forecasting methods Quotes

And this is one way to do technology forecasting; get a sense of where technology is, and then anticipate the next upturn.

I'm an economist, I do a lot of forecasting, and I'm probably one of the most successful forecasters in terms of very specific kinds of forecasts.

The Brahmins say that in their books there are many predictions of times in which it will rain. But press those books as strongly as you can, you can not get out of them a drop of water. So you can not get out of all the books that contain the best precepts the smallest good deed.

Future forecasting is all about testing strategies - it's like a wind tunnel.

In a sense, there are as many forecasting methods as there are forecasters. But I would argue that most projections are derived from two major methods: macro-econometric models and eclectic judgment.

The best predictor of future events is probably past events.

There are two processes which we adopt consciously or unconsciously when we try to prophesy. We can seek a period in the past whose conditions resemble as closely as possible those of our day, and presume that the sequel to that period will, save for some minor alterations, be similar. Secondly, we can survey the general course of development in our immediate past, and endeavor to prolong it into the near future. The first is the method the historian; the second that of the scientist. Only the second is open to us now, and this only in a partial sphere.

We spend a lot of time and effort trying to figure out who's going to be a good NFL quarterback, and we do a very bad job of it. We don't really know. And we also spend a lot of time trying to figure out who will be a good teacher, and we're really bad at that too. We don't know if someone is going to be a good teacher when they start teaching. So what should we do in those situations in which predictions are useless?