Extract posterior draws from fitted mvgam objects

Extract posterior draws in conventional formats as data.frames, matrices, or arrays.

Usage

# S3 method for class 'mvgam'
as.data.frame(
  x,
  row.names = NULL,
  optional = TRUE,
  variable = "betas",
  use_alias = TRUE,
  regex = FALSE,
  ...
)

# S3 method for class 'mvgam'
as.matrix(x, variable = "betas", regex = FALSE, use_alias = TRUE, ...)

# S3 method for class 'mvgam'
as.array(x, variable = "betas", regex = FALSE, use_alias = TRUE, ...)

# S3 method for class 'mvgam'
as_draws(
  x,
  variable = NULL,
  regex = FALSE,
  inc_warmup = FALSE,
  use_alias = TRUE,
  ...
)

# S3 method for class 'mvgam'
as_draws_matrix(
  x,
  variable = NULL,
  regex = FALSE,
  inc_warmup = FALSE,
  use_alias = TRUE,
  ...
)

# S3 method for class 'mvgam'
as_draws_df(
  x,
  variable = NULL,
  regex = FALSE,
  inc_warmup = FALSE,
  use_alias = TRUE,
  ...
)

# S3 method for class 'mvgam'
as_draws_array(
  x,
  variable = NULL,
  regex = FALSE,
  inc_warmup = FALSE,
  use_alias = TRUE,
  ...
)

# S3 method for class 'mvgam'
as_draws_list(
  x,
  variable = NULL,
  regex = FALSE,
  inc_warmup = FALSE,
  use_alias = TRUE,
  ...
)

# S3 method for class 'mvgam'
as_draws_rvars(x, variable = NULL, regex = FALSE, inc_warmup = FALSE, ...)

Arguments

x

list object of class mvgam

row.names

Ignored

optional

Ignored

variable

A character specifying which parameters to extract. Can either be one of the following options:

obs_params (other parameters specific to the observation model, such as overdispsersions for negative binomial models or observation error SD for gaussian / student-t models)
betas (beta coefficients from the GAM observation model linear predictor; default)
smooth_params (smoothing parameters from the GAM observation model)
linpreds (estimated linear predictors on whatever link scale was used in the model)
trend_params (parameters governing the trend dynamics, such as AR parameters, trend SD parameters or Gaussian Process parameters)
trend_betas (beta coefficients from the GAM latent process model linear predictor; only available if a trend_formula was supplied in the original model)
trend_smooth_params (process model GAM smoothing parameters; only available if a trend_formula was supplied in the original model)
trend_linpreds (process model linear predictors on the identity scale; only available if a trend_formula was supplied in the original model)

OR can be a character vector providing the variables to extract

use_alias

Logical. If more informative names for parameters are available (i.e. for beta coefficients b or for smoothing parameters rho), replace the uninformative names with the more informative alias. Defaults to TRUE

regex

Logical. If not using one of the prespecified options for extractions, should variable be treated as a (vector of) regular expressions? Any variable in x matching at least one of the regular expressions will be selected. Defaults to FALSE.

...

Ignored

inc_warmup

Should warmup draws be included? Defaults to FALSE.

Value

A data.frame, matrix, or array containing the posterior draws.

