Aira-class: The aira main class.
In frbl/airaR:

Description Fields Methods

The aira main class.

bootstrap_iterations: the number of bootstrap iterations to do for determining the significance of the effects
horizon: the number of steps to look in the future
var_model: the var model to perform the calculations on
orthogonalize: use orthogonalized IRF

determine_best_node_from_all(negative_variables = c()): Returns the total effect a variable has on all other variables in the network. If bootstrap iterations provided to aira is 0, we will not run any bootstrapping. If bootstrap iterations >0, we will only consider the significant effects in the response. If negative_variables are provided, we will convert those variables to positive ones (i.e., depression will become -1 * depression) @param negative_variables the variables to invert to positibe variables
determine_effect_network(include_autoregressive_effects = FALSE): Returns the summed effect each node has on the other nodes node @param include_autoregressive_effects if enabled, autoregressive effects are used (default FALSE). Not yet supported!
determine_length_of_effect(variable_name, response, measurement_interval, first_effect_only = FALSE, plot_results = FALSE): Returns the time in minues a variable is estimated to have an effect on another variable. @param variable_to_shock the name of the variable to receive the shock @param variable_to_respond the name of the variable to respond to the shock @param measurement interval the time in minutes between two measurements
determine_percentage_effect(variable_to_improve, percentage): Returns the percentage for each variable in the network (other then the provided variable) to be changed in order to change the variable_to_improve with the given percentage. @param variable_to_improve the name of the variable in the network which we'd like to improve @param percentage the percentage with which we'd like to improve the variable to improve
get_all_variable_names(): returns all variables in the var model