<?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 Proc mixed and integer overflow in Statistical Procedures</title>
    <link>https://communities.sas.com/t5/Statistical-Procedures/Proc-mixed-and-integer-overflow/m-p/316591#M16671</link>
    <description>&lt;P&gt;Hi there&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;I have found several posts on this subject but have not managed to solve my problem yet.&lt;/P&gt;&lt;P&gt;I am running a mixed model on a dataset with 30 subjects who have got an average of 4000 measurements each (The highest number of measurements per subject is 16000).&lt;/P&gt;&lt;P&gt;I have run the model using the RANDOM statement (with a random intercept for each subject) and it worked fine.&lt;/P&gt;&lt;P&gt;However, I would like to change the covariance structure to an autogressive one. For this reason I have been trying to use the REPEATED statement and I keep getting the following error&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;ERROR: Integer overflow on computing amount of memory required. A request to allocate 5952.94M bytes of memory can not be honored.&lt;BR /&gt;ERROR: The SAS System stopped processing this step because of insufficient memory.&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;I tried to make the model the simplest possible (without any fixed effect) and I have tried to change the DDFM option but it still doesn't work.&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;Does anyone know how to fix it?&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;Thanks a lot!!!&lt;/P&gt;</description>
    <pubDate>Mon, 05 Dec 2016 01:02:38 GMT</pubDate>
    <dc:creator>miminz85</dc:creator>
    <dc:date>2016-12-05T01:02:38Z</dc:date>
    <item>
      <title>Proc mixed and integer overflow</title>
      <link>https://communities.sas.com/t5/Statistical-Procedures/Proc-mixed-and-integer-overflow/m-p/316591#M16671</link>
      <description>&lt;P&gt;Hi there&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;I have found several posts on this subject but have not managed to solve my problem yet.&lt;/P&gt;&lt;P&gt;I am running a mixed model on a dataset with 30 subjects who have got an average of 4000 measurements each (The highest number of measurements per subject is 16000).&lt;/P&gt;&lt;P&gt;I have run the model using the RANDOM statement (with a random intercept for each subject) and it worked fine.&lt;/P&gt;&lt;P&gt;However, I would like to change the covariance structure to an autogressive one. For this reason I have been trying to use the REPEATED statement and I keep getting the following error&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;ERROR: Integer overflow on computing amount of memory required. A request to allocate 5952.94M bytes of memory can not be honored.&lt;BR /&gt;ERROR: The SAS System stopped processing this step because of insufficient memory.&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;I tried to make the model the simplest possible (without any fixed effect) and I have tried to change the DDFM option but it still doesn't work.&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;Does anyone know how to fix it?&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;Thanks a lot!!!&lt;/P&gt;</description>
      <pubDate>Mon, 05 Dec 2016 01:02:38 GMT</pubDate>
      <guid>https://communities.sas.com/t5/Statistical-Procedures/Proc-mixed-and-integer-overflow/m-p/316591#M16671</guid>
      <dc:creator>miminz85</dc:creator>
      <dc:date>2016-12-05T01:02:38Z</dc:date>
    </item>
    <item>
      <title>Re: Proc mixed and integer overflow</title>
      <link>https://communities.sas.com/t5/Statistical-Procedures/Proc-mixed-and-integer-overflow/m-p/316693#M16675</link>
      <description>&lt;P&gt;You could try&lt;A href="http://support.sas.com/documentation/cdl/en/statug/68162/HTML/default/viewer.htm#statug_hpmixed_toc.htm" target="_self"&gt; PROC HPMIXED&lt;/A&gt;, which uses sparse matrices to compute the model. See the paper &lt;A href="https://support.sas.com/resources/papers/proceedings09/256-2009.pdf" target="_self"&gt;"All the cows in Canada..." (Wang and Tobias, 2009)&lt;/A&gt;&lt;/P&gt;</description>
