Boostrap for Model Predictions

Source: R/tunaboot.R

Bootstrap function which compute proportion by species fishing mode and ocean for confindence interval

tunaboot(
  sample_data,
  allset_data,
  Ntree = 1000,
  Nmtry = 2,
  Nseed = 7,
  min_node = 5,
  Nboot = 10,
  Nseed_boot,
  target_period
)

Arguments

sample_data

(data frame) Data used for the modelling. Output table from process 3.1.

allset_data

(data frame) Data used for prediction.Output table from process 3.4.

Ntree

(integer) Number of trees to grow. This should not be set to too small a number, to ensure that every input row gets predicted at least a few times. The default value is 1000.

Nmtry

Number of variables randomly sampled as candidates at each split. The default value is 2.

Nseed

Set the initial seed for the modelling. The default value is 7.

min_node

Minimum size of terminal nodes. Setting this number larger causes smaller trees to be grown (and thus take less time).The default value is 5.

Nboot

The number of bootstrap samples desired. The fefault value is 10

Nseed_boot

Set the initial seed for the modelling. The default value is equal to Nseed parameter

target_period

Time period for the predictions in year. Default is the year of the data to predict