<?xml version='1.0'?>
<!DOCTYPE art SYSTEM 'http://www.biomedcentral.com/xml/article.dtd'>
<art>
   <ui>1471-2288-4-1</ui>
   <ji>1471-2288</ji>
   <fm>
      <dochead>Correction</dochead>
      <bibl>
         <title>
            <p>Correction: A simple method for analyzing data from a randomized trial with a missing binary outcome</p>
         </title>
         <aug>
            <au id="A1" ca="yes">
               <snm>Baker</snm>
               <mi>G</mi>
               <fnm>Stuart</fnm>
               <insr iid="I1"/>
               <email>sb16i@nih.gov</email>
            </au>
            <au id="A2">
               <snm>Freedman</snm>
               <mi>S</mi>
               <fnm>Laurence</fnm>
               <insr iid="I2"/>
               <email>lsf@actcom.co.il</email>
            </au>
         </aug>
         <insg>
            <ins id="I1">
               <p>Biometry Research Group, Division of Cancer Prevention, National Cancer Institute, USA</p>
            </ins>
            <ins id="I2">
               <p>Department of Mathematics, Statistics, and Computer Science, Bar Ilan University, Ramat Gan 52900, Israel</p>
            </ins>
         </insg>
         <source>BMC Medical Research Methodology</source>
         <issn>1471-2288</issn>
         <pubdate>2004</pubdate>
         <volume>4</volume>
         <issue>1</issue>
         <fpage>1</fpage>
         <url>http://www.biomedcentral.com/1471-2288/4/1</url>
         <xrefbib>
            <pubidlist>
               <pubid idtype="doi">10.1186/1471-2288-4-1</pubid>
               <pubid idtype="pmpid">14711383</pubid>
            </pubidlist>
         </xrefbib>
      </bibl>
      <history>
         <rec>
            <date>
               <day>02</day>
               <month>1</month>
               <year>2004</year>
            </date>
         </rec>
         <acc>
            <date>
               <day>07</day>
               <month>1</month>
               <year>2004</year>
            </date>
         </acc>
         <pub>
            <date>
               <day>07</day>
               <month>1</month>
               <year>2004</year>
            </date>
         </pub>
      </history>
      <cpyrt>
         <year>2004</year>
         <collab>Baker and Freedman; licensee BioMed Central Ltd. This is an Open Access article: verbatim copying and redistribution of this article are permitted in all media for any purpose, provided this notice is preserved along with the article's original URL.</collab>
      </cpyrt>
      <abs>
         <sec>
            <st>
               <p/>
            </st>
            <p/>
         </sec>
      </abs>
   </fm>
   <bdy>
      <sec>
         <st>
            <p/>
         </st>
         <p>In this article <abbrgrp><abbr bid="B1">1</abbr></abbrgrp>, equation (8) is incorrect because it omitted the covariance terms. Let <it>h </it>denote the number of strata, so <it>s </it>= 1,2,...,<it>h</it>. Let <it>T </it>denote transpose, &#8226; denote matrix product, and <it>Diagonal Matrix </it>[<it>vector</it>] denote a matrix of all 0's except for <it>vector </it>on the diagonal. The correct formula is</p>
         <p>
            <graphic file="1471-2288-4-1-i1.gif"/>
         </p>
         <p>where</p>
         <p>
            <graphic file="1471-2288-4-1-i2.gif"/>
         </p>
         <p>In our example, the effect of the correction was negligible; the corrected estimated standard error was the same to two significant digits as the incorrect value.</p>
         <p>Also for clarification, we note that in the sentence after (11), it is an assumption that, within stratum <it>s</it>, the difference, &#916;<sub><it>s</it></sub>, does not depend on the unobserved covariate <it>x</it>.</p>
      </sec>
   </bdy>
   <bm>
      <refgrp>
         <bibl id="B1">
            <title>
               <p>A simple method for analyzing data from a randomized trial with a missing binary outcome</p>
            </title>
            <aug>
               <au>
                  <snm>Baker</snm>
                  <fnm>SG</fnm>
               </au>
               <au>
                  <snm>Freedman</snm>
                  <fnm>LS</fnm>
               </au>
            </aug>
            <source>BMC Medical Research Methodology</source>
            <pubdate>2003</pubdate>
            <volume>3</volume>
            <fpage>8</fpage>
            <xrefbib>
               <pubidlist>
                  <pubid idtype="pmcid">194902</pubid>
                  <pubid idtype="pmpid" link="fulltext">12734019</pubid>
                  <pubid idtype="doi">10.1186/1471-2288-3-8</pubid>
               </pubidlist>
            </xrefbib>
         </bibl>
      </refgrp>
      <sec>
         <st>
            <p>Pre-publication history</p>
         </st>
         <p>The pre-publication history for this paper can be accessed here:</p>
         <p>
            <url>http://www.biomedcentral.com/1471-2288/4/1/prepub</url>
         </p>
      </sec>
   </bm>
</art>
