Summarize the results from the BuyseTest function.
# S4 method for BuyseRes
summary(object, print = TRUE, percentage = TRUE,
statistic = BuyseTest.options()$statistic, conf.level = 0.95,
alternative = "two.sided", method.boot = "percentile", strata = if
(length(object@level.strata) == 1) { "global" } else { NULL },
digit = c(2, 4))output of BuyseTest
[logical] Should the table be displayed?.
[logical] Should the percentage of pairs of each type be displayed ? Otherwise the number of pairs is displayed.
[character] the statistic summarizing the pairwise comparison:
"netChance" displays the net chance in favor of treatment, as described in Buyse (2010) and Peron et al. (2016)),
whereas "winRatio" displays the win ratio, as described in Wang et al. (2016).
[numeric] confidence level for the confidence intervals.
[character] the type of alternative hypothesis: "two.sided", "greater", or "less".
[character] the method used to compute the boostrap confidence intervals and p-values.
Can be "percentile" for computing the CI using the quantiles of the boostrap distribution or
"gaussian" for using a Gaussian approximation to compute the CI where the standard error is computed using the bootstrap samples.
[character vector] the name of the strata to be displayed. Can also be "global" to display the average over all strata.
[integer vector] the number of digit to use for printing the counts and the delta.
arguments to be passed from the generic method to the class specific method [not relevant to the user]
When using a permutation test, the uncertainty associated with the estimator is computed under the null hypothesis. Thus the confidence interval may not be valid if the null hypothesis is false. More precisely, the quantiles of the distribution of the statistic are computed under the null hypothesis and then shifted by the punctual estimate of the statistic. Therefore it is possible that the limits of the confidence interval are estimated outside of the interval of definition of the statistic (e.g. outside [-1,1] for the proportion in favor of treatment).
Note: For the win ratio, the proposed implementation enables the use of thresholds and endpoints that are not time to events as well as the correction proposed in Peron et al. (2016) to account for censoring. These development have not been examined by Wang et al. (2016), or in other papers (at out knowledge). They are only provided here by implementation convenience.
BuyseTest for performing a generalized pairwise comparison.
BuyseRes-class for a presentation of the BuyseRes object.
# NOT RUN {
dt <- simBuyseTest(1e2, n.strata = 3)
# }
# NOT RUN {
BT <- BuyseTest(Treatment ~ TTE(eventtime, censoring = status) + Bin(toxicity), data=dt)
# }
# NOT RUN {
# }
# NOT RUN {
summary(BT)
summary(BT, percentage = FALSE)
summary(BT, statistic = "winRatio")
# }
Run the code above in your browser using DataLab