1

I have a time series for which I want to adjust a structural model (trend, seasonal and cycle) using KFAS. However, seasonality starts at a certain point in time. Say, the time series ranges monthly from january 2000 through august 2022, but seasonality starts in 2011. Is there a way to capture such behavior in the series without splitting the data at that point?

I have already tried splitting the time series, but I would like a unified model. I am using KFAS in R for the estimation, though I have used also autostm for automatic structural models. Even though they achieve an appropriate fit (even for the whole time series), I think it can be improved with this idea. I thought I could us a regressor on the seasonality but I couldn't find how.

Jesús A. Piñera
  • 113
  • 4

1 Answers1

1

Are you using SSModel with a formula input? You could try adding a seasonality term to your data and add the seasonality term to the right-hand side of ~ in the formula.

Isaiah
  • 2,091
  • 3
  • 19
  • 28
  • 1
    Indeed I am using SSModel, and I tried generating the seasonal dummy variables as regressors and use SSMregression with these dummies and an indicator function over the period of interest. I have tried using combinations of both at the same time. I believe this might be the solution but I am still checking because the residuals aren't white noise. – Jesús A. Piñera Nov 18 '22 at 17:46
  • 1
    I succeeded using an external regressor made of the dummies for the seasonality. I also achieved changes in the seasonality by estimating the variance of each month separately. – Jesús A. Piñera Jan 17 '23 at 03:21