data.simASD: A simulated mega-dataset for illustrating the adaptive...

In gu-mi/simASD: Enhancement of the Adaptive Signature Design (ASD) for Learning and Confirming in a Single Pivotal Trial

Description

A dataset containing the survival times, censoring status, biomarkers and indicators for learn/confirm allocations. This dataset is used as an example to illustrate how to perform a simulation study for evaluating key parameters in an adaptive signature design (ASD).

Usage

data(data.simASD)

Format

A data frame with 70,000 rows and 13 variables:

dataset

an index for the 100 simulated datasets, each consisting of 700 subjects

id

unique subject IDs in each dataset

trt

treatment arm indicator (0 = control; 1 = treatment)

y_duration

survival time (in days)

y_censor

censoring status (0 = censored; 1 = event)

x1-x3

continuous biomarkers, generated from Uniform(0,1) distribution

ME_30_flag-ME_70_flag

indicator (0/1) for learn/confirm allocations: column name "30" means 30% of subjects are in the learn stage, while 70% are in the confirm stage

Source

Results from an internal simulator at Eli Lilly and Company. The dataset is identical to the one used in the manuscript, scenario: n=700, p=3, the strongest predictive biomarker effect.

gu-mi/simASD documentation built on May 17, 2019, 8:57 a.m.