Unit root test
Arguments
- vintages.view
mts object. Vertical or diagonal view of the
create_vintages()
output- adfk
Number of lags to consider for Augmented Dicky-Fuller (ADF) test
- 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)
unitroot(vintages$diagonal_view)
#> DF.value DF.stderr DF.statistic DF.pvalue ADF.value ADF.stderr
#> Release[1] 1.0760920 0.02650206 2.8711717 0.9983733 1.0706418 0.03494104
#> Release[2] 1.0797077 0.02169862 3.6733980 0.9997991 1.0449947 0.02861695
#> Release[3] 0.9544934 0.05288013 -0.8605614 0.3188937 0.9361367 0.05377613
#> Release[4] 0.9563834 0.05157373 -0.8457132 0.3246546 0.9422743 0.05422577
#> Release[5] 1.0065022 0.06202035 0.1048397 0.6987347 1.0032162 0.06771362
#> ADF.statistic ADF.pvalue DFCT.value DFCT.stderr DFCT.statistic
#> Release[1] 2.02174337 0.9873704 0.9373832 0.05674814 -1.103415
#> Release[2] 1.57230855 0.9688151 0.9511755 0.04311644 -1.132388
#> Release[3] -1.18757674 0.2051380 0.3611297 0.24695041 -2.587039
#> Release[4] -1.06454285 0.2450705 0.3239961 0.28829986 -2.344794
#> Release[5] 0.04749681 0.6790338 -0.1899049 0.38666233 -3.077375
#> DFCT.pvalue PP.value PP.stderr PP.statistic PP.pvalue
#> Release[1] 0.9108172 1.0760920 0.02650206 2.5667940 0.9964668
#> Release[2] 0.9054680 1.0797077 0.02169862 2.6465254 0.9971078
#> Release[3] 0.3038507 0.9544934 0.05288013 -0.9088984 0.3006094
#> Release[4] 0.4168471 0.9563834 0.05157373 -0.9059072 0.3017861
#> Release[5] 0.1437274 1.0065022 0.06202035 0.4597083 0.8043938