fit_models: Fit EDM (Simplex), multiview embedding, Larkin, and Ricker...

In andrew-edwards/EDMsimulate: Simulating Fish Populations for Empirical Dynamic Modeling

Fit EDM (Simplex), multiview embedding, Larkin, and Ricker models

Description

Fits EDM, multiview embedding, Larkin, and Ricker models to simulated data using parallel processing

Usage

fit_models(
  sim,
  res_realisations,
  R_switch,
  T,
  pbsEDM_args,
  mve_args,
  larkin_args,
  ricker_args,
  mvs_fit,
  larkin_fit,
  ricker_fit
)

Arguments

sim	Tibble of simulated data generated from salmon_sim()
res_realisations	Empty data frame with correct headers for outputs of estimation
R_switch	either 'R_prime_t' or 'R_t' to specify which one the calculations are based on, and what should be the response variable for multiview embedding.
T	number of time points being used to forecast 'R_switch' at 'T+1'
pbsEDM_args	List of arguments to pass onto 'pbsEDM::pbsEDM()'. Note that 'lags' has no default, so needs to be specified here. First one must be called 'R_switch' to then get automatically changed to what is specified by the 'R_switch' parameter
mve_args	List of arguments to pass onto 'pbsEDM::multiview_embedding()', here we will add 'R_switch' as the response variable
larkin_args	List of arguments to pass onto 'larkin::....()'.
ricker_args	List of arguments to pass onto 'larkin::....()'.
mvs_fit	Is the multivariate simplex fit? (TRUE/FALSE).
larkin_fit	Is the Larkin model fit? (TRUE/FALSE).
ricker_fit	Is the Ricker model fit? (TRUE/FALSE).

Value

List object call output with components: - 'single_realisation' forecasts from all models in last year - 'fit_edm_single' predictions for each year from EDM, with realisation number appended to start - 'fit_mve_single' predictions for each year from multiview embedding, with realisation number appended to start - 'fit_lar_single' predictions for each year from larkin, with realisation number appended to start - 'fit_ric_single' predictions for each year from ricker, with realisation number appended to start

Author(s)

Carrie Holt and Andrew Edwards

Examples

## Not run: 
# See Issue #17, kind of. Have copied into #18 (and Andy's READpbs) to paste
  into R console. Need to get this working; currently get error because m
  not defined.
set.seed(42)
R_switch_manual <- "R_t"
simulated_5 <- EDMsimulate::salmon_sim()
##' edm_args_manual <- list(lags = list(R_switch = 0, S_t = 0:3),
                               first_difference = TRUE,
                               centre_and_scale = TRUE)
mve_args_manual <- list(lags = list(R_t = 0:1, S_t = 0:3))
larkin_args_manual = list(run_stan = FALSE,
                          prior_mean_alpha = 2,
                          prior_mean_beta = -rep(1,4),
                          prior_mean_sigma = 0.5,
                          prior_sd_alpha = 0.5,
                          prior_sd_beta = rep(0.25,4),
                          prior_sd_sigma = 0.25)
ricker_args_manual = list(run_stan = FALSE,
                          prior_mean_alpha = 2,
                          prior_mean_beta = -1,
                          prior_mean_sigma = 0.5,
                          prior_sd_alpha = 0.5,
                          prior_sd_beta = 0.25,
                          prior_sd_sigma = 0.25)

res_fit_models_5 <- fit_models(simulated_5,
                               R_switch = R_switch_manual,
                               T = nrow(simulated_5),
                               mve_args = mve_args_manual),
                               pbsEDM_args = edm_args_manual
                               larkin_args = larkin_args_manual,
                               ricker_args = ricker_args_manual)


# This next one doesn't quite work.
set.seed(42)
h_simulated <- 0.1095 + sample(1:180) * 0.001 # has mean of 0.2
simulated_4 <- EDMsimulate::salmon_sim(h = h_simulated)
res_fit_models <- fit_models(simulated_4,
                             R_switch = "R_t",
                             T = 80,
                             pbsEDM_args = list(
                                 lags = list(R_switch = 0,
                                 first_difference = TRUE,
                                 centre_and_scale = TRUE),
                             mve_args = list(
                                    lags = list(R_t = 0:4,
                                                  S_t = 0:8)),
                                    larkin_args = list(
                                      run_stan = FALSE,
                                      prior_mean_alpha = 2,
                                      prior_mean_beta = -rep(1,4),
                                      prior_mean_sigma = 0.5,
                                    prior_sd_alpha = 0.5,
                                      prior_sd_beta = rep(0.25,4),
                                      prior_sd_sigma = 0.25),
                                 ricker_args = list(
                                      run_stan = FALSE,
                                   prior_mean_alpha = 2,
                                      prior_mean_beta = -1,
                                      prior_mean_sigma = 0.5,
                                      prior_sd_alpha = 0.5,
                                      prior_sd_beta = 0.25,
                                      prior_sd_sigma = 0.25))


## End(Not run)

andrew-edwards/EDMsimulate documentation built on Oct. 25, 2023, 2:43 p.m.