Examples

# \donttest{
sim <- sim_mvgam(family = Gamma())
mod1 <- mvgam(y ~ s(season, bs = 'cc'),
             trend_model = 'AR1',
             data = sim$data_train,
             family = Gamma(),
             chains = 2,
             silent = 2)
#> Warning: Supplying trend_model as a character string is deprecated
#> Please use the dedicated functions (i.e. RW() or ZMVN()) instead
#> This warning is displayed once per session.
#> In file included from stan/lib/stan_math/stan/math/prim/prob/von_mises_lccdf.hpp:5,
#>                  from stan/lib/stan_math/stan/math/prim/prob/von_mises_ccdf_log.hpp:4,
#>                  from stan/lib/stan_math/stan/math/prim/prob.hpp:359,
#>                  from stan/lib/stan_math/stan/math/prim.hpp:16,
#>                  from stan/lib/stan_math/stan/math/rev.hpp:16,
#>                  from stan/lib/stan_math/stan/math.hpp:19,
#>                  from stan/src/stan/model/model_header.hpp:4,
#>                  from C:/Users/uqnclar2/AppData/Local/Temp/RtmpotLup8/model-9e8c33d43f8.hpp:2:
#> stan/lib/stan_math/stan/math/prim/prob/von_mises_cdf.hpp: In function 'stan::return_type_t<T_x, T_sigma, T_l> stan::math::von_mises_cdf(const T_x&, const T_mu&, const T_k&)':
#> stan/lib/stan_math/stan/math/prim/prob/von_mises_cdf.hpp:194: note: '-Wmisleading-indentation' is disabled from this point onwards, since column-tracking was disabled due to the size of the code/headers
#>   194 |       if (cdf_n < 0.0)
#>       | 
#> stan/lib/stan_math/stan/math/prim/prob/von_mises_cdf.hpp:194: note: adding '-flarge-source-files' will allow for more column-tracking support, at the expense of compilation time and memory
beta_draws_df <- as.data.frame(mod1, variable = 'betas')
head(beta_draws_df)
#>   (Intercept) s(season).1 s(season).2 s(season).3 s(season).4 s(season).5 s(season).6 s(season).7 s(season).8
#> 1    0.319726   -0.972376   -1.148710   -0.734276    0.462118     1.59223    0.934666    0.399375    0.176647
#> 2    0.180193   -1.616300   -1.036090   -0.768414    0.655170     1.20669    0.844760    0.243960    0.868440
#> 3    0.304901   -1.073380   -1.322890   -0.503359    0.964529     1.30952    1.059640    0.516082    0.115212
#> 4    0.268791   -1.224270   -0.946018   -0.636852    0.379731     1.22659    0.803573    0.351586    0.719370
#> 5    0.245721   -0.968587   -1.256310   -0.893110    0.591861     1.64159    1.097970    0.255019    0.607658
#> 6    0.135226   -1.155560   -1.011880   -0.336560    0.623057     1.02631    0.844620    0.643441    0.583991
str(beta_draws_df)
#> 'data.frame':	1000 obs. of  9 variables:
#>  $ (Intercept): num  0.32 0.18 0.305 0.269 0.246 ...
#>  $ s(season).1: num  -0.972 -1.616 -1.073 -1.224 -0.969 ...
#>  $ s(season).2: num  -1.149 -1.036 -1.323 -0.946 -1.256 ...
#>  $ s(season).3: num  -0.734 -0.768 -0.503 -0.637 -0.893 ...
#>  $ s(season).4: num  0.462 0.655 0.965 0.38 0.592 ...
#>  $ s(season).5: num  1.59 1.21 1.31 1.23 1.64 ...
#>  $ s(season).6: num  0.935 0.845 1.06 0.804 1.098 ...
#>  $ s(season).7: num  0.399 0.244 0.516 0.352 0.255 ...
#>  $ s(season).8: num  0.177 0.868 0.115 0.719 0.608 ...

beta_draws_mat <- as.matrix(mod1, variable = 'betas')
head(beta_draws_mat)
#>     variable
#> draw (Intercept) s(season).1 s(season).2 s(season).3 s(season).4 s(season).5 s(season).6 s(season).7
#>    1    0.319726   -0.972376   -1.148710   -0.734276    0.462118     1.59223    0.934666    0.399375
#>    2    0.180193   -1.616300   -1.036090   -0.768414    0.655170     1.20669    0.844760    0.243960
#>    3    0.304901   -1.073380   -1.322890   -0.503359    0.964529     1.30952    1.059640    0.516082
#>    4    0.268791   -1.224270   -0.946018   -0.636852    0.379731     1.22659    0.803573    0.351586
#>    5    0.245721   -0.968587   -1.256310   -0.893110    0.591861     1.64159    1.097970    0.255019
#>    6    0.135226   -1.155560   -1.011880   -0.336560    0.623057     1.02631    0.844620    0.643441
#>     variable
#> draw s(season).8
#>    1    0.176647
#>    2    0.868440
#>    3    0.115212
#>    4    0.719370
#>    5    0.607658
#>    6    0.583991
str(beta_draws_mat)
#>  num [1:1000, 1:9] 0.32 0.18 0.305 0.269 0.246 ...
#>  - attr(*, "dimnames")=List of 2
#>   ..$ draw    : chr [1:1000] "1" "2" "3" "4" ...
#>   ..$ variable: chr [1:9] "(Intercept)" "s(season).1" "s(season).2" "s(season).3" ...
#>  - attr(*, "nchains")= int 2

shape_pars <- as.matrix(mod1, variable = 'shape', regex = TRUE)
head(shape_pars)# }
#>     variable
#> draw shape[1] shape[2] shape[3]
#>    1 1.365670 0.973384 1.237680
#>    2 0.869383 1.512070 0.948521
#>    3 0.790533 1.020250 1.035100
#>    4 0.957937 1.139440 1.354040
#>    5 0.981846 0.952409 1.087680
#>    6 0.967652 1.438820 1.650290