<?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: How to only output influence diagnostics panel 1 when using proc logistic in Statistical Procedures</title>
    <link>https://communities.sas.com/t5/Statistical-Procedures/How-to-only-output-influence-diagnostics-panel-1-when-using-proc/m-p/756520#M36842</link>
    <description>This is extremely helpful. Thank you. MM</description>
    <pubDate>Sun, 25 Jul 2021 17:19:24 GMT</pubDate>
    <dc:creator>MaryA_Marion</dc:creator>
    <dc:date>2021-07-25T17:19:24Z</dc:date>
    <item>
      <title>How to only output influence diagnostics panel 1 when using proc logistic</title>
      <link>https://communities.sas.com/t5/Statistical-Procedures/How-to-only-output-influence-diagnostics-panel-1-when-using-proc/m-p/756445#M36835</link>
      <description>&lt;PRE&gt;SAS CODE (it runs ok except I have two panels of influence plots -I only want the first one)&lt;/PRE&gt;
&lt;PRE&gt;ods graphics on;&lt;BR /&gt;ods select ClassLevelInfo ConvergenceStatus EffectPlot GoodnessOfFit LackFitChiSq ParameterEstimates clparmPL OddsRatios OddsRatiosPL influencePlots;&lt;BR /&gt;proc logistic data=throat descending plot(only)=(influence effect(x=(D) sliceby=T)) alpha=.05;&lt;BR /&gt;class T / param=ref;&lt;BR /&gt;model y = D T/ scale=none aggregate lackfit clparm=PL expb influence;&lt;BR /&gt;run; quit;&lt;BR /&gt;&lt;BR /&gt;Thanks. MM&lt;/PRE&gt;</description>
      <pubDate>Sun, 25 Jul 2021 01:43:23 GMT</pubDate>
      <guid>https://communities.sas.com/t5/Statistical-Procedures/How-to-only-output-influence-diagnostics-panel-1-when-using-proc/m-p/756445#M36835</guid>
      <dc:creator>MaryA_Marion</dc:creator>
      <dc:date>2021-07-25T01:43:23Z</dc:date>
    </item>
    <item>
      <title>Re: How to only output influence diagnostics panel 1 when using proc logistic</title>
      <link>https://communities.sas.com/t5/Statistical-Procedures/How-to-only-output-influence-diagnostics-panel-1-when-using-proc/m-p/756466#M36837</link>
      <description>&lt;P&gt;Hello&amp;nbsp;&lt;a href="https://communities.sas.com/t5/user/viewprofilepage/user-id/16492"&gt;@MaryA_Marion&lt;/a&gt;,&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;As I've just learned from the documentation of the &lt;A href="https://documentation.sas.com/doc/en/pgmsascdc/9.4_3.5/odsug/p1b72ff70v3obrn16aanp1r9q2bu.htm" target="_blank" rel="noopener"&gt;ODS SELECT statement&lt;/A&gt;, you can specify quoted labels (known from output obtained with &lt;A href="https://documentation.sas.com/doc/en/pgmsascdc/9.4_3.5/odsug/p1fpt3uuow90o3n155hs7bp1mo7f.htm" target="_blank" rel="noopener"&gt;ODS TRACE ON&lt;/A&gt;) in requests of ODS output objects. In your example, specify "Panel 1" to restrict the influence plots to the first panel:&lt;/P&gt;
&lt;PRE&gt;&lt;FONT size="4"&gt;ods select ClassLevelInfo ... influencePlots&lt;FONT color="#3366FF"&gt;&lt;STRONG&gt;.'Panel 1'&lt;/STRONG&gt;&lt;/FONT&gt;;&lt;/FONT&gt;&lt;/PRE&gt;</description>
      <pubDate>Sun, 25 Jul 2021 10:12:29 GMT</pubDate>
      <guid>https://communities.sas.com/t5/Statistical-Procedures/How-to-only-output-influence-diagnostics-panel-1-when-using-proc/m-p/756466#M36837</guid>
      <dc:creator>FreelanceReinh</dc:creator>
      <dc:date>2021-07-25T10:12:29Z</dc:date>
    </item>
    <item>
      <title>Re: How to only output influence diagnostics panel 1 when using proc logistic</title>
      <link>https://communities.sas.com/t5/Statistical-Procedures/How-to-only-output-influence-diagnostics-panel-1-when-using-proc/m-p/756481#M36838</link>
      <description>&lt;P&gt;FreelanceReinhard gave the correct answer, but it is worth mentioning that you can also match PATTERNS of strings. Learn how to &lt;A href="https://blogs.sas.com/content/iml/2018/11/19/select-ods-tables-wildcards-regular-expressions-sas.html" target="_self"&gt;select ODS tables by using wildcards and regular expressions in SAS.&lt;/A&gt;&lt;/P&gt;</description>
      <pubDate>Sun, 25 Jul 2021 11:20:04 GMT</pubDate>
      <guid>https://communities.sas.com/t5/Statistical-Procedures/How-to-only-output-influence-diagnostics-panel-1-when-using-proc/m-p/756481#M36838</guid>
      <dc:creator>Rick_SAS</dc:creator>
      <dc:date>2021-07-25T11:20:04Z</dc:date>
