<?xml version="1.0" encoding="utf-8"?>
<rss xmlns:atom="http://www.w3.org/2005/Atom" version="2.0"><channel><title>Making Connections - Latest Comments</title><link xmlns="http://www.w3.org/2005/Atom" rel="http://api.friendfeed.com/2008/03#sup" href="http://disqus.com/sup/all.sup#forumcomments-1071c749" type="application/json"/><link>http://makingconnections.disqus.com/</link><description>None</description><atom:link href="http://makingconnections.disqus.com/comments.rss" rel="self"></atom:link><language>en</language><lastBuildDate>Tue, 16 Apr 2013 10:47:33 -0000</lastBuildDate><item><title>Re: Private: Modeling Customers Switching Between Brands &amp;ndash; The General Case</title><link>http://blog.iseesystems.com/modeling-tips/array-methods-4/#comment-865185126</link><description>&lt;p&gt;Good question.  New people arrive through the gaining customers inflow.  To add 100 more for brand A at a certain time (let's use month 5 for the example), you would change that formula as follows:&lt;/p&gt;

&lt;p&gt;market_share[Products]*customer_influx + (Products = 1)*PULSE(100, 5, 10000)&lt;/p&gt;

&lt;p&gt;[For version 9, use (ARRAYIDX() = 1) instead of (Products = 1).]&lt;/p&gt;

&lt;p&gt;However, I do not think this is quite what you are looking for because the market shares/switching percentages are constant, so the model will still seek the distribution given in those switching constants.&lt;/p&gt;

&lt;p&gt;To make the model dynamically vary the brand switching based on some criteria, you have to turn the constants in the table into equations for your new formulation.  For example, you can use STEP to reduce A's switching out probability at a certain time, and/or adjust market share (second model).  Using the second model, you could adjust only the market share to show an increase in both new customers and switching customers choosing brand A (rather than using the PULSE above).  Just make sure to adjust your equations so that the sum of the market shares is always one.&lt;/p&gt;

&lt;p&gt;While stepping up the market share or pulsing in extra customers can be an interesting policy exercise or model sensitivity test, you normally would tie these probabilities and market shares to dynamically changing endogenous variables of the model, such as price, features, reputation, perception of value, etc.&lt;/p&gt;</description><dc:creator xmlns:dc="http://purl.org/dc/elements/1.1/">kchichakly</dc:creator><pubDate>Tue, 16 Apr 2013 10:47:33 -0000</pubDate></item><item><title>Re: Private: Modeling Customers Switching Between Brands &amp;ndash; The General Case</title><link>http://blog.iseesystems.com/modeling-tips/array-methods-4/#comment-861856566</link><description>&lt;p&gt;How do you change the matrix if there is category expansion. Eg, in time 0, there were 500 people in market and now 600. Especially if we know that new 100 people are buying brand A.&lt;/p&gt;</description><dc:creator xmlns:dc="http://purl.org/dc/elements/1.1/">Mam</dc:creator><pubDate>Sat, 13 Apr 2013 02:38:22 -0000</pubDate></item><item><title>Re: What is the difference between STELLA and iThink?</title><link>http://blog.iseesystems.com/stella-ithink/what-is-the-difference-between-stella-and-ithink/#comment-775318522</link><description>&lt;p&gt;Difference at initial configurations could be handled as some default profiles beside user defined ones. It seems there should be other reasons for releasing and maintaining two different versions of the same product. Working on concepts and outsourcing software production will improve the product since at 2013 it seems like 1995 soft-wares...&lt;/p&gt;</description><dc:creator xmlns:dc="http://purl.org/dc/elements/1.1/">Anonymous</dc:creator><pubDate>Tue, 22 Jan 2013 21:00:58 -0000</pubDate></item><item><title>Re: Private: Working with Array Equations in Version 10</title><link>http://blog.iseesystems.com/modeling-tips/working-with-array-equations-in-version-10/#comment-752342283</link><description>&lt;p&gt;I agree with showing actual example that can be downloaded&lt;/p&gt;</description><dc:creator xmlns:dc="http://purl.org/dc/elements/1.1/">Cam</dc:creator><pubDate>Mon, 31 Dec 2012 20:17:06 -0000</pubDate></item><item><title>Re: Private: Working with Array Equations in Version 10</title><link>http://blog.iseesystems.com/modeling-tips/working-with-array-equations-in-version-10/#comment-745976259</link><description>&lt;p&gt;This article seems very interesting, but I suggest it would be better to develop examples based on stock and flow diagrams which present real situations.&lt;/p&gt;

&lt;p&gt;Above all do more examples of using arrays in conveyor and queues.&lt;/p&gt;

