cohere {titecrm} | R Documentation |
Returns a message on the coherence status of a two-stage CRM design.
cohere(prior, target, n, x0, method="bayes", scale=sqrt(1.34), detail=TRUE)
prior |
A vector of initial estimates of toxicity probabilities associated the doses. |
target |
The target DLT rate. |
n |
Sample size of the trial. |
x0 |
A vector of treatment sequence according to the initial
design. Must be of length n . |
method |
A character string to specify the method for parameter estimation. The default method ``bayes'' estimates the model parameter by the posterior mean. Estimation using ``mle'' is to be made available. |
scale |
Standard deviation of the normal prior of the model parameter. Default is sqrt(1.34). |
detail |
If TRUE, details about incoherent escalations will be displayed. |
Dose-toxicity relationship is assumed as an empiric power model $a_i^{exp(β)}$ where $a_i$ is the initial estimate of toxicity probability of dose level i and the model parameter $β$ has a normal prior with mean 0 and scale to be provided by users.
A two-stage CRM is defined by two components. First, an initial
design sequence (x0
) for dose assignments before any DLT is seen.
When a DLT is seen, dose assignment decisions are switched to the
CRM. See Cheung (2005) in the reference section.
A string character giving a message on the coherence status of a two-stage CRM design.
Cheung, Y. K. and Chappell, R. (2000). Sequential designs for phase I clinical trials with late-onset toxicities. Biometrics 56:1177-1182.
Cheung, Y. K. (2005). Coherence principles in dose-finding studies. Biometrika 92:863-873.
# Create a simple data set prior <- c(0.05,0.10,0.20,0.35,0.50,0.70) target <- 0.2 n <- 24 x0 <- c(rep(1,3),rep(2,3),rep(3,3),rep(4,3),rep(5,3),rep(6,9)) # The above design is coherent foo <- cohere(prior,target,n,x0) print(foo) # The design is incoherent if a larger target DLT rate is used. target2 <- 0.3 foo2 <- cohere(prior,target2,n,x0)