Can lead to a better understanding of the nature of any nonstationary process among the different component series.
Usage
vecm(
vintages.view,
lag = 2,
model = c("none", "cnt", "trend"),
na.zero = FALSE
)Arguments
- vintages.view
mts object. Vertical or diagonal view of the
create_vintages()output- lag
Number of lags
- model
Character. Must be "none" (the default), "cnt" or "trend".
- na.zero
Boolean whether missing values should be considered as 0 or rather as data not (yet) available (the default).
Examples
## Simulated data
df_long <- simulate_long(
n_period = 10L * 4L,
n_revision = 5L,
periodicity = 4L,
start_period = as.Date("2010-01-01")
)
## Create vintage and test
vintages <- create_vintages(df_long, periodicity = 4L)
vecm(vintages$diagonal_view)
#> trace(2) trace(1) max(2) max(1)
#> [Release[1]]_[Release[2]] 1.6562945 8.031349 1.6562945 6.375054
#> [Release[1]]_[Release[3]] 3.0793634 10.069574 3.0793634 6.990211
#> [Release[1]]_[Release[4]] 2.1102022 9.568271 2.1102022 7.458069
#> [Release[1]]_[Release[5]] 2.3791334 9.230042 2.3791334 6.850908
#> [Release[2]]_[Release[3]] 3.6984240 14.349196 3.6984240 10.650772
#> [Release[2]]_[Release[4]] 0.8551128 4.692964 0.8551128 3.837852
#> [Release[2]]_[Release[5]] 1.8385867 11.062839 1.8385867 9.224252
#> [Release[3]]_[Release[4]] 3.6598144 16.043888 3.6598144 12.384074
#> [Release[3]]_[Release[5]] 1.5652573 8.413604 1.5652573 6.848347
#> [Release[4]]_[Release[5]] 2.1921695 24.436972 2.1921695 22.244803