&lt;p&gt;Anyway congratulations for having written this.&lt;/p&gt;

&lt;p&gt;Merry Christmas from Monterrey, Mexico.&lt;/p&gt;</description><dc:creator xmlns:dc="http://purl.org/dc/elements/1.1/">pedrodago</dc:creator><pubDate>Sun, 23 Dec 2012 01:12:53 -0000</pubDate></item><item><title>Re: Private: Working with Array Equations in Version 10</title><link>http://blog.iseesystems.com/modeling-tips/working-with-array-equations-in-version-10/#comment-745975306</link><description>&lt;p&gt;This article seems very interesting, but I suggest it would be better to develop examples based on stock and flow diagrams which present real situations.&lt;/p&gt;

&lt;p&gt;Above all do more examples of using arrays in conveyor and queues.&lt;/p&gt;

&lt;p&gt;Anyway congratulations for having written this.&lt;/p&gt;

&lt;p&gt;Merry Christmas from Monterrey, Mexico.&lt;/p&gt;

&lt;p&gt;Pedro Almaguer Prado pedrodago@gmail.com&lt;/p&gt;</description><dc:creator xmlns:dc="http://purl.org/dc/elements/1.1/">Pedro Dagoberto Almaguer Prado</dc:creator><pubDate>Sun, 23 Dec 2012 01:08:38 -0000</pubDate></item><item><title>Re: Tip: Setting up imports for 2D Graphical Functions</title><link>http://blog.iseesystems.com/modeling-tips/setting-up-imports-for-2d-graphical-functions/#comment-740303585</link><description>&lt;p&gt;If there are more than 2000 projects, project 1, project 2,..., project 2000. I want to use 1001, 1002,..., 3000 instead of project 1, project 2, .... Is there any method to import them from excel, or is there any function to set them in stella? Thank you.&lt;/p&gt;</description><dc:creator xmlns:dc="http://purl.org/dc/elements/1.1/">sigmund</dc:creator><pubDate>Mon, 17 Dec 2012 02:41:58 -0000</pubDate></item><item><title>Re: Matrix Arithmetic</title><link>http://blog.iseesystems.com/modeling-tips/matrix-arithmetic/#comment-739164960</link><description>&lt;p&gt;These files are all ITM files, i.e., created by iThink.  STELLA will open them if you choose "iThink doc" from the pop-up menu at the bottom of the Open File dialog.&lt;/p&gt;</description><dc:creator xmlns:dc="http://purl.org/dc/elements/1.1/">kchichakly</dc:creator><pubDate>Sun, 16 Dec 2012 13:59:26 -0000</pubDate></item><item><title>Re: Matrix Arithmetic</title><link>http://blog.iseesystems.com/modeling-tips/matrix-arithmetic/#comment-739162265</link><description>&lt;p&gt;This is trickier than the other way, but still not difficult.  Say d is the vector and I want to put it into the diagonal of square matrix a. In version 9.1.5 or earlier, make the a's equation:&lt;/p&gt;

&lt;p&gt;IF ARRAYIDX() = ARRAYIDX(2) THEN d[Dim3] ELSE 0&lt;/p&gt;

&lt;p&gt;In version 10, make a's equation:&lt;/p&gt;

