Events vs. Seasonality variation in Forecast Studio

bluesky — Tue, 25 Oct 2016 17:12:51 GMT

I have month-wise data that I'm using to forecast in Forecast Studio.

If I set up events (Pulse) for each month (of historical data) and apply the 'Use if Significant' filter, I'm getting substantially different results compared to not using events and just using the usual seasonality parameters.

Basically, then it looks like the events are picking up additional variation compared to what the seasonality alone picks up.

I'm wondering if anyone would have any insights to why this may be happening? Any thoughts greatly appreciated!

Thanks.

Re: Events vs. Seasonality variation in Forecast Studio

mitrov — Fri, 04 Nov 2016 14:24:21 GMT

Seasonal components in time series models are not equivalent to dummy variables for the months, as they are often in linear regression models. Therefore, it is not suprising that you are getting different results.

For example, the following page details the equations for the additive Holt-Winters model, which is an exponential smoothing model with an additive seasonal component.

https://support.sas.com/documentation/cdl/en/etsug/68148/HTML/default/viewer.htm#etsug_tffordet_sect021.htm

As you can see, the seasonal component S_t is dynamic, in that it depends on the past values S_(t-p), where p is the period.

In a regression model with seasonal dummies, the seasonal effect is a static additive component which does not vary with time.

topic Re: Events vs. Seasonality variation in Forecast Studio in SAS Forecasting and Econometrics

Events vs. Seasonality variation in Forecast Studio

Re: Events vs. Seasonality variation in Forecast Studio