<div dir="ltr"><div><div><div><div><div>Hi - <br><br></div>I am using the documentation page for the escorc Pearson sample correlation function: <a href="http://www.ncl.ucar.edu/Document/Functions/Built-in/escorc.shtml">http://www.ncl.ucar.edu/Document/Functions/Built-in/escorc.shtml</a><br><br></div>** Under Example 1, two methods for the calculation and confidence limits are given. Under the alternative method, the following is given:<br><p>
An alternative for testing significance is:
</p><pre> t = r*log<a href="http://www.ncl.ucar.edu/Document/Functions/Built-in/log.shtml"><strong></strong></a>((n-2)/(1-<b>r</b>^2))
p = student_t(t, df)
psig = 0.05 ; test significance level
print("t="+t+" p="+p) ; t=2.02755 p=0.0732238
</pre>** However, to calculate t (as stated further up on the page) one uses:<br> <i><br></i>t =<b> </b>r*sqrt[ (<i>n</i>-2)/(1-r^2) ]<br><br></div>It seems then that the formula for t given in the alternative test is wrong, in using the log rather than the sqrt? <br><br></div>Thanks as always for your help.<br></div><br><div><div><div><div><div><br clear="all"><div><div><div><div class="gmail_signature" data-smartmail="gmail_signature"><div dir="ltr"><div><div dir="ltr"><div><div dir="ltr"><div>-- <br>Tess Parker<br>Associate Researcher<br>School of Earth, Atmosphere and Environment<br>Room 225, Building 28<br></div><div>9 Rainforest Walk<br></div><div>Monash University, Clayton VIC 3800<br><br></div><a href="http://users.monash.edu.au/~tess/index.html" target="_blank">http://users.monash.edu.au/~tess/index.html</a><br></div></div></div></div></div></div></div>
</div></div></div></div></div></div></div></div>