<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
<style type="text/css" style="display:none;"> P {margin-top:0;margin-bottom:0;} </style>
</head>
<body dir="ltr">
<div class="elementToProof" style="font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; color: rgb(0, 0, 0);">
<span style="font-size: 12pt;">Thank you, Prof. </span><span style="font-size: 11pt;">Michael for your response. </span></div>
<div class="elementToProof" style="font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 11pt; color: rgb(0, 0, 0);">
<br>
</div>
<div class="elementToProof" style="font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 11pt; color: rgb(0, 0, 0);">
Marimuthu</div>
<div id="appendonsend"></div>
<hr style="display:inline-block;width:98%" tabindex="-1">
<div id="divRplyFwdMsg" dir="ltr"><font face="Calibri, sans-serif" style="font-size:11pt" color="#000000"><b>From:</b> Michael Dewey <lists@dewey.myzen.co.uk><br>
<b>Sent:</b> Thursday, December 5, 2024 9:58 AM<br>
<b>To:</b> R Special Interest Group for Meta-Analysis <r-sig-meta-analysis@r-project.org><br>
<b>Cc:</b> Marimuthu S <sm@mcmaster.ca><br>
<b>Subject:</b> Re: [R-meta] Goodness of fit test for dose-response meta-analysis</font>
<div> </div>
</div>
<div class="BodyFragment"><font size="2"><span style="font-size:11pt;">
<div class="PlainText">[You don't often get email from lists@dewey.myzen.co.uk. Learn why this is important at
<a href="https://aka.ms/LearnAboutSenderIdentification">https://aka.ms/LearnAboutSenderIdentification</a> ]<br>
<br>
Caution: External email.<br>
<br>
<br>
Dear Marimuthu<br>
<br>
According to the paper cited in the help file for gof() the degrees of<br>
freedom only take into account n and p. No mention is made of the<br>
covariance matrix of the random effects. The paper is well worth a look<br>
as it is much more extensive than what you see after ?gof<br>
<br>
Michael<br>
<br>
On 04/12/2024 20:19, Marimuthu S via R-sig-meta-analysis wrote:<br>
> Dear all,<br>
><br>
> I am currently working on random effect one-stage dose-response<br>
> meta-analysis (DRMA), and I am trying to assess goodness of fit using<br>
> the R package "dosresmeta".<br>
><br>
> Here are the R code I used and the results:<br>
><br>
> *# Goodness fits statistics for Random effect quadratic polynomial model*<br>
> library(dosresmeta)<br>
> data(alcohol_cvd)<br>
><br>
> lin.R <- dosresmeta(formula = logrr ~ dose+I(dose^2), type = type, id =<br>
> id, se = se, cases = cases, n = n,proc = "1stage", data = alcohol_cvd,<br>
> method="reml", control = list(maxiter =1000))<br>
><br>
> >*gof(lin.R, fixed =FALSE)* Goodness-of-fit statistics: Deviance test:<br>
> D = 19.920 (df = 17), p-value = 0.278 <br>
> *# Goodness fits statistics for fixed effect quadratic polynomial model*<br>
> lin.F <- dosresmeta(formula = logrr ~ dose+I(dose^2), type = type, id =<br>
> id, se = se, cases = cases, n = n,proc = "1stage", data = alcohol_cvd,<br>
> method="fixed")<br>
> >*gof(lin.F)* Goodness-of-fit statistics: Deviance test: D = 40.992 (df<br>
> = 17), p-value = 0.001<br>
> The deviances are different for fixed vs. random but the degrees of<br>
> freedom are identical. Since the random effect model includes the<br>
> between study variance-covariance components (which should be<br>
> estimated),, I expected the degrees of freedom for random effect to be<br>
> smaller.<br>
><br>
> I would appreciate if anyone could share their thoughts.<br>
><br>
> Warm Regards,<br>
><br>
> *Marimuthu S,*<br>
> Ph.D. Student (Biostatistics)<br>
><br>
><br>
><br>
> <<a href="http://www.avg.com/email-signature?utm_medium=email&utm_source=link&utm_campaign=sig-email&utm_content=emailclient">http://www.avg.com/email-signature?utm_medium=email&utm_source=link&utm_campaign=sig-email&utm_content=emailclient</a>> Virus-free.www.avg.com
<<a href="http://www.avg.com/email-signature?utm_medium=email&utm_source=link&utm_campaign=sig-email&utm_content=emailclient">http://www.avg.com/email-signature?utm_medium=email&utm_source=link&utm_campaign=sig-email&utm_content=emailclient</a>><br>
><br>
> <#DAB4FAD8-2DD7-40BB-A1B8-4E2AA1F9FDF2><br>
><br>
> _______________________________________________<br>
> R-sig-meta-analysis mailing list @ R-sig-meta-analysis@r-project.org<br>
> To manage your subscription to this mailing list, go to:<br>
> <a href="https://stat.ethz.ch/mailman/listinfo/r-sig-meta-analysis">https://stat.ethz.ch/mailman/listinfo/r-sig-meta-analysis</a><br>
<br>
--<br>
Michael<br>
</div>
</span></font></div>
</body>
</html>