&lt;p&gt;IF @1 = @2 THEN d[Dim3] ELSE 0&lt;/p&gt;</description><dc:creator xmlns:dc="http://purl.org/dc/elements/1.1/">kchichakly</dc:creator><pubDate>Sun, 16 Dec 2012 13:56:52 -0000</pubDate></item><item><title>Re: Matrix Arithmetic</title><link>http://blog.iseesystems.com/modeling-tips/matrix-arithmetic/#comment-732915848</link><description>&lt;p&gt;How I convert a vector to a diagonal  matrix ?&lt;br&gt;&lt;/p&gt;</description><dc:creator xmlns:dc="http://purl.org/dc/elements/1.1/">Noé Aron fuentes</dc:creator><pubDate>Mon, 10 Dec 2012 23:38:11 -0000</pubDate></item><item><title>Re: Private: What are &amp;ldquo;Mental Models&amp;rdquo;?</title><link>http://blog.iseesystems.com/systems-thinking/what-are-mental-models/#comment-725404074</link><description>&lt;p&gt;not bad at all&lt;/p&gt;</description><dc:creator xmlns:dc="http://purl.org/dc/elements/1.1/">Camilia Moussawi Khanafer</dc:creator><pubDate>Sun, 02 Dec 2012 09:48:14 -0000</pubDate></item><item><title>Re: Private: Modeling Customers Switching Between Brands &amp;ndash; The General Case</title><link>http://blog.iseesystems.com/modeling-tips/array-methods-4/#comment-719564063</link><description>&lt;p&gt;This shows a way to model the effect of customers changing brands, presumably through consumer preferences and competition.  It is explicitly looking at number of customers, not how much each customer is spending.  As such, contraction in spending is outside the bounds of this model.  However, once you know how many customers you have, you can multiply that by the average spend per customer per month to get your monthly revenue.  In a contraction, the average spend per customer would drop based on some function you provide (using the STEP or RAMP functions or your own graphical function).  You may also lose customers in a contraction, which you would implement by increasing the loss rate in the model above.  It is likely during a contraction that you would also have a reduction in the customer influx.&lt;/p&gt;</description><dc:creator xmlns:dc="http://purl.org/dc/elements/1.1/">kchichakly</dc:creator><pubDate>Mon, 26 Nov 2012 14:00:38 -0000</pubDate></item><item><title>Re: Private: Steady-State Initialization of Conveyors</title><link>http://blog.iseesystems.com/modeling-tips/steady-state-init-of-conveyors/#comment-714700001</link><description>&lt;p&gt;why it can only be used one leakage for conveyor?, isn't it probable for a conveyor to have more than one?&lt;/p&gt;</description><dc:creator xmlns:dc="http://purl.org/dc/elements/1.1/">valentina</dc:creator><pubDate>Tue, 20 Nov 2012 03:43:50 -0000</pubDate></item><item><title>Re: Private: Integration Methods and DT</title><link>http://blog.iseesystems.com/modeling-tips/integration-methods-and-dt/#comment-711454627</link><description>&lt;p&gt;DT, as we use it in our models, is short for delta time, i.e., the difference between two time values.  It is NOT the dt from calculus (as pointed out above).  The difference between two time values has the same units as the time values being subtracted, i.e., time.  DT has the same units as the unit of time you set in the run specs.&lt;/p&gt;</description><dc:creator xmlns:dc="http://purl.org/dc/elements/1.1/">kchichakly</dc:creator><pubDate>Thu, 15 Nov 2012 22:49:50 -0000</pubDate></item><item><title>Re: Tip: Setting up imports for 2D Graphical Functions</title><link>http://blog.iseesystems.com/modeling-tips/setting-up-imports-for-2d-graphical-functions/#comment-654912672</link><description>&lt;p&gt;If i have a model that i want to run repetitively (like a 100 times) with a different set of random numbers, how can this be done? I was thinking of having a counter for the repetition i am in, I then I can look in the 10th or 12th coloumn for my set of random numbers. Really do not want to hard code this... Thanks so much for your help.&lt;/p&gt;</description><dc:creator xmlns:dc="http://purl.org/dc/elements/1.1/">robert</dc:creator><pubDate>Tue, 18 Sep 2012 17:30:50 -0000</pubDate></item><item><title>Re: Using PEST to Calibrate Models</title><link>http://blog.iseesystems.com/modeling-tips/calibrate-models-pest/#comment-615517435</link><description>&lt;p&gt;@kchichakly  I found the main issue was windows 2007 ; i am working in it. In PEST manual also suggest the same. Sometime batch files works well alone in dos mode, mosttimes is not and doesnt shows the errors. Rarely it works in pst files, but it couldnt open the template and instruction files (its a error). I dont know hw to fix this bug!?!?!??! do u have any suggestion?&lt;/p&gt;</description><dc:creator xmlns:dc="http://purl.org/dc/elements/1.1/">Dinmech</dc:creator><pubDate>Fri, 10 Aug 2012 08:18:28 -0000</pubDate></item><item><title>Re: Using PEST to Calibrate Models</title><link>http://blog.iseesystems.com/modeling-tips/calibrate-models-pest/#comment-615358830</link><description>&lt;p&gt;Hi kchichakly, Thanks for your comments. I solved this problem. But new problem arised, if i run batch file (test.bat) alone, it updates the model output files. when i am using pest filename for running the model, it shows the error "Unexpected end to model output file OBSPOINTS.OUT.&lt;br&gt;Instruction line follows -&lt;br&gt;"l3 @TEMP@" &lt;br&gt;After this error-All the model ouput files has been erased. my email id is dinkuleuven@gmail .com. u can email if possible, so i can send my files to check.&lt;/p&gt;

&lt;p&gt;Thanks&lt;/p&gt;

&lt;p&gt;Regards&lt;/p&gt;

