This is a very simle question and I hope you can at least give me a
quick reply. 

   I know that MCSim is designed to deal with problems where the mean
function is implicitly given through an ordinary differential equation
of t.  

   Now, my mean function has one more complexity on top of that. It is
an integral of f(t,x)*g(x). Where g is an explicit function and f is the
solution of some ordinary differential equation. Can MCSim deal this
kind of model?

   You can probably already guess that we are trying to integrate out x
which represents the individual parameters. Indeed this is the case. And
we have to do this because we don't get data of each individual, we are
only given their average data. 

Thank you very much in advance

Yanyuan

Objet : Help-mcsim digest, Vol 1 #135 - 2 msgs

Hi !

This is a classical problem with some compilers. 
Apparently the linker does not see modi.c or modi.o and modo.c or modo.o which
contain the needed routines.
You need to compile all the files in the mod directory and then link them all together.
I don't know how to do it with MS C++...

F. Bois

From: "Chen, Lijian" <chen.855 <at> osu.edu>
To: <help-mcsim <at> gnu.org>
Subject: I can not compile it
Date: Wed, 16 Oct 2002 04:26:30 -0400

hi

I can not link it using microsoft c++ 6.0.

the error information is listed below:

--------------------Configuration: mod - Win32 Debug--------------------
Linking...
mod.obj : error LNK2001: unresolved external symbol _WriteModel
mod.obj : error LNK2001: unresolved external symbol _ReadModel
Debug/mod.exe : fatal error LNK1120: 2 unresolved externals
Error executing link.exe.

mod.exe - 3 error(s), 0 warning(s)

could you help to figure it out?

sincerely yours

lijian chen

McSim query

Hi,

I'm trying to do some analysis with McSim 4.1 and I'd like to specify
priors in a heirarchical fashion exactly as the authors of the software
did in their 1996 paper - Bois, F. Y., Gelman, A., Jiang, J., Maszle, D.,
Zeise, L. and Alexeef, G. (1996). Population toxicokinetics of
tetrachloroethylene. Archives of Toxicology 70:347-355. also used in
Gelman, A., Bois, F. Y. and Jiang, J. (1996). Physiological
pharmacokinetic analysis using population modeling and informative prior
distributions. Journal of the American Statistical Association
91:1400-1412.

The problem I'm facing is that I see no way to easily incorporate the
Lognormal hierarchical prior (mu*, Sigma*) (where mu* and Sigma* are the
geometric mean and standard deviations respectively = exp(mu) and
exp(Sigma)) with further conditional distributions on mu ~ Normal (M,S)
and Sigma as inverse-gamma(a,b) (a, b being the shape and scale
parameters, respectively) in the McSim framework. 

I've tried a number of things including toying with levels, exponents,
outputs, scaling etc. and nothing seems to work.

What one desires, I presume, is a way to specify the following
hierarchical distributions in the simulation file (which the authors used
in both references above):

Distrib (Sigma_V, InvGamma, 2, 0.1823);
Distrib (Mean_V, Normal, 0.1, 1.2); # values are abitrary
Distrib (V, TruncLogNormal, exp(Mean_V), exp(Sigma_V), 1e-6,10);

But the above formulation isn't allowed by McSim (no exponentiation
alllowed in the Distrib specification).

Or an alternative way to get the same effect - is there something obvious
that I'm not seeing? Presumably, there is a way to do this, I would be
greatly appreciative if anyone would let me know how.

