Skip to content
Back to formatted view

Raw Message

Message-ID: <Pine.LNX.4.44.0304012023250.12034-100000@gannet.stats>
Date: 2003-04-01T19:45:16Z
From: Brian Ripley
Subject: cor.test observations limit
In-Reply-To: <3.0.5.32.20030401135701.009f71a0@host2a.emmes.com>

Yes.  About 1290 for the Spearman test.

You need (n^3 - n) representable as an integer.

On Tue, 1 Apr 2003, Ming-Chung Li wrote:

> Is there a limit on the number of observations for using cor.test. For
> example,
> 
> > library(ctest)

That's not needed, and has not been for about 3 years.

> > cor.test(rnorm(3000), rnorm(3000), method="spearman")
> Error in if (q > (n^3 - n)/6) pspearman(q - 1, n, lower.tail = FALSE) else
> pspearman(q,  : 
>         missing value where logical needed
> In addition: Warning message: 
> NAs introduced by coercion 

-- 
Brian D. Ripley,                  ripley at stats.ox.ac.uk
Professor of Applied Statistics,  http://www.stats.ox.ac.uk/~ripley/
University of Oxford,             Tel:  +44 1865 272861 (self)
1 South Parks Road,                     +44 1865 272866 (PA)
Oxford OX1 3TG, UK                Fax:  +44 1865 272595