https://community.jmp.com/t5/Discussions/Valeur-en-dessous-du-seuil-de-d%C3%A9tection-et-analyse-statistique/m-p/765626#M94535 <P>Hi&nbsp;<a href="https://community.jmp.com/t5/user/viewprofilepage/user-id/57934">@CEB87</a>,</P> <P>&nbsp;</P> <P>Welcome in the Community !</P> <P>&nbsp;</P> <P>You can use&nbsp;<A href="https://www.jmp.com/support/help/en/18.0/index.shtml#page/jmp/detection-limits.shtml" target="_blank">Detection Limits</A>&nbsp;in your response column property to define a lower and/or upper threshold <SPAN>beyond which a response cannot be measured.</SPAN></P> <P><SPAN>When using <A href="https://www.jmp.com/support/help/en/18.0/index.shtml#page/jmp/generalized-regression-models.shtml#" target="_self">Generalized Regression</A>&nbsp;models (JMP Pro) in the Fit Model platform, this property (and corresponding values) will be used to create censored values when observation is oustside of these limits. You can watch the presentation&nbsp;<LI-MESSAGE title="Limits of Detection (LoD) - New in JMP Pro 16" uid="417757" url="https://community.jmp.com/t5/Learning-Center/Limits-of-Detection-LoD-New-in-JMP-Pro-16/m-p/417757#U417757" discussion_style_icon_css="lia-mention-container-editor-message lia-img-icon-tkb-thread lia-fa-icon lia-fa-tkb lia-fa-thread lia-fa"></LI-MESSAGE>&nbsp;to get a better understanding of the benefit to use detection limits in modeling.</SPAN></P> <P>&nbsp;</P> <P><SPAN>Hope this answer will help you,</SPAN></P> Thu, 13 Jun 2024 16:28:52 GMT Victor_G 2024-06-13T16:28:52Z https://community.jmp.com/t5/Discussions/Valeur-en-dessous-du-seuil-de-d%C3%A9tection-et-analyse-statistique/m-p/765472#M94519 <P>Bonjour,</P><P>Pour une étude, plusieurs valeurs (numériques continues) sont en dessous du seuil de détection.</P><P>Quelle est la méthode statistique recommandée pour exploiter ces données ?</P><P>Quelle application sur JMP ?</P><P>Merci beaucoup pour vos conseils.</P><P>CEB</P> Thu, 13 Jun 2024 14:31:31 GMT https://community.jmp.com/t5/Discussions/Valeur-en-dessous-du-seuil-de-d%C3%A9tection-et-analyse-statistique/m-p/765472#M94519 CEB87 2024-06-13T14:31:31Z https://community.jmp.com/t5/Discussions/Valeur-en-dessous-du-seuil-de-d%C3%A9tection-et-analyse-statistique/m-p/765626#M94535 <P>Hi&nbsp;<a href="https://community.jmp.com/t5/user/viewprofilepage/user-id/57934">@CEB87</a>,</P> <P>&nbsp;</P> <P>Welcome in the Community !</P> <P>&nbsp;</P> <P>You can use&nbsp;<A href="https://www.jmp.com/support/help/en/18.0/index.shtml#page/jmp/detection-limits.shtml" target="_blank">Detection Limits</A>&nbsp;in your response column property to define a lower and/or upper threshold <SPAN>beyond which a response cannot be measured.</SPAN></P> <P><SPAN>When using <A href="https://www.jmp.com/support/help/en/18.0/index.shtml#page/jmp/generalized-regression-models.shtml#" target="_self">Generalized Regression</A>&nbsp;models (JMP Pro) in the Fit Model platform, this property (and corresponding values) will be used to create censored values when observation is oustside of these limits. You can watch the presentation&nbsp;<LI-MESSAGE title="Limits of Detection (LoD) - New in JMP Pro 16" uid="417757" url="https://community.jmp.com/t5/Learning-Center/Limits-of-Detection-LoD-New-in-JMP-Pro-16/m-p/417757#U417757" discussion_style_icon_css="lia-mention-container-editor-message lia-img-icon-tkb-thread lia-fa-icon lia-fa-tkb lia-fa-thread lia-fa"></LI-MESSAGE>&nbsp;to get a better understanding of the benefit to use detection limits in modeling.</SPAN></P> <P>&nbsp;</P> <P><SPAN>Hope this answer will help you,</SPAN></P> Thu, 13 Jun 2024 16:28:52 GMT https://community.jmp.com/t5/Discussions/Valeur-en-dessous-du-seuil-de-d%C3%A9tection-et-analyse-statistique/m-p/765626#M94535 Victor_G 2024-06-13T16:28:52Z https://community.jmp.com/t5/Discussions/Valeur-en-dessous-du-seuil-de-d%C3%A9tection-et-analyse-statistique/m-p/765783#M94554 <P>Merci <a href="https://community.jmp.com/t5/user/viewprofilepage/user-id/11568">@Victor_G</a>&nbsp;&nbsp;</P><P>Cette fonctionnalité n'est pas disponible sur JMP 12. Une autre façon de faire?&nbsp;</P><P>Merci&nbsp;</P><P>CEB</P> Fri, 14 Jun 2024 07:43:30 GMT https://community.jmp.com/t5/Discussions/Valeur-en-dessous-du-seuil-de-d%C3%A9tection-et-analyse-statistique/m-p/765783#M94554 CEB87 2024-06-14T07:43:30Z https://community.jmp.com/t5/Discussions/Valeur-en-dessous-du-seuil-de-d%C3%A9tection-et-analyse-statistique/m-p/765836#M94560 <P>I'm not familiar with the options available in JMP12, but you could probably use <A href="https://en.wikipedia.org/wiki/Quantile_regression" target="_self">Quantile Regression</A> to deal with censored values in the Generalized Regression options.</P> <P>The idea is either to use a regression model that doesn't estimate the conditional mean of the response variable across factors values, as it will be biased towards censored values (unlike estimating conditional median in Quantile Regression), and/or lower the importance of the censored data points on the model fit (to avoid the leverage effects of these censored values points).</P> <P>&nbsp;</P> <P>Hope this answer will help you,</P> Fri, 14 Jun 2024 08:42:35 GMT https://community.jmp.com/t5/Discussions/Valeur-en-dessous-du-seuil-de-d%C3%A9tection-et-analyse-statistique/m-p/765836#M94560 Victor_G 2024-06-14T08:42:35Z