Returns the final confidence interval for the parameter of interest. It is based on the prototype case, i.e., the test for testing a mean for normally distributed variables.
getFinalConfidenceInterval(
design,
dataInput,
...,
directionUpper = NA,
thetaH0 = NA_real_,
tolerance = 1e-06,
stage = NA_integer_
)Returns a list containing
finalStage,
medianUnbiased,
finalConfidenceInterval,
medianUnbiasedGeneral, and
finalConfidenceIntervalGeneral.
The trial design.
The summary data used for calculating the test results.
This is an element of DatasetGeneral, DatasetMeans,
DatasetRates, or DatasetSurvival
and should be created with the function getDataset().
For more information see getDataset().
Further (optional) arguments to be passed:
normalApproximationThe type of computation of the p-values. Default is FALSE for
testing means (i.e., the t test is used) and TRUE for testing rates and the hazard ratio.
For testing rates, if normalApproximation = FALSE is specified, the binomial test
(one sample) or the exact test of Fisher (two samples) is used for calculating the p-values.
In the survival setting, normalApproximation = FALSE has no effect.
equalVariancesThe type of t test. For testing means in two treatment groups, either
the t test assuming that the variances are equal or the t test without assuming this,
i.e., the test of Welch-Satterthwaite is calculated, default is TRUE.
stdErrorEstimateEstimate of standard error for calculation of final confidence intervals for
comparing rates in two treatment groups, default is "pooled".
Logical. Specifies the direction of the alternative,
only applicable for one-sided testing; TRUE
means that larger values of the test statistics yield smaller p-values.
The default is TRUE for means, rates, and count data, and FALSE for survival data
(power calculations, simulations, and analyses).
In sample size calculations, the direction is derived from the specified alternative;
a specified directionUpper must agree with it.
The null hypothesis value,
default is 0 for general estimates, the normal case, and the binary case,
it is 1 for the survival case (testing the hazard ratio).
For non-inferiority designs, thetaH0 is the non-inferiority bound.
That is, in case of (one-sided) testing of
general estimates: a value on the scale of the supplied estimates can be specified.
means: a value != 0
(or a value != 1 for testing the mean ratio) can be specified.
rates: a value != 0
(or a value != 1 for testing the risk ratio pi1 / pi2) can be specified.
survival data: a bound for testing H0: hazard ratio = thetaH0 != 1 can be specified.
count data: a bound for testing H0: lambda1 / lambda2 = thetaH0 != 1 can be specified.
For testing a rate in one sample, a value thetaH0 in (0, 1) has to be specified for
defining the null hypothesis H0: pi = thetaH0.
The numerical tolerance, default is 1e-06. Must be a positive numeric of length 1.
The stage number (optional). Default: total number of existing stages in the data input.
Depending on design and dataInput the final confidence interval and median unbiased estimate
that is based on the stage-wise ordering of the sample space will be calculated and returned.
Additionally, a non-standardized ("general") version is provided,
the estimated standard deviation must be used to obtain
the confidence interval for the parameter of interest.
For the inverse normal combination test design with more than two stages, a warning informs that the validity of the confidence interval is theoretically shown only if no sample size change was performed.
Other analysis functions:
getAnalysisResults(),
getClosedCombinationTestResults(),
getClosedConditionalDunnettTestResults(),
getConditionalPower(),
getConditionalRejectionProbabilities(),
getFinalPValue(),
getRepeatedConfidenceIntervals(),
getRepeatedPValues(),
getStageResults(),
getTestActions()
if (FALSE) {
design <- getDesignInverseNormal(kMax = 2)
data <- getDataset(
n = c(20, 30),
means = c(50, 51),
stDevs = c(130, 140)
)
getFinalConfidenceInterval(design, dataInput = data)
}
Run the code above in your browser using DataLab