<?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 TOST analysis help in Discussions</title>
    <link>https://community.jmp.com/t5/Discussions/TOST-analysis-help/m-p/879780#M104317</link>
    <description>&lt;P&gt;I am trying to do TOST analysis for different CQAs. I want to create forest plots, where I can have all items in one plot rather then individual one for all CQAs. I have attached examples of both combined one (from research paper) and the individual one I created in JMP. Please, see if anyone can help with this.&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;Thanks!&lt;/P&gt;</description>
    <pubDate>Fri, 13 Jun 2025 16:02:53 GMT</pubDate>
    <dc:creator>AutoIconsIguana</dc:creator>
    <dc:date>2025-06-13T16:02:53Z</dc:date>
    <item>
      <title>TOST analysis help</title>
      <link>https://community.jmp.com/t5/Discussions/TOST-analysis-help/m-p/879780#M104317</link>
      <description>&lt;P&gt;I am trying to do TOST analysis for different CQAs. I want to create forest plots, where I can have all items in one plot rather then individual one for all CQAs. I have attached examples of both combined one (from research paper) and the individual one I created in JMP. Please, see if anyone can help with this.&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;Thanks!&lt;/P&gt;</description>
      <pubDate>Fri, 13 Jun 2025 16:02:53 GMT</pubDate>
      <guid>https://community.jmp.com/t5/Discussions/TOST-analysis-help/m-p/879780#M104317</guid>
      <dc:creator>AutoIconsIguana</dc:creator>
      <dc:date>2025-06-13T16:02:53Z</dc:date>
    </item>
    <item>
      <title>Re: TOST analysis help</title>
      <link>https://community.jmp.com/t5/Discussions/TOST-analysis-help/m-p/880092#M104370</link>
      <description>&lt;P&gt;Hi&amp;nbsp;&lt;a href="https://community.jmp.com/t5/user/viewprofilepage/user-id/43821"&gt;@AutoIconsIguana&lt;/a&gt;&amp;nbsp;: The way you can do it is as follows:&lt;/P&gt;
&lt;P&gt;1. Your data should have three columns: Y, Group, and CQA&lt;/P&gt;
&lt;P&gt;2. Fit Y by X platform: Response = Y, Factor = Group, By = CQA&lt;/P&gt;
&lt;P&gt;3. Get your 90% confidence intervals as you have; but first, hold down the control key when choosing that option so the intervals are calculated for each CQA.&lt;/P&gt;
&lt;P&gt;4. Right mouse click on the confidence interval output for one of the CQAs and choose "Make Combined Data Table".&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;5. The data set from 4 above can be used with Graph builder to get the plot you want.&lt;/P&gt;
&lt;P&gt;6. Drag (together) the lower and upper bound to to the X axis.&lt;/P&gt;
&lt;P&gt;7. Choose Bar graph from the Bar icon at the top of the Graph Builder GUI.&lt;/P&gt;
&lt;P&gt;8. Then in the Bar Style dialog (under Bar on left hand side) choose "Interval".&lt;/P&gt;
&lt;P&gt;9. Then drag the mean difference to the X axis as well.&lt;/P&gt;
&lt;P&gt;10. Then drag CQA to the "Group" section (right Y axis).&lt;/P&gt;
&lt;P&gt;11. Then add reference lines to the X axis based on your equivalence limits.&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;You can also to this via similar steps if you have a separate Y column for each CQA. The difference is you'll put all the Ys in the "Response" section, and the "By" section will be empty. Then carry on as above from 3-11.&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;Then embellish as desired.&amp;nbsp;&lt;/P&gt;</description>
      <pubDate>Mon, 16 Jun 2025 17:03:50 GMT</pubDate>
      <guid>https://community.jmp.com/t5/Discussions/TOST-analysis-help/m-p/880092#M104370</guid>
      <dc:creator>MRB3855</dc:creator>
      <dc:date>2025-06-16T17:03:50Z</dc:date>
    </item>
  </channel>
</rss>

