getAnalysisResults {rpact}  R Documentation 
Calculates and returns the analysis results for the specified design and data.
getAnalysisResults(design, dataInput, ..., directionUpper = C_DIRECTION_UPPER_DEFAULT, thetaH0 = NA_real_, nPlanned = NA_real_)
design 
The trial design. 
dataInput 
The summary data used for calculating the test results.
This is either an element of 
... 
Further arguments to be passed to methods (cp. separate functions in See Also), e.g.,

directionUpper 
The direction of onesided testing.
Default is 
thetaH0 
The null hypothesis value, default is 0 for the normal and the binary case,
it is 1 for the survival case.
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. 
nPlanned 
The sample size planned for the subsequent stages. It should be a vector with length equal to the remaining stages and is the overall sample size in the two treatment groups if two groups are considered. 
Given a design and a dataset, at given stage the function calculates the test results
(effect sizes, stagewise test statistics and pvalues, overall pvalues and test statistics,
conditional rejection probability (CRP), conditional power, Repeated Confidence Intervals (RCIs),
repeated overall pvalues, and final stage pvalues, median unbiased effect estimates,
and final confidence intervals.
dataInput
is either an element of DatasetMeans
, of DatasetRates
, or of
DatasetSurvival
and should be created with the function getDataset
.
Returns an AnalysisResults
object.
The conditional power is calculated only if effect size and sample size is specified. Median unbiased effect estimates and confidence intervals are calculated if a group sequential design or an inverse normal combination test design was chosen, i.e., it is not applicable for Fisher's pvalue combination test design.
A final stage pvalue for Fisher's combination test is calculated only if a twostage design was chosen. For Fisher's combination test, the conditional power for more than one remaining stages is estimated via simulation.
Alternatively the analysis results can be calculated separately using one of the following functions:
design < getDesignGroupSequential() dataMeans < getDataset( n = c(10,10), means = c(1.96,1.76), stDevs = c(1.92,2.01)) getAnalysisResults(design, dataMeans) # produces: # # Analysis results (group sequential design): # Stages : 1, 2, 3 # Information rates : 0.333, 0.667, 1.000 # Critical values : 3.471, 2.454, 2.004 # Futility bounds (nonbinding) : Inf, Inf # Cumulative alpha spending : 0.0002592, 0.0071601, 0.0250000 # Stage levels : 0.0002592, 0.0070554, 0.0225331 # Effect sizes : 1.96, 1.86, NA # Test statistics : 3.228, 2.769, NA # pvalues : 0.005177, 0.010895, NA # Overall test statistics : 3.228, 4.342, NA # Overall pvalues : 0.0051766, 0.0001757, NA # Futility bounds for power : NA # Actions : continue, reject and stop, NA # Theta H0 : 0 # CRP : 0.3177, 0.9434, NA # Planned sample size : NA, NA, NA # Planned allocation ratio : 1 # Assumed effect : NA # Assumed standard deviation : 1 # Conditional power : NA, NA, NA # RCIs (lower) : 1.236, 0.702, NA # RCIs (upper) : 5.16, 3.02, NA # Repeated pvalues : 0.081766, 0.001825, NA # Final stage : 2 # Final pvalue : NA, 0.0004094, NA # Final CIs (lower) : NA, 0.654, NA # Final CIs (upper) : NA, 2.36, NA # Median unbiased estimate : NA, 1.51, NA