<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:taxo="http://purl.org/rss/1.0/modules/taxonomy/" version="2.0">
  <channel>
    <title>topic Re: Understanding the Alias-Optimal design algorithm, optimization of a fixed block effect in Discussions</title>
    <link>https://community.jmp.com/t5/Discussions/Understanding-the-Alias-Optimal-design-algorithm-optimization-of/m-p/424325#M67347</link>
    <description>&lt;P&gt;The algorithm is the same: coordinate exchange. The criterion is different. It is the minimum of the trace of A'A, where A is the alias matrix as described in &lt;A href="https://www.jmp.com/support/help/en/16.1/#page/jmp/optimality-criteria.shtml" target="_self"&gt;the Help&lt;/A&gt;.&lt;/P&gt;</description>
    <pubDate>Thu, 07 Oct 2021 13:32:57 GMT</pubDate>
    <dc:creator>Mark_Bailey</dc:creator>
    <dc:date>2021-10-07T13:32:57Z</dc:date>
    <item>
      <title>Understanding the Alias-Optimal design algorithm, optimization of a fixed block effect</title>
      <link>https://community.jmp.com/t5/Discussions/Understanding-the-Alias-Optimal-design-algorithm-optimization-of/m-p/424171#M67338</link>
      <description>&lt;P&gt;I was wondering: when one adds a fixed block effect to the alias-optimal design, how is it optimized?&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;For instance, following the explications by Jones and Nachtsheim(2011): is it optimized in the first objective being D-optimality optimization for the model terms, or, is it optimized in the secondary objective, being optimizing the orthogonality between Alias term and the model terms?&lt;/P&gt;&lt;P&gt;.. or something else?&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;</description>
      <pubDate>Thu, 08 Jun 2023 21:06:14 GMT</pubDate>
      <guid>https://community.jmp.com/t5/Discussions/Understanding-the-Alias-Optimal-design-algorithm-optimization-of/m-p/424171#M67338</guid>
      <dc:creator>Not_A_Student</dc:creator>
      <dc:date>2023-06-08T21:06:14Z</dc:date>
    </item>
    <item>
      <title>Re: Understanding the Alias-Optimal design algorithm, optimization of a fixed block effect</title>
      <link>https://community.jmp.com/t5/Discussions/Understanding-the-Alias-Optimal-design-algorithm-optimization-of/m-p/424325#M67347</link>
      <description>&lt;P&gt;The algorithm is the same: coordinate exchange. The criterion is different. It is the minimum of the trace of A'A, where A is the alias matrix as described in &lt;A href="https://www.jmp.com/support/help/en/16.1/#page/jmp/optimality-criteria.shtml" target="_self"&gt;the Help&lt;/A&gt;.&lt;/P&gt;</description>
      <pubDate>Thu, 07 Oct 2021 13:32:57 GMT</pubDate>
      <guid>https://community.jmp.com/t5/Discussions/Understanding-the-Alias-Optimal-design-algorithm-optimization-of/m-p/424325#M67347</guid>
      <dc:creator>Mark_Bailey</dc:creator>
      <dc:date>2021-10-07T13:32:57Z</dc:date>
    </item>
    <item>
      <title>Re: Understanding the Alias-Optimal design algorithm, optimization of a fixed block effect</title>
      <link>https://community.jmp.com/t5/Discussions/Understanding-the-Alias-Optimal-design-algorithm-optimization-of/m-p/428925#M67839</link>