&lt;p&gt;Dinesh&lt;br&gt;&lt;/p&gt;</description><dc:creator xmlns:dc="http://purl.org/dc/elements/1.1/">Dinmech</dc:creator><pubDate>Fri, 10 Aug 2012 04:04:32 -0000</pubDate></item><item><title>Re: Using PEST to Calibrate Models</title><link>http://blog.iseesystems.com/modeling-tips/calibrate-models-pest/#comment-614586917</link><description>&lt;p&gt;Hi Dinmech, this tells you there is an error in your PST file.  If you look at the sample, you will notice that there is a "* model command line" section near the end that needs a command line after it (I invoke a batch file in the example).   PESTGEN will create this file for you and then you should just have to make minor edits.  Do not accidentally delete things or change the spacing.  It is very finicky.  Please refer to the PEST manual if you cannot follow the PST file format.&lt;/p&gt;</description><dc:creator xmlns:dc="http://purl.org/dc/elements/1.1/">kchichakly</dc:creator><pubDate>Thu, 09 Aug 2012 12:20:04 -0000</pubDate></item><item><title>Re: Using PEST to Calibrate Models</title><link>http://blog.iseesystems.com/modeling-tips/calibrate-models-pest/#comment-614359030</link><description>&lt;p&gt;VS2DHP.PST should read Derivatives command line or model command line - error message....wht it mean??/&lt;/p&gt;</description><dc:creator xmlns:dc="http://purl.org/dc/elements/1.1/">Dinmech</dc:creator><pubDate>Thu, 09 Aug 2012 06:28:12 -0000</pubDate></item><item><title>Re: Cleaner Vehicles through Fees &amp;amp; Rebates</title><link>http://blog.iseesystems.com/education/feebates/#comment-613548568</link><description>&lt;p&gt;It charges in approximately six hours on a 240V/40A charger. .... a $2500 rebate through the Clean Vehicle Rebate Program in California and ...&lt;br&gt; &lt;/p&gt;</description><dc:creator xmlns:dc="http://purl.org/dc/elements/1.1/">Søgemaskineoptimering</dc:creator><pubDate>Wed, 08 Aug 2012 12:29:07 -0000</pubDate></item><item><title>Re: Published Papers that Feature Models</title><link>http://blog.iseesystems.com/stories-from-the-field/published-papers/#comment-554724299</link><description>&lt;p&gt;In the same way can someone help me with developing graph, as the attached image. Any help would be greatly appreciated.&lt;/p&gt;

&lt;p&gt;Looking forward for the help.&lt;/p&gt;

&lt;p&gt;Thank you.&lt;/p&gt;</description><dc:creator xmlns:dc="http://purl.org/dc/elements/1.1/">Patrickhenry</dc:creator><pubDate>Mon, 11 Jun 2012 17:43:10 -0000</pubDate></item><item><title>Re: Published Papers that Feature Models</title><link>http://blog.iseesystems.com/stories-from-the-field/published-papers/#comment-554714693</link><description>&lt;p&gt; patrick&lt;/p&gt;</description><dc:creator xmlns:dc="http://purl.org/dc/elements/1.1/">Patrick</dc:creator><pubDate>Mon, 11 Jun 2012 17:31:02 -0000</pubDate></item><item><title>Re: Private: Converting a Sector-based Model to Modules</title><link>http://blog.iseesystems.com/modeling-tips/converting-a-sector-based-model-to-modules/#comment-549957878</link><description>&lt;p&gt;After ghosting and entity within one module close the module, open the next module and drop the ghosted entity. Both modules do not need to be open at the same time. Please e-mail support@iseesystems.com if you have questions.&lt;/p&gt;</description><dc:creator xmlns:dc="http://purl.org/dc/elements/1.1/">Sdavie</dc:creator><pubDate>Thu, 07 Jun 2012 12:04:42 -0000</pubDate></item><item><title>Re: Private: Converting a Sector-based Model to Modules</title><link>http://blog.iseesystems.com/modeling-tips/converting-a-sector-based-model-to-modules/#comment-549155400</link><description>&lt;p&gt;Does this method work for 9.1.4 or has been written for some earlier version? I cannot open one module if the other is open to paste a ghost, even when I go up one level.&lt;/p&gt;</description><dc:creator xmlns:dc="http://purl.org/dc/elements/1.1/">Sikander</dc:creator><pubDate>Wed, 06 Jun 2012 17:07:34 -0000</pubDate></item><item><title>Re: Private: Steady-State Initialization of Conveyors</title><link>http://blog.iseesystems.com/modeling-tips/steady-state-init-of-conveyors/#comment-532473965</link><description>&lt;p&gt;We will reply to this request in e-mail.&lt;br&gt;&lt;/p&gt;</description><dc:creator xmlns:dc="http://purl.org/dc/elements/1.1/">Sdavie</dc:creator><pubDate>Fri, 18 May 2012 17:25:50 -0000</pubDate></item></channel></rss>