Computes optimal orders (lag structure) for the short-run relationships and autoregressive part of the ARDL model prior to ARDL bounds test with the approach of Pesaran et al. (2001).
ardlBoundOrders(data = NULL , formula = NULL, ic = c("AIC", "BIC", "MASE",
"GMRAE"), max.p = 15, max.q = 15, FullSearch = FALSE )
A data.frame
including all dependent and independent series. Column names this data.frame
must match the variable names in formula
.
A formula
object showing the dependent and independent series.
Information criterion to be used in the serach for optimal orders.
Maximum order for the short-run coefficients.
Maximum auto-regressive order.
If TURE
, a search over all possbilble models is implemented. See the details.
An integer
or data.frame
object including p-orders for the short-run relationship part.
The autoregressive order.
The selected statistic of all the considered models where all short-run relationship orders (p-orders) are equal.
The selected statistic of all possible combinations of short-run relationship orders (p-orders). The reported lag structure is the one that gives the minimum value to the chosen statistic among these combinations.
If FullSearch = FALSE
, this function first assumes that all p-orders are equal for the short-run relationships and finds the optimal p-order and autoregressive orders. Then, it finds the best subset of p-orders allowing them to change for each series in the short-run relationship part of the ARDL model under alternative hypothesis of ARDL bounds test.