SYNPM: SYNthetic Prediction Models (SYNPM) and Validation dataset

In predRupdate: Prediction Model Validation and Updating

SYNthetic Prediction Models (SYNPM) and Validation dataset

Description

A list containing: (1) information on some (synthetic) existing prediction models (representing those available/published, which we want to validate in another independent dataset); and (2) a synthetic dataset that we wish to validate/update the models on.

Usage

SYNPM

Format

A list with six elements.

1. The first element is a data frame with the information about three existing binary (logistic regression) models for a binary outcome at one year

2. The second element is a data frame with the information about three existing time-to-event (Cox) models for the time-to-event outcome

3. The third, fourth and fifth elements are the cumulative baseline hazard information for the three time-to-event model

4. The sixth element is the (synthetic) validation dataset on which we want to validate the existing models. The dataset has 20000 rows and 8 variables:

   Age

   The age of the individual at baseline

   SexM

   The sex of the individual (1 = male; 0 = female)

   Smoking_Status

   Indicates whether the individual was or is a smoker (1=previous/ current smoker, 0=non-smoker)

   Diabetes

   Indicates whether the individual has diabetes (1=diabetic, 0=not diabetic)

   Creatinine

   The Creatinine value for the individual (mg/dL)

   ETime

   The time from baseline until either the event or censoring

   Status

   Indicator of whether the patient experienced the event or was censored at ETime

   Y

   Binary indicator of whether the individual experienced the event by 1 time-unit

Source

Simulated Data; see https://github.com/GlenMartin31/predRupdate

predRupdate documentation built on Sept. 11, 2024, 5:34 p.m.