`MVNORM.Rd`

This sampler function for BAMLSS uses estimated `parameters`

and the Hessian
information to create samples from a multivariate normal distribution. Note that smoothing
variance uncertainty is not accounted for, therefore, the resulting credible intervals
are most likely too narrow.

MVNORM(x, y = NULL, family = NULL, start = NULL, n.samples = 500, hessian = NULL, ...)

x | The |
---|---|

y | The model response, as returned from function |

family | A bamlss family object, see |

start | A named numeric vector containing possible starting values, the names are based on
function |

n.samples | Sets the number of samples that should be generated. |

hessian | The Hessian matrix that should be used. Note that the row and column names
must be the same as the names of the |

… | Arguments passed to function |

Function `MVNORM()`

returns samples of parameters. The samples are provided as a
`mcmc`

matrix.

## Simulated data example illustrating ## how to call the sampler function. ## This is done internally within ## the setup of function bamlss(). d <- GAMart() f <- num ~ s(x1, bs = "ps") bf <- bamlss.frame(f, data = d, family = "gaussian") ## First, find starting values with optimizer. o <- with(bf, bfit(x, y, family))#> AICc 310.9125 logPost -146.281 logLik -148.601 edf 6.7482 eps 2.4418 iteration 1 #> AICc 308.4063 logPost -135.263 logLik -148.941 edf 5.1966 eps 0.1422 iteration 2 #> AICc 306.2649 logPost -126.116 logLik -149.144 edf 3.9490 eps 0.0221 iteration 3 #> AICc 305.0141 logPost -136.724 logLik -149.282 edf 3.1979 eps 0.0667 iteration 4 #> AICc 304.8739 logPost -172.796 logLik -149.351 edf 3.0608 eps 0.0184 iteration 5 #> AICc 304.8739 logPost -172.796 logLik -149.351 edf 3.0608 eps 0.0000 iteration 6 #> AICc 304.8739 logPost -172.796 logLik -149.351 edf 3.0608 eps 0.0000 iteration 6 #> elapsed time: 0.47sec#>plot(samps)