      <pubDate>Mon, 05 Dec 2016 13:29:45 GMT</pubDate>
      <guid>https://communities.sas.com/t5/Statistical-Procedures/Proc-mixed-and-integer-overflow/m-p/316693#M16675</guid>
      <dc:creator>Rick_SAS</dc:creator>
      <dc:date>2016-12-05T13:29:45Z</dc:date>
    </item>
    <item>
      <title>Re: Proc mixed and integer overflow</title>
      <link>https://communities.sas.com/t5/Statistical-Procedures/Proc-mixed-and-integer-overflow/m-p/316884#M16682</link>
      <description>&lt;P&gt;Hi Rick!&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;Thanks for this. I tried but I still get the following message :(:&lt;/P&gt;&lt;P&gt;ERROR: The HPMIXED procedure stopped because of the insufficient memory.&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;This is my code. I got rid of the fixed effects so that it would be the simplest possible.&lt;/P&gt;&lt;PRE&gt;proc hpmixed data=j; 
    class seconds;
    model logconcentration=; 
    repeated seconds/sub=worker_id type=AR(1); 
run; &lt;/PRE&gt;</description>
      <pubDate>Mon, 05 Dec 2016 23:31:30 GMT</pubDate>
      <guid>https://communities.sas.com/t5/Statistical-Procedures/Proc-mixed-and-integer-overflow/m-p/316884#M16682</guid>
      <dc:creator>miminz85</dc:creator>
      <dc:date>2016-12-05T23:31:30Z</dc:date>
    </item>
    <item>
      <title>Re: Proc mixed and integer overflow</title>
      <link>https://communities.sas.com/t5/Statistical-Procedures/Proc-mixed-and-integer-overflow/m-p/316998#M16690</link>
      <description>&lt;P&gt;I assume you are using&lt;A href="http://support.sas.com/documentation/cdl/en/hostwin/67962/HTML/default/viewer.htm#n0srij4mcdpzv2n1vtphltb00xjw.htm" target="_self"&gt; the MEMSIZE system option&lt;/A&gt; to make sure the SAS process has access to as much RAM as possible?&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;DIV id="wrapper" class="hfeed"&gt;
&lt;DIV id="main"&gt;
&lt;DIV id="container"&gt;
&lt;DIV id="content"&gt;
&lt;DIV id="post-14415" class="post-14415 post type-post status-publish format-standard hentry category-uncategorized tag-14-1 tag-r tag-sasprogramming"&gt;
&lt;DIV class="entry-content"&gt;
&lt;P&gt;You can run PROC OPTIONS to display the current value of the MEMSIZE option:&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;proc options option=MEMSIZE value;&lt;/P&gt;
&lt;P&gt;run;&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;The default value on Windows is only 2GB. You can use the MEMSIZE system option to permit SAS to allocate a greater amount of system memory. &lt;A href="http://blogs.sas.com/content/iml/2015/07/31/large-matrices.html" target="_self"&gt;Use this article to guide you in setting the MEMSIZE option to a larger value.&lt;/A&gt;&lt;/P&gt;
&lt;/DIV&gt;
&lt;/DIV&gt;
&lt;/DIV&gt;
&lt;/DIV&gt;
&lt;/DIV&gt;
&lt;/DIV&gt;</description>
      <pubDate>Tue, 06 Dec 2016 12:48:21 GMT</pubDate>
      <guid>https://communities.sas.com/t5/Statistical-Procedures/Proc-mixed-and-integer-overflow/m-p/316998#M16690</guid>
      <dc:creator>Rick_SAS</dc:creator>
      <dc:date>2016-12-06T12:48:21Z</dc:date>
    </item>
    <item>
      <title>Re: Proc mixed and integer overflow</title>
      <link>https://communities.sas.com/t5/Statistical-Procedures/Proc-mixed-and-integer-overflow/m-p/317144#M16701</link>
      <description>&lt;P&gt;Thanks Rick. I have just done it but my computer has got a 4GB RAM and it is not enough ...&lt;/P&gt;</description>
      <pubDate>Tue, 06 Dec 2016 21:33:17 GMT</pubDate>
      <guid>https://communities.sas.com/t5/Statistical-Procedures/Proc-mixed-and-integer-overflow/m-p/317144#M16701</guid>
      <dc:creator>miminz85</dc:creator>
      <dc:date>2016-12-06T21:33:17Z</dc:date>
    </item>
  </channel>
</rss>

