ConditionalSampleSize-class {adoptr} | R Documentation |
This score simply evaluates n(d, x1)
for a design d
and the
first-stage outcome x1
.
The data distribution and prior are only relevant when it is integrated.
ConditionalSampleSize() ExpectedSampleSize(dist, prior) ## S4 method for signature 'ConditionalSampleSize,TwoStageDesign' evaluate(s, design, x1, optimization = FALSE, ...)
dist |
a univariate |
prior |
a |
s |
|
design |
object |
x1 |
stage-one test statistic |
optimization |
logical, if |
... |
further optional arguments |
design <- TwoStageDesign(50, .0, 2.0, 50, 2.0, order = 5L) prior <- PointMassPrior(.4, 1) css <- ConditionalSampleSize() evaluate(css, design, c(0, .5, 3)) ess <- ExpectedSampleSize(Normal(), prior) # those two are equivalent evaluate(ess, design) evaluate(expected(css, Normal(), prior), design)