<!doctype html public "-//W3C//DTD W3 HTML//EN">
<html><head><style type="text/css"><!--
blockquote, dl, ul, ol, li { padding-top: 0 ; padding-bottom: 0 }
--></style><title>binom.test and small N</title></head><body>
<div>running R 1.4.1 on MAC and 1.2.2 on Linux</div>
<div><br></div>
<div>When I use run binom.test with small N the results are a little
perplexing to me</div>
<div><br></div>
<div>>binom.test(9,20,p=0.5)</div>
<div><br></div>
<div>gives the below plus other stuff</div>
<div><br></div>
<div>95 percent confidence interval:<br>
0.2305779 0.6847219</div>
<div><br></div>
<div>Now:</div>
<div><br></div>
<div>>pbiom(9,20,0.6847219)</div>
<div>[1] 0.02499998 # i.e., lower 2.5% of
distribution</div>
<div>>pbinom(9,20,0.2305779)</div>
<div>[1] 0.9923132</div>
<div>>pbinom(8,20,0.2305779)</div>
<div> [1] 0.975 # i.e., upper 2.5%
of distribution</div>
<div><br></div>
<div>I would think I generally want a 95% CI on the observed 9 out of
20, not 8 out of 20 LB and 9 out of 20 UB. I am missing
something or is this strictly a function of the beta approximation
used in the source code??</div>
<div><br></div>
<x-sigsep><pre>--
</pre></x-sigsep>
<div><br>
Tony Long<br>
<br>
Ecology and Evolutionary Biology<br>
Steinhaus Hall<br>
University of California at Irvine<br>
Irvine, CA<br>
92697-2525<br>
<br>
Tel: (949) 824-2562 (office)<br>
Tel: (949) 824-5994 (lab)<br>
Fax: (949) 824-2181<br>
<br>
email: tdlong@uci.edu<br>
http://hjmuller.bio.uci.edu/~labhome/</div>
</body>
</html>