NEWS.md

In modMStates: Simulation and Estimation of Continuous-Time Multi-State Markov Models for Panel Data

modMStates 0.0.1

Initial release of the reorganised package.

• Trajectories are generated exactly and the panel record is formed by evaluating the trajectory at the observation times, keeping trajectory generation and panel construction separate.
• sim_mspdata() supports irregular, subject-specific visit schedules, random missed visits, exactly observed absorption times, and Weibull (semi-Markov) holding times for assessing the Markov assumption.
• fit_msm() replaces fit.msm(), whose name collided with S3 dispatch on objects of class msm. fit.msm() and sim.mspdata() remain as deprecated aliases.
• fit_msm() validates state coding, duplicate visit times and observed transitions against the assumed structure before calling the optimiser, supports deathexact for exactly observed absorption, and reports the optimiser's convergence code.
• ms_montecarlo() reports Monte Carlo standard errors alongside bias, RMSE and coverage, and counts non-convergence from the optimiser code rather than from the absence of an error.
• fit_msm() recovers from the numerical overflow that msm can hit in large samples by refitting with a rescaled objective, and records this in the rescaled element. The retry runs only after an unscaled attempt has failed, so ordinary fits are unchanged.
• Licence changed to GPL-3 for compatibility with msm.

modMStates documentation built on Sept. 3, 2026, 5:10 p.m.