Return-Path: Received: from corot.bc.edu (corot.bc.edu [136.167.2.209]) by monet.bc.edu (8.8.7/8.8.7) with ESMTP id MAA343692 for ; Fri, 2 Apr 1999 12:17:21 -0500 From: maiser@efs.mq.edu.au Received: (from root@localhost) by corot.bc.edu (8.8.7/8.8.7) with X.500 id MAA35956 for baum@mail1.bc.edu; Fri, 2 Apr 1999 12:17:21 -0500 Received: from sunb.ocs.mq.edu.au (sunb.ocs.mq.edu.au [137.111.1.11]) by corot.bc.edu (8.8.7/8.8.7) with ESMTP id MAA118378 for ; Fri, 2 Apr 1999 12:17:19 -0500 Received: from efs1.efs.mq.edu.au (efs1.efs.mq.edu.au [137.111.64.8]) by sunb.ocs.mq.edu.au (8.9.2/8.9.2) with ESMTP id DAA26553 for ; Sat, 3 Apr 1999 03:17:08 +1000 (EST) Received: from EFS1/SpoolDir by efs1.efs.mq.edu.au (Mercury 1.40); 3 Apr 99 03:18:56 GMT+1000 Received: from SpoolDir by EFS1 (Mercury 1.40); 3 Apr 99 03:18:55 GMT+1000 To: baum@bc.edu Date: Sat, 3 Apr 99 3:18:55 GMT+1000 Subject: Re: Message-ID: <8253D5A0C0D@efs1.efs.mq.edu.au> From: Gonzalez.Steven@fin.gc.ca To: "RATS Discussion List" Subject: MSE in Neural networks Date: Wed, 31 Mar 1999 16:27:03 -0500 Errors-to: Reply-to: "RATS Discussion List" Sender: Maiser@efs1.efs.mq.edu.au X-listname: MIME-Version: 1.0 X-Mailer: Internet Mail Service (5.5.2448.0) (via Mercury MTS (Bindery) v1.40) Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: quoted-printable As you may know, version 4.30 added new commands to estimate neural networks. As part of the output of the NNLEARN command, RATS provides the mean = squared error (MSE) of the estimated network. However, the computed value is = not equal to the standard definition of MSE used in statistics (i.e. the = average of the squared errors across the sample). Unfortunately, the on-line = Help function does not describe the formula used to calculate the MSE given = by the NNLEARN command. I have no idea how it is computed. Does anyone know the formula used by the NNLEARN command to compute the = MSE? Thank you.=20 =20 Steven Gonzalez Department of Finance, Canada / Minist=E8re des finances du Canada Fiscal Policy Division / Division de la politique fiscale Tel: (613) 996-0332 Fax: (613) 992-5773 gonzalez.steven@fin.gc.ca ---------- End of message ---------- From: Joseph Malm /Svetlana Kutuzova-Malm To: "RATS Discussion List" Subject: generalized leontiff cost functions Date: Thu, 01 Apr 1999 02:24:16 -0700 Errors-to: Reply-to: "RATS Discussion List" Sender: Maiser@efs1.efs.mq.edu.au X-listname: X-Mailer: Mozilla 4.05 [en] (Win95; I) (via Mercury MTS (Bindery) v1.40) MIME-Version: 1.0 Content-Type: multipart/alternative; boundary="------------4C93FB966218F53A96CC3B35" --------------4C93FB966218F53A96CC3B35 Content-Type: text/plain; charset=koi8-r Content-Transfer-Encoding: 7bit Can anyone suggest how to set up the necessary equations to derive the cost minimizing input-output equations in a generalized leontief cost funtion. The funtional form is a s follows: C=Y * [ SUM SUM d ij(PiPj)1/2 where SUM is the usual sum operatore for i=1 to n and j = 1 to n The input output equations are aij = X i /Y = SUM dij (Pj/Pi)1/2 i = 1...n Thanks Joseph Malm jmalm@unm.edu --------------4C93FB966218F53A96CC3B35 Content-Type: text/html; charset=koi8-r Content-Transfer-Encoding: 7bit Can anyone suggest how to set up the necessary equations to derive the cost minimizing input-output equations in a generalized leontief cost funtion. The funtional form is a s follows:
 C=Y * [ SUM SUM d ij(PiPj)1/2
where SUM is the usual sum operatore  for i=1 to n and j = 1 to n
The input output equations  are
aij  = X i /Y = SUM dij (Pj/Pi)1/2    i = 1...n
Thanks Joseph Malm
jmalm@unm.edu --------------4C93FB966218F53A96CC3B35-- ---------- End of message ----------