The state released an updated forecast from Moody’s today along with some slides that make little sense (found here). I would go into the details of the forecast but why bother? We have absolutely no insight into the forecast process followed, the assumptions underlying any model relationships, or even a list of variables employed and the time period considered. Seriously, if this were my forecasting class, they would fail.
I did some looking at sales tax revenues. I went back to July of 2009 and stopped the graph at December 2015. I will have a separate post looking at the circumstances after that date with the revision of the forecast and what happened then. These data come from the state OMB Rev-E-News publication released monthly.
This is going to get a bit more technical than many of my other posts. However, I am a big believer that there is no reason to shy away from complexity, particularly when avoiding it sacrifices accuracy. So we are going to discuss forecast performance for sales tax in North Dakota. There are many different ways to evaluate forecasts and the one I will use here is called a tracking signal.
So I told my forecasting students I would post what I taught them today. I project monthly ND oil prices forward to the end of 2016. The following graph is the result of this process.