Comparison of randomization procedures
Compares randomization procedures based on a specified issue in clinical trials.
compare(issue, ..., endp) ## S4 method for signature 'issue,missing' compare(issue, ..., endp) ## S4 method for signature 'issue,endpoint' compare(issue, ..., endp)
issue: object of class issue....: at least one object of class randSeq or a list of objects of class randSeq.endp: object of class endpoint, or missing.S4 object of class comparison summarizing the comparison of the randomization procedures.
Randomization procedures behave differently with respect to issues like selection bias, chronological bias, or loss in power estimation. The compare function evaluates the behavior of randomization procedures with respect to one issue. Its first argument should represent one of the implemented issues. The second argument should be any number of objects of the class randSeq. These objects represent the randomization procedures for the planned comparison. The last argument endp may be provided if the assessment should take the distribution of the treatment groups into account, e.g. for power evaluation.
# compare Random Allocation Rule and Big Stick for N = 4 with respect to # correct guesses RAR <- getAllSeq(rarPar(4)) BSD <- getAllSeq(bsdPar(4, mti = 2)) corGuess <- corGuess("CS") (comp <- compare(corGuess, RAR, BSD)) plot(comp) # compare the same procedures with respect to selection bias for a normal endpoint endp <- normEndp(c(2, 2), c(1, 1)) selBias <- selBias("CS", 4, "exact") (comp <- compare(selBias, RAR, BSD, endp = endp)) plot(comp) # compare the same procedures with respect to selection bias for an exponential endpoint endp <- expEndp(lambda = c(0.5, 0.5), cenRate=0.1, accrualTime=1, cenTime=5) selBias <- selBias("CS", 0.1, "exact") (comp <- compare(selBias, RAR, BSD, endp = endp)) plot(comp)
Representation of randomization procedures: randPar
Generation of randomization sequences: genSeq
issues for the assessment of randomization sequences
Useful links