    </item>
    <item>
      <title>Re: How to only output influence diagnostics panel 1 when using proc logistic</title>
      <link>https://communities.sas.com/t5/Statistical-Procedures/How-to-only-output-influence-diagnostics-panel-1-when-using-proc/m-p/756518#M36841</link>
      <description>This was extremely helpful. How can I create custom panels of 2-6 plots? Thanks. MM</description>
      <pubDate>Sun, 25 Jul 2021 17:18:06 GMT</pubDate>
      <guid>https://communities.sas.com/t5/Statistical-Procedures/How-to-only-output-influence-diagnostics-panel-1-when-using-proc/m-p/756518#M36841</guid>
      <dc:creator>MaryA_Marion</dc:creator>
      <dc:date>2021-07-25T17:18:06Z</dc:date>
    </item>
    <item>
      <title>Re: How to only output influence diagnostics panel 1 when using proc logistic</title>
      <link>https://communities.sas.com/t5/Statistical-Procedures/How-to-only-output-influence-diagnostics-panel-1-when-using-proc/m-p/756520#M36842</link>
      <description>This is extremely helpful. Thank you. MM</description>
      <pubDate>Sun, 25 Jul 2021 17:19:24 GMT</pubDate>
      <guid>https://communities.sas.com/t5/Statistical-Procedures/How-to-only-output-influence-diagnostics-panel-1-when-using-proc/m-p/756520#M36842</guid>
      <dc:creator>MaryA_Marion</dc:creator>
      <dc:date>2021-07-25T17:19:24Z</dc:date>
    </item>
    <item>
      <title>Re: How to only output influence diagnostics panel 1 when using proc logistic</title>
      <link>https://communities.sas.com/t5/Statistical-Procedures/How-to-only-output-influence-diagnostics-panel-1-when-using-proc/m-p/756537#M36843</link>
      <description>&lt;BLOCKQUOTE&gt;&lt;HR /&gt;&lt;a href="https://communities.sas.com/t5/user/viewprofilepage/user-id/16492"&gt;@MaryA_Marion&lt;/a&gt;&amp;nbsp;wrote:&lt;BR /&gt;This was extremely helpful. How can I create custom panels of 2-6 plots? Thanks. MM&lt;HR /&gt;&lt;/BLOCKQUOTE&gt;
&lt;P&gt;I have never done this, but I see three options:&lt;/P&gt;
&lt;UL&gt;
&lt;LI&gt;Locate the ODS template used by PROC LOGISTIC for these graphs and modify a copy of it so that it includes only the plots of interest (cf.&amp;nbsp;&lt;A href="https://documentation.sas.com/doc/en/pgmsascdc/9.4_3.5/statug/statug_templt_sect033.htm" target="_blank" rel="noopener"&gt;ODS Graphics Template Modification&lt;/A&gt;).&lt;/LI&gt;
&lt;LI&gt;Create one or more (ODS output) datasets from the statistics underlying the plots of interest and create the custom graph using &lt;A href="https://documentation.sas.com/doc/en/pgmsascdc/9.4_3.5/grstatproc/p1k87u73xirwdsn0ztn1eqchrxt4.htm" target="_blank" rel="noopener"&gt;PROC SGPANEL&lt;/A&gt; based on these datasets.&lt;/LI&gt;
&lt;LI&gt;If this is not a recurring task, create the graphs of the default panels separately (see the&amp;nbsp;&lt;A href="https://documentation.sas.com/doc/en/pgmsascdc/9.4_3.5/statug/statug_logistic_syntax01.htm#statug.logistic.logisticplots" target="_blank" rel="noopener"&gt;UNPACK option&lt;/A&gt;) and combine them as you like in a post-processing step using graphics software.&lt;/LI&gt;
&lt;/UL&gt;</description>
      <pubDate>Sun, 25 Jul 2021 21:36:00 GMT</pubDate>
      <guid>https://communities.sas.com/t5/Statistical-Procedures/How-to-only-output-influence-diagnostics-panel-1-when-using-proc/m-p/756537#M36843</guid>
      <dc:creator>FreelanceReinh</dc:creator>
      <dc:date>2021-07-25T21:36:00Z</dc:date>
    </item>
    <item>
      <title>Re: How to only output influence diagnostics panel 1 when using proc logistic</title>
      <link>https://communities.sas.com/t5/Statistical-Procedures/How-to-only-output-influence-diagnostics-panel-1-when-using-proc/m-p/758124#M36909</link>
      <description>Rick,&lt;BR /&gt;I have found ods exclude to be more reliable; I will carefully attempt the&lt;BR /&gt;ods include on smaller projects. Pattern matching looks powerful. Thanks. MM&lt;BR /&gt;</description>
      <pubDate>Thu, 29 Jul 2021 15:20:22 GMT</pubDate>
      <guid>https://communities.sas.com/t5/Statistical-Procedures/How-to-only-output-influence-diagnostics-panel-1-when-using-proc/m-p/758124#M36909</guid>
      <dc:creator>MaryA_Marion</dc:creator>
      <dc:date>2021-07-29T15:20:22Z</dc:date>
    </item>
  </channel>
</rss>

