<html><head><style type="text/css"><!-- DIV {margin:0px;} --></style></head><body><div style="font-family:arial, helvetica, sans-serif;font-size:10pt;color:#000000;"><DIV></DIV>
<DIV>
<DIV>Dear R-friends,</DIV>
<DIV style="FONT-FAMILY: arial, helvetica, sans-serif; FONT-SIZE: 10pt">
<DIV style="FONT-FAMILY: times new roman, new york, times, serif; FONT-SIZE: 12pt">
<DIV style="FONT-FAMILY: arial, helvetica, sans-serif; COLOR: #000000; FONT-SIZE: 10pt">
<DIV> </DIV>
<DIV>I just started learning R. I have a project on lot <SPAN id=lw_1276681209_0 class=yshortcuts>quality assurance</SPAN> sampling (LQAS). In this project I have to develop LQAS plans to make decision on stopping / continuing a programme. The LQAS plans is based on <SPAN style="BORDER-BOTTOM: #366388 2px dotted; CURSOR: hand" id=lw_1276681209_1 class=yshortcuts>cluster sampling</SPAN>: selection of k clusters (villages) of m children each for a total sample of n. In this connection I would like to estimate the classification errors ( alpha and beta) that would be expected as a consequence of sampling clusters (villages / households) instead of usual SRS under traditional LQAS. In order to estimate the classification errors I would like to simulate correlated binary outcomes for a given level of prevalence and intracluster correlation (rho).</DIV>
<DIV> </DIV>
<DIV>Specifically I would like simulate an LQAS plan (33 clusters of 6 children each, n =198 children) to generate clusters with specific intercluster (0.05) and intracluster correlation (0.1) subject to the constraint that the intercluster correlation is less than or equal to intracluster correlation for a given level of prevalence (upper threshold =1% and lower threshold=0.1%). For this purpose I have used the following command (which is under mvtBinaryEP in mvtnorm library in R):</DIV>
<DIV> </DIV>
<DIV>ep0 = ep(mu=0.1, rho=0.05, n=6, nRep=33, seed=NULL)<BR>apply(ep0$y, c(1,2), mean); cor(ep0$y)<BR></DIV>
<DIV>The above commands produce 198 binary outcomes (33 clusters with cluster size of 6 each) and a matrix (6x6) of bivariate correlations. Since the input among others requires values either for 'rho' along with 'mu' or an 'R' matrix and a <SPAN style="BORDER-BOTTOM: #366388 2px dotted; CURSOR: hand" id=lw_1276681209_2 class=yshortcuts>column vector</SPAN> of 'mu', I wonder whether the binary outcomes meets my specification about inter-cluster correlation. I would be very much grateful to R-community, if someone helps me out.</DIV>
<DIV> </DIV>
<DIV>thanking you in advance and I am looking forward to R-community</DIV>
<DIV> </DIV>
<DIV>subramanian</DIV>
<DIV>==========</DIV>
<DIV> </DIV>Dr S.Subramanian<BR>Assistant Director<BR>Vector Control Research Centre<BR>Indira Nagar<BR>Pondicherry - 605 006<BR>INDIA <BR> </DIV></DIV></DIV></DIV>
<DIV></DIV></div><br>
</body></html>