I'm finding trouble applying the Holt Winter's seasonal method to daily data I've read about it, but I can't solve the trouble.
I have a dataset of the daily uses of a transport. The data goes from the 1st September of 2016 to the 31st August. I've removed the COVID-19 effect, separating the 2020 and 2021 years.
datos_def = ts(datos_demanda[,-1], start = c(2016,246), end= c(2021, 243),frequency = 365)
viajeros_r <- window(datos_def, start = c(2016,246), end = c(2019,365))
Then when I try to use the Holt Winter's method:
fit1 = hw(viajeros_r, h = 365, seasonal = "multiplicative", level = c(80,95))
I'm getting the next error:
Error in ets(x, "MAM", alpha = alpha, beta = beta, gamma = gamma, phi = phi, : Frequency too high
What should I change?
