This preview shows page 1. Sign up to view the full content.
Unformatted text preview: 5-FU suggested that, when given in combination with topotecan, theMTD of 5-FU was a priori believed to be less than 425 mg/m2. Inconsequence, the support of the prior for the MTD was finite. In manycontexts, there will not be sucient information available prior to theonset of the phase I trial to unambiguously determine a suitable upperbound for the MTD (and hence for the range of dose levels to besearched). In this case, one might introduce a hyperparameterXmaxandspecify a joint prior distribution for the MTD andXmaxashg;Xmax f1gjXmaxfXmaxwith, to continue the 5-FU example,f1(gjXmax) denoting the probabilitydensity function (pdf) of a uniform random variable on [140, 425] andf(Xmax) a monotone decreasing pdf defined on [425,l), such as atruncated normal with mean 425 and suitable standard deviation.Flournoy (1993) considered the two-parameter logistic model in Eq.(3) reparameterized in terms of the MTD and the nuisance parameterN=h2. The parametersgandNwere assumed to be independent a priori...
View Full Document
This note was uploaded on 06/13/2011 for the course PHYSICS 101 taught by Professor Shu during the Spring '11 term at FIU.
- Spring '11