Thanks to Kit Baum, merlin is now available on SSC.
ssc install merlin
Requires: Stata version 14.2.
merlin allows you to fit mixed effects regression models for linear and non-linear outcomes.
Much of what merlin can do, can be done with gsem or gllamm...much of what merlin can do, can't be done with gsem or gllamm.
merlin can fit multivariate outcome models of any type, each of which could be repeatedly measured (longitudinal), with any number of levels, and with any number of random effects at each level. Standard distributions/models available include the Bernoulli, beta, gamma, Gaussian, linear quantile, negative binomial, ordinal, Poisson, and time-to-event/survival models include the exponential, Gompertz, splines on the log hazard scale, Royston-Parmar, and Weibull. merlin provides a flexible complex predictor syntax, allowing the user to define variables, random effects, restricted cubic spline and fractional polynomial functions, user-defined functions, functions of other outcome models, and any interaction between each of them. Non-linear and time-dependent effects are seamlessly incorporated into the predictor. merlin allows level-specific random effect distributions, either multivariate normal or t, which are integrated out using either Gaussian quadrature (adaptive or non-adaptive) or Monte-Carlo integration. merlin also allows the user to provide their own log likelihood function, or [log]hazard and cumulative hazard function for survival analysis, which is written in Mata using merlin utility functions, whilst still being able to make use of the powerful complex predictor, which provides a framework for methods development.
See the merlin homepage on my website for examples, of which there are many more to add.
All the models from my other commands including, stjm (joint longitudinal and survival models), stgenreg (user-defined hazard regression) and stmixed (multilevel parametric survival models), can all be fitted with merlin, and substantially extended.
Feedback is welcome, as I'm continuing to develop merlin, but especially bug reports, of which I expect there may be quite a few...
Thanks,
Michael
ssc install merlin
Requires: Stata version 14.2.
merlin allows you to fit mixed effects regression models for linear and non-linear outcomes.
Much of what merlin can do, can be done with gsem or gllamm...much of what merlin can do, can't be done with gsem or gllamm.
merlin can fit multivariate outcome models of any type, each of which could be repeatedly measured (longitudinal), with any number of levels, and with any number of random effects at each level. Standard distributions/models available include the Bernoulli, beta, gamma, Gaussian, linear quantile, negative binomial, ordinal, Poisson, and time-to-event/survival models include the exponential, Gompertz, splines on the log hazard scale, Royston-Parmar, and Weibull. merlin provides a flexible complex predictor syntax, allowing the user to define variables, random effects, restricted cubic spline and fractional polynomial functions, user-defined functions, functions of other outcome models, and any interaction between each of them. Non-linear and time-dependent effects are seamlessly incorporated into the predictor. merlin allows level-specific random effect distributions, either multivariate normal or t, which are integrated out using either Gaussian quadrature (adaptive or non-adaptive) or Monte-Carlo integration. merlin also allows the user to provide their own log likelihood function, or [log]hazard and cumulative hazard function for survival analysis, which is written in Mata using merlin utility functions, whilst still being able to make use of the powerful complex predictor, which provides a framework for methods development.
See the merlin homepage on my website for examples, of which there are many more to add.
All the models from my other commands including, stjm (joint longitudinal and survival models), stgenreg (user-defined hazard regression) and stmixed (multilevel parametric survival models), can all be fitted with merlin, and substantially extended.
Feedback is welcome, as I'm continuing to develop merlin, but especially bug reports, of which I expect there may be quite a few...
Thanks,
Michael
Comment