MathGroup Archive 2010

[Date Index] [Thread Index] [Author Index]

Search the Archive

Re: New to Mathematica

  • To: mathgroup at smc.vnet.net
  • Subject: [mg114173] Re: New to Mathematica
  • From: Eduardo Pollak <eduardo.pollak at me.com>
  • Date: Fri, 26 Nov 2010 05:27:31 -0500 (EST)

Thank you,
I Changed the line and  the system went forever until overflowed with a ver=
y small sample.
I am using Mathematica 7 Home edition on an Apple MacbookPro with 4GB Ram.=

I guess the NMinimize is not the solution.  
Thank you.
Eduardo
P.D I will try with FindMinimum

Begin forwarded message:

> From: Daniel Lichtblau <danl at wolfram.com>
> Date: November 25, 2010 1:41:03 PM GMT-03:00
> To: Eduardo Pollak <eduardo.pollak at me.com>
> Subject: Re: [mg114157] New to Mathematica
>
>
>
> ----- Original Message -----
>> From: "Eduardo Pollak" <eduardo.pollak at me.com>
>> To: mathgroup at smc.vnet.net
>> Sent: Thursday, November 25, 2010 4:59:36 AM
>> Subject: [mg114157] New to Mathematica
>> I am minimizing a Likelihood Function and the evaluation at a certain
>> point gives me the following message:
>>
>> Please see link to notebook Below
>> https://files.me.com/eduardo.pollak/zm4e9f
>>
>> If I evaluate the MSMVeros function at the point indeterminate it is
>> not indeterminate and it should not be indeterminate. Also all
>> functions
>> called are determinate.
>>
>> Do you have a hint of what is happening? Appreciate any
>> suggestions...
>>
>> Thank you
>>
>> Eduardo
>
> That symbolic expression really does evaluate to Indeterminate.
>
> In[15]:== MSMVeros[k, b, m0, g, sigma, datos, A]
> Out[15]== Indeterminate
>
> You can avoid this by defining it to only evaluate as a "black box", that=
 is, when the optimization variables are explicitly numeric.
>
> MSMVeros[kbar_, b_?NumberQ, m0_?NumberQ,
> gkbar_?NumberQ, sigma_, datos_, atempl_]
>
> Daniel Lichtblau
> Wolfram Research




 Nov 25, 2010, at 10:06 AM, Ingolf Dahl wrote:

> I hope that the answer below is of some help to you, you are not the firs=
t to ask about this error:
>
> If I change your line
>
> MSMVeros[kbar_, b_, m0_, gkbar_, sigma_, datos_, atempl_] :==
>
> to
>
> MSMVeros[kbar_, b_?NumericQ, m0_?NumericQ,
> gkbar_?NumericQ, sigma_, datos_, atempl_]:==
>
> the behavior changes, and I get another warning
>
> NMinimize:: nrnum: The function value 51783.4 - 115.456 I is not a real n=
umber at {65.5947, 1.12823, 1.68306} >>
>
> But I also a result after a long computation:
>
> {42279.6,{b->57.0693,g->0.935193,m0->1.97611}}
>
> Best regards
>
> Ingolf Dahl
> ingolf.dahl at telia.com
>
>
>
>
> -----Ursprungligt meddelande-----
> Fr=E5n: Eduardo Pollak [mailto:eduardo.pollak at me.com]
> Skickat: den 25 november 2010 12:00
> Till: mathgroup at smc.vnet.net
> =C4mne: [mg114157] New to Mathematica
>
> I am minimizing a Likelihood Function and the evaluation at a certain
> point gives me the following message:
>
> Please see link to notebook Below
> https://files.me.com/eduardo.pollak/zm4e9f
>
> If I evaluate the MSMVeros function at the point indeterminate it is
> not indeterminate and it should not be indeterminate. Also all functions=

> called are determinate.
>
> Do you have a hint of what is happening? Appreciate any
> suggestions...
>
> Thank you
>
> Eduardo
>
>
> "La informaci==F3n contenida en esta transmisi==F3n y sus documentos
> adjuntos, es confidencial y no puede ser usada o difundida por personas=

> distintas a su(s) destinatario(s). El uso no autorizado de la
> informaci==F3n contenida en esta transmisi==F3n puede ser sancionado
> criminalmente de conformidad con la ley chilena. Si ha recibido esta
> transmisi==F3n por error, por favor destr==FAyala y notifique al
> remitente. Gracias."
> "This e-mail and any attachments are confidential and may also be
> privileged. If you are  not the intended recipient and have received
> this message in error, please immediately notify the sender (by e-mail)=

> and delete this e-mail and any attachments from your system. You are
> hereby notified that any use, distribution, reproduction or disclosure
> by any person other than the intended recipient is strictly prohibited.=

> Thank you==94
>
>
>








"La informaci=F3n contenida en esta transmisi=F3n y sus documentos adjuntos=
, es confidencial y no puede ser usada o difundida por personas distintas a=
 su(s) destinatario(s). El uso no autorizado de la informaci=F3n contenida =
en esta transmisi=F3n puede ser sancionado criminalmente de conformidad con=
 la ley chilena. Si ha recibido esta transmisi=F3n por error, por favor des=
tr=FAyala y notifique al remitente. Gracias."
"This e-mail and any attachments are confidential and may also be privilege=
d. If you are  not the intended recipient and have received this message in=
 error, please immediately notify the sender (by e-mail) and delete this e-=
mail and any attachments from your system. You are hereby notified that any=
 use, distribution, reproduction or disclosure by any person other than the=
 intended recipient is strictly prohibited. Thank you=94



  • Prev by Date: Re: /. Hold -> Identity (Was: One more rules + ev<>rol problem)
  • Next by Date: Re: Efficient search for bounding list elements
  • Previous by thread: Re: New to Mathematica
  • Next by thread: disappointing CUDA speed