Open-source software
Everything the team maintains in the open — the merlin family, specialist Stata commands, our R packages, and the reproducible code behind the papers. All free and openly licensed, on GitHub or SSC.
The merlin family
One survival-regression engine and the packages built directly on it, in R and Stata.
merlin
StataRThe survival-regression engine — multilevel mixed-effects models, ten baseline families, cure and relative-survival models, and time-dependent effects under one syntax.
stmerlin
StataConvenience wrapper for fitting parametric and semi-parametric survival models with merlin, optionally across multiple timescales.
morgana
StataR · in devBayesian flexible survival models built on the merlin engine. The Stata package is available now; an R implementation with full posterior inference via the No-U-Turn Sampler is in development.
pendragon
StataRIn devMulti-state and competing-risks models on top of merlin and morgana — transition probabilities, length of stay, restricted mean time in state, and health-economic outputs (QALYs, costs, ICERs, CEACs). In active development in R and Stata.
avalon
StataRIn devSurvival-data simulation — standard, flexible-parametric, and user-defined hazards, with competing-risks and multi-state structures. Under one name in R and Stata; in active development.
gawain
StataRIn devValidation for survival prediction models — discrimination, calibration and decision-curve utility, for single-event, competing-risks and multi-state outcomes. Takes predictions as data, so it evaluates a model fitted in any software; in active development in R and Stata.
Focused survival commands
Standalone Stata commands for specific survival-analysis problems — each installable from this website or from GitHub.
jmqaly
StataQuality-adjusted life years after a joint longitudinal-survival model fitted with merlin. The reference implementation of the paper's estimators; requires one specific merlin version.
stdmest
StataStandardised survival probabilities and hierarchical contrasts after mixed-effects survival models.
Also on SSC
Further Stata commands from the team's published work, each installable from SSC with ssc install. The descriptions are SSC's own.
extfunnel
StataFunnel-plot overlays showing the impact a new study would have on a meta-analysis.
Install with ssc install extfunnel.
metapow
StataSimulation-based sample size for a new study that updates a meta-analysis.
Install with ssc install metapow.
stgenreg
StataGeneral parametric survival models with any user-defined baseline hazard.
Install with ssc install stgenreg.
stjm
StataShared-parameter joint models of longitudinal and survival data.
Install with ssc install stjm.
stjm11
StataShared-parameter joint models of longitudinal and survival data. The Stata 11 edition of stjm.
Install with ssc install stjm11.
stjmgraph
StataA joint longitudinal and survival graph.
Install with ssc install stjmgraph.
stmix
StataTwo-component parametric mixture survival models.
Install with ssc install stmix.
stmt
StataMultiple timescales in flexible parametric survival models on the log-hazard scale.
Install with ssc install stmt.
Our work in R
A growing set of R packages for multi-state visualisation, trial simulation, and standardised hierarchical contrasts.
msm.stacked
RStacked-probability plots and transition probabilities for msm multi-state models.
stdmest-r
RStandardised survival probabilities and hierarchical contrasts — an R port of the Stata stdmest.
Code behind the papers
Replication data, annotated code, and talk materials accompanying the team's published methods work.
multilevel-survival-regstd
StataSynthetic data and annotated code reproducing the analyses in the multilevel-standardisation paper.
jmqaly-example
StataSimulated example data and Stata code for the paper on estimating quality-adjusted life years with joint models.
2023-nesc-hsurv
StataSlides and code for the talk “Hierarchical Survival Models: Estimation, Prediction, Interpretation.”