<div dir="ltr">Hi everyone, <div><br></div><div>I'm a bit stuck and would really appreciate any help on my issue. </div><div><br></div><div>I'm doing a meta analysis (using R). There are several instances where authors reported multiple effect sizes (e.g., reported effect sizes for different timepoints) that I need to combine. I've tried to aggregate my multiple effect sizes using both the metafor package and the formula in Borenstein's manual (chapter 24 - using the mean effect size weighted according to the sample size and the formula attached to this email to calculate the variance). While variances using these two techniques are quite similar, the computed effect sizes are very different. </div><div><br></div><div><u><i>My questions are: </i></u></div><div><ul><li>Why/how does yi (combined effect size) change quite a lot based on the value of rho when using the metafor package?</li><li>Are the yi's that we get when using the metafor package correct?</li><li>The combined effect sizes using these methods are quite different from using the mean effect size. Is it correct to use the Metafor package? </li></ul><div>This is the example I've been working on </div><div><br></div><div><table border="0" cellpadding="0" cellspacing="0" width="318" style="border-collapse:collapse;width:238pt">
<colgroup><col width="105" style="width:79pt">
<col width="71" span="3" style="width:53pt">
</colgroup><tbody><tr height="20" style="height:15pt">
<td height="20" width="105" style="height:15pt;width:79pt;padding-top:1px;padding-right:1px;padding-left:1px;color:black;font-size:11pt;font-family:Calibri,sans-serif;vertical-align:bottom;border:none;white-space:nowrap">Authors</td>
<td width="71" style="width:53pt;padding-top:1px;padding-right:1px;padding-left:1px;color:black;font-size:11pt;font-family:Calibri,sans-serif;vertical-align:bottom;border:none;white-space:nowrap">N</td>
<td width="71" style="width:53pt;padding-top:1px;padding-right:1px;padding-left:1px;color:black;font-size:11pt;font-family:Calibri,sans-serif;vertical-align:bottom;border:none;white-space:nowrap">Time</td>
<td width="71" style="width:53pt;padding-top:1px;padding-right:1px;padding-left:1px;color:black;font-size:11pt;font-family:Calibri,sans-serif;vertical-align:bottom;border:none;white-space:nowrap">corr</td>
</tr>
<tr height="20" style="height:15pt">
<td height="20" style="height:15pt;padding-top:1px;padding-right:1px;padding-left:1px;color:black;font-size:11pt;font-family:Calibri,sans-serif;vertical-align:bottom;border:none;white-space:nowrap">Polanska
2017</td>
<td align="right" style="padding-top:1px;padding-right:1px;padding-left:1px;color:black;font-size:11pt;font-family:Calibri,sans-serif;vertical-align:bottom;border:none;white-space:nowrap">337</td>
<td align="right" style="padding-top:1px;padding-right:1px;padding-left:1px;color:black;font-size:11pt;font-family:Calibri,sans-serif;vertical-align:bottom;border:none;white-space:nowrap">2</td>
<td align="right" style="padding-top:1px;padding-right:1px;padding-left:1px;color:black;font-size:11pt;font-family:Calibri,sans-serif;vertical-align:bottom;border:none;white-space:nowrap">-0.09</td>
</tr>
<tr height="20" style="height:15pt">
<td height="20" style="height:15pt;padding-top:1px;padding-right:1px;padding-left:1px;color:black;font-size:11pt;font-family:Calibri,sans-serif;vertical-align:bottom;border:none;white-space:nowrap">Polanska
2017</td>
<td align="right" style="padding-top:1px;padding-right:1px;padding-left:1px;color:black;font-size:11pt;font-family:Calibri,sans-serif;vertical-align:bottom;border:none;white-space:nowrap">219</td>
<td align="right" style="padding-top:1px;padding-right:1px;padding-left:1px;color:black;font-size:11pt;font-family:Calibri,sans-serif;vertical-align:bottom;border:none;white-space:nowrap">1</td>
<td align="right" style="padding-top:1px;padding-right:1px;padding-left:1px;color:black;font-size:11pt;font-family:Calibri,sans-serif;vertical-align:bottom;border:none;white-space:nowrap">-0.02</td>
</tr>
</tbody></table><br></div><div>Using R's metafor package, I obtained a combined effect size of -0.0718. Using Borenstein's method, I obtain an effect size of -0.06255. </div><div><br></div><div>Note. I often have fewer than 10 articles to combine in my meta-analyses (it varies between 3 and 10). I expect heterogeneity to be moderate to high in most of my analyses. </div></div><div><br></div><div>Thank you very much,</div><div>-- <br><div dir="ltr" class="gmail_signature" data-smartmail="gmail_signature"><div dir="ltr"><div><font color="#000000" size="1" face="arial, sans-serif"><b>GARANCE DELAGNEAU</b></font></div><div><font color="#000000" size="1" face="arial, sans-serif">PhD Student (Clinical Neuropsychology)</font></div><div><font size="1" color="#000000" face="arial, sans-serif"><br></font></div><div><font size="1" color="#000000" face="arial, sans-serif">M: 0452 323 762<br></font><div><font size="1" color="#000000" face="arial, sans-serif">E: <a href="mailto:elinor.fraser@monash.edu" style="color:rgb(17,85,204)" target="_blank">g</a><a href="mailto:arance.delagneau@monash.edu" target="_blank">arance.delagneau@monash.edu</a> </font></div></div></div></div></div></div>