Learn More
This article describes some of the important statistical properties of the commonly used permuted-block design, also known simply as blocked-randomization. Under a permutation model for statistical tests, proper analyses should employ tests that incorporate the blocking used in the randomization. These include the block-stratified Mantel-Haenszel chi-square(More)
The statistical properties of simple (complete) randomization, permuted-block (or simply blocked) randomization, and the urn adaptive biased-coin randomization are summarized. These procedures are contrasted to covariate adaptive procedures such as minimization and to response adaptive procedures such as the play-the-winner rule. General recommendations are(More)
A double-blind, placebo-controlled trial was set up to compare clindamycin and pyrimethamine as prophylaxis for toxoplasmic encephalitis (TE) in HIV-infected patients at risk of the disorder. Interim analysis showed that clindamycin-treated patients were 4.4 (95% confidence interval 1.3-15.2) times more likely to experience an adverse effect that(More)
Many medical studies rely on the evaluation of large amounts of clinical data. Neither a trained technician nor a standard computer program can be used to perform the evaluation which requires clinical Judgement. We are currently doing research on the use of expert systems to reduce the tlme and expense of having a medlcal expert perform these subjective(More)
Powerful new training algorithms developed for ar tificial neural networks hold th e promise of identifying regulari ties in t he t raining data an d generalizing over t he test data. T he backprop a-gatio n algorithm is one such t raining algorithm t ha t, with th e use of hidden units, can learn functions such as exclusive-or. These fun ctions can be(More)
  • 1