stpm

stpm implements Stochastic Process Models (SPM) in R for joint modeling of longitudinal repeated measures and time-to-event (survival) outcomes, enabling estimation and simulation of stochastic dynamics and their impact on hazard functions.

Key Features:

• Model Estimation: Supports discrete- and continuous-time multidimensional SPMs and one-dimensional models with time-dependent parameters for estimating stochastic dynamics.
• Joint Modeling with Survival Analysis: Integrates stochastic processes with time-to-event outcomes to quantify effects of repeatedly measured variables on hazard functions.
• Simulation and Projection Tools: Simulates individual trajectories and projects hazard functions for scenario analysis.
• Data Preparation Functions: Provides utilities for preparing longitudinal datasets for SPM analysis.

Scientific Applications:

• Clinical longitudinal studies: Modeling relationships between time-varying biomarkers and patient survival or other event outcomes.
• Engineering reliability monitoring: Analyzing system reliability by modeling time-varying measures and failure probabilities.
• Longitudinal research: Investigating dynamic interplay between repeatedly measured covariates and event risks in biomedical and applied settings.

Methodology:

Integration of stochastic processes with survival analysis; supports discrete- and continuous-time SPM frameworks; simulation of individual trajectories and projection of hazard functions.