Performs equivalence tests and related confidence intervals for ratios of two normal means of multiple endpoints.
multeq.rat(data, grp, resp = NULL, base = 1, margin.lo = NULL, margin.up = NULL,
method = "single.step", var.equal = FALSE, FWER = 0.05)
a data frame containing response variables (endpoints) and the group variable as columns, the data must have exactly two treatment groups
the name of the group variable in " "
a vector of names of the response variables (endpoints) in " "
a single integer specifying the base/control group
a vector of relative lower margins under the null hypotheses relating to the endpoints
a vector of relative upper margins under the null hypotheses relating to the endpoints
a character string:
"step.up": method of Quan et al. (2001),
"single.step": Bonferroni-adjusted single-step procedure
a logical indicating homogeneous or heterogeneous variances of the data
a single numeric value specifying the familywise error rate to be controlled by the simultaneous confidence intervals
An object of class multeq.rat containing:
a (named) vector of estimated ratios
a (named) vector of the calculated test statistics (var.equal=TRUE)
a (named) vector of the calculated test statistics (up) (var.equal=FALSE)
a (named) vector of the calculated test statistics (do) (var.equal=FALSE)
a single degree of freedom (var.equal=TRUE)
a (named) vector of degrees of freedom for test statistics (up) (var.equal=FALSE)
a (named) vector of degrees of freedom for test statistics (do) (var.equal=FALSE)
a (named) vector of degrees of freedom used for the confidence intervals (var.equal=FALSE)
a (named) vector of p-values adjusted for multiplicity
a (named) vector of lower confidence limits
a (named) vector of upper confidence limits
The objective is to show equivalence for two treatment groups on multiple primary, normally distributed response variables (endpoints). If margin.up is not given, one-sided tests are applied for the alternative hypothesis that the ratios (to the base group) of the means is larger than margin.lo. Analogously, same vice versa. Only if both margin.lo and margin.up are given, a two-sided equivalence tests for ratios is done. Bonferroni adjusted "two one-sided t-tests" (TOST) and related simultaneous confidence intervals are used for method "single.step"; an extended version of the method of Quan et al. (2001) is applied for "step.up". Welch t-tests and related confidence intervals are used for var.equal=FALSE.
Quan et al. (2001): Assessmant of equivalence on multiple endpoints, Statistics in Medicine 20, 3159-3173
# NOT RUN {
data(clinic)
comp <- multeq.rat(data=clinic,grp="fact",method="step.up",margin.up=rep(1.25,5),
margin.lo=1/rep(1.25,5))
summary(comp)
# }
Run the code above in your browser using DataLab