Thanks in advance,

Sincerely,

Suhrid 

GPSS

Objet : Help-mcsim digest, Vol 1 #139 - 1 msg

Hi,

If you want to do:

Distrib (Sigma_V, InvGamma, 2, 0.1823);
Distrib (Mean_V, Normal, 0.1, 1.2);  # values are abitrary
Distrib (V, TruncLogNormal, exp(Mean_V), exp(Sigma_V), 1e-6,10);

you have a problem with V, the way to do it is to define a variable Log_V and do:

in the model definition file, define V and compute it in the Scale section as :
V = exp(Log_V);

in the input file:
Distrib (Sigma_V, InvGamma, 2, 0.1823);
Distrib (Mean_V, Normal, 0.1, 1.2);  # values are abitrary
Distrib (Log_V, TruncNormal, Mean_V, Sigma_V, -14, 2.3);

This way, V will have the lognormal distribution you want.
Note that we used InvGamma as priors for variances, as usually made, rather than for SDs.
If you use a variance you would do:

Distrib (SigmaSquare_V, InvGamma, 2, 0.1823);
Distrib (Mean_V, Normal, 0.1, 1.2);  # values are abitrary
Distrib (Log_V, TruncNormal_v, Mean_V, SigmaSquare_V, -14, 2.3);

using the TruncNormal_v distribution specification.

I hope this helps.

Frederic Bois

>>> <help-mcsim-request <at> gnu.org> Vendredi 25 octobre 2002 11:42:37 >>>
Date: Fri, 25 Oct 2002 02:46:42 -0400 (EDT)
From: Suhrid Balakrishnan <suhrid <at> paul.rutgers.edu>
To: help-mcsim <at> gnu.org 
Subject: McSim query 

Hi,

I'm trying to do some analysis with McSim 4.1 and I'd like to specify
priors in a heirarchical fashion exactly as the authors of the software
did in their 1996 paper - Bois, F. Y., Gelman, A., Jiang, J., Maszle, D.,
Zeise, L. and Alexeef, G. (1996). Population toxicokinetics of
tetrachloroethylene. Archives of Toxicology 70:347-355. also used in
Gelman, A., Bois, F. Y. and Jiang, J. (1996). Physiological
pharmacokinetic analysis using population modeling and informative prior
distributions. Journal of the American Statistical Association
91:1400-1412.

The problem I'm facing is that I see no way to easily incorporate the
Lognormal hierarchical prior (mu*, Sigma*) (where mu* and Sigma* are the
geometric mean and standard deviations respectively = exp(mu) and
exp(Sigma)) with further conditional distributions on mu ~ Normal (M,S)
and Sigma as inverse-gamma(a,b) (a, b being the shape and scale
parameters, respectively) in the McSim framework. 

I've tried a number of things including toying with levels, exponents,
outputs, scaling etc. and nothing seems to work.

What one desires, I presume, is a way to specify the following
hierarchical distributions in the simulation file (which the authors used
in both references above):

Distrib (Sigma_V, InvGamma, 2, 0.1823);
Distrib (Mean_V, Normal, 0.1, 1.2); # values are abitrary
Distrib (V, TruncLogNormal, exp(Mean_V), exp(Sigma_V), 1e-6,10);

But the above formulation isn't allowed by McSim (no exponentiation
alllowed in the Distrib specification).

Or an alternative way to get the same effect - is there something obvious
that I'm not seeing? Presumably, there is a way to do this, I would be
greatly appreciative if anyone would let me know how.

Thanks in advance,

Sincerely,

Suhrid 

--__--__--

_______________________________________________
Help-mcsim mailing list
Help-mcsim <at> gnu.org 
http://mail.gnu.org/mailman/listinfo/help-mcsim 

End of Help-mcsim Digest

perc.mtc.in fails?

I'm trying out MCSim 4.2.0 and I'm getting an error from the perc.mtc.in 
example.  All of the other examples run without trouble.  Here's the output:
Testing NDoses with perc.ndoses.in ...
-PASSED-
Testing Monte Carlo with perc.mtc.in ...
make: *** [one] Error 1
Any ideas what is wrong?  I'm using GCC 3.2 under Solaris 8.

Rodney Sparapani              Medical College of Wisconsin
Sr. Biostatistician           Patient Care & Outcomes Research
rsparapa <at> mcw.edu              http://www.mcw.edu/pcor
Was 'Name That Tune' rigged?  WWLD -- What Would Lombardi Do