Skip to main content
. Author manuscript; available in PMC: 2012 Oct 1.
Published in final edited form as: Stroke. 2011 Sep 1;42(10):2990–2994. doi: 10.1161/STROKEAHA.111.620765

Table 1.

Comparison of the NeuSTART CRM and even randomization with 33 subjects, under a dose-toxicity curve where dose tier 3 is the MTD and the toxicity rate increases with an odds ratio of 2.5 at each increment.

Design characteristics CRM Randomization
(a) Probability of selecting the MTDa 0.54 0.47
(b) Probability of selecting an overdosea 0.17 0.26
(c) Average number of subjects at MTD 13 7
(d) Average number of subjects at an overdose 6 13
(e) Median of toxicity odds ratio estimatea 5.2 2.6
a

The MTD and the odds ratio are estimated using logistic regression at the end of each simulated trial for the CRM and the randomization design.