      <description>&lt;P&gt;Thank you Mark,&amp;nbsp;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;One point that remains confusing for me:&lt;/P&gt;&lt;P&gt;Is the Fixed Block effect placed in the Model (the X1) or in the&amp;nbsp;&lt;SPAN&gt;matrix of model terms for the alias effects the (X2)&lt;/SPAN&gt;?&lt;/P&gt;&lt;P&gt;See picture:&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;&lt;span class="lia-inline-image-display-wrapper lia-image-align-inline" image-alt="Not_A_Student_0-1634804616278.png" style="width: 767px;"&gt;&lt;img src="https://community.jmp.com/t5/image/serverpage/image-id/36882iDFE697903D3443D1/image-dimensions/767x593?v=v2" width="767" height="593" role="button" title="Not_A_Student_0-1634804616278.png" alt="Not_A_Student_0-1634804616278.png" /&gt;&lt;/span&gt;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;Reason for asking is that Following Jones and Nachtsheim (2011), i saw we minimize a mix of the trace of the Alias matrix and the D-efficiency with a weight factor to balance out.&amp;nbsp; More formally, we minimize the objective function:&lt;/P&gt;&lt;P&gt;&lt;span class="lia-inline-image-display-wrapper lia-image-align-inline" image-alt="Not_A_Student_2-1634805384992.png" style="width: 400px;"&gt;&lt;img src="https://community.jmp.com/t5/image/serverpage/image-id/36884iA62F04EA3F35A9CC/image-size/medium?v=v2&amp;amp;px=400" role="button" title="Not_A_Student_2-1634805384992.png" alt="Not_A_Student_2-1634805384992.png" /&gt;&lt;/span&gt;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;Where:&lt;/P&gt;&lt;P&gt;&lt;span class="lia-inline-image-display-wrapper lia-image-align-inline" image-alt="Not_A_Student_3-1634805406507.png" style="width: 400px;"&gt;&lt;img src="https://community.jmp.com/t5/image/serverpage/image-id/36885iB97FE45DC6808709/image-size/medium?v=v2&amp;amp;px=400" role="button" title="Not_A_Student_3-1634805406507.png" alt="Not_A_Student_3-1634805406507.png" /&gt;&lt;/span&gt;&lt;/P&gt;&lt;P&gt;&lt;span class="lia-inline-image-display-wrapper lia-image-align-inline" image-alt="Not_A_Student_4-1634805513522.png" style="width: 400px;"&gt;&lt;img src="https://community.jmp.com/t5/image/serverpage/image-id/36886iDBFAF31D5BAF0212/image-size/medium?v=v2&amp;amp;px=400" role="button" title="Not_A_Student_4-1634805513522.png" alt="Not_A_Student_4-1634805513522.png" /&gt;&lt;/span&gt;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;This let's me wonder:&amp;nbsp;&lt;/P&gt;&lt;P&gt;If the block effect becomes a model term of design matrix X1 i guess it would optimize&amp;nbsp; predictability (predictive variance) of the blocks as strongly as other model terms. If the block effect was in the model terms for matrix for the alias&amp;nbsp; X2 we would optimize it's orthogonality against the X1 terms but it's predictive variance would be greater and estimated block effect sizes would not necessarily be orthogonal against potentially aliased effects.&amp;nbsp;&amp;nbsp;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;Thank you for helping me understanding ;)&lt;/img&gt;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;</description>
      <pubDate>Thu, 21 Oct 2021 08:54:04 GMT</pubDate>
      <guid>https://community.jmp.com/t5/Discussions/Understanding-the-Alias-Optimal-design-algorithm-optimization-of/m-p/428925#M67839</guid>
      <dc:creator>Not_A_Student</dc:creator>
      <dc:date>2021-10-21T08:54:04Z</dc:date>
    </item>
    <item>
      <title>Re: Understanding the Alias-Optimal design algorithm, optimization of a fixed block effect</title>
      <link>https://community.jmp.com/t5/Discussions/Understanding-the-Alias-Optimal-design-algorithm-optimization-of/m-p/428981#M67845</link>
      <description>&lt;P&gt;The fixed effect of X5 (blocking factor) is in X1, not in X2.&lt;/P&gt;</description>
      <pubDate>Thu, 21 Oct 2021 12:57:20 GMT</pubDate>
      <guid>https://community.jmp.com/t5/Discussions/Understanding-the-Alias-Optimal-design-algorithm-optimization-of/m-p/428981#M67845</guid>
      <dc:creator>Mark_Bailey</dc:creator>
      <dc:date>2021-10-21T12:57:20Z</dc:date>
    </item>
  </channel>
</rss>

