I try to estimate a model using the ARIMA function of the fable package. The function works fine on the example provided by the authors of the package, however, when I try to run the code on my own data, I get the warning: “not all series have the same phase”, and it results in , while I assumed to get an estimated ARIMA model.

I ran the following sample code, where I received the error:

library(fable)

key = c(rep("group 1",53))
date = seq.Date(as.Date("2022-01-01"), by = "14 days", length.out = 53)
timeseries_data = rnorm(53,3,2)

tsibble_data <- tsibble(data.frame(key,date ,timeseries_data),key = "key", index = "date")

test_model <- tsibble_data %>%
  model(ARIMA(timeseries_data))
report(test_model)