heemod (version 0.4.0)

run_models: Run one or more Markov Model

Description

Runs one or more unevaluated Markov Models. When more than one model is provided, all models should have the same states and state value names.

Usage

run_models(..., parameters = define_parameters(), init = c(1000L, rep(0L, get_state_number(get_states(list(...)[[1]])) - 1)), cycles = 1, method = c("life-table", "beginning", "end", "half-cycle"), cost = NULL, effect = NULL, base_model = NULL)
run_models_(list_models, parameters, init, cycles, method, cost, effect, base_model)

Arguments

...

One or more uneval_model object.

parameters

Optional. An object generated by define_parameters.

init

numeric vector, same length as number of model states. Number of individuals in each model state at the beginning.

cycles

positive integer. Number of Markov Cycles to compute.

method

Counting method.

cost

Names or expression to compute cost on the cost-effectiveness plane.

effect

Names or expression to compute effect on the cost-effectiveness plane.

base_model

Name of base model used as reference. By default the model with the lowest effectiveness.

list_models

List of models, only used by run_models_ to avoid using ....

Value

A list of evaluated models with computed values.

Details

A usual situation where more than one model needs to be run is when comparing different care startegies.

In order to compute comparisons Markov Models must be similar (same states and state value names). Thus models should only differ through parameters, transition matrix cell values and values attached to states (but not state value names).

The initial number of individuals in each state and the number of cycle will be the same for all models.

Internally this function does 2 operations: first evaluating parameters, transition matrix, state values and computing individual counts through eval_model; and then using individual counts and evaluated state values to compute values at each cycle through compute_values.

Examples

# running a single model

mod1 <-
  define_model(
    transition_matrix = define_matrix(
      .5, .5,
      .1, .9
    ),
    define_state(
      cost = 543,
      ly = 1
    ),
    define_state(
      cost = 432,
      ly = 1
    )
  )


res <- run_models(
  mod1,
  init = c(100, 0),
  cycles = 2,
  cost = cost,
  effect = ly
)

# running several models
mod2 <-
  define_model(
    transition_matrix = define_matrix(
      .5, .5,
      .1, .9
    ),
    define_state(
      cost = 789,
      ly = 1
    ),
    define_state(
      cost = 456,
      ly = 1
    )
    
  )


res2 <- run_models(
  mod1, mod2,
  init = c(100, 0),
  cycles = 10,
  cost = cost,
  effect = ly
)