Thursday, March 25, 2010

Fore-casting is generally WRONG. Watch an expert explain that

There was a piece on Huffpost today (the link for that is on my Facebook page) where the guy was parsing a recent Greenspan talk and then accusing him of being a bunch of things. As with these pieces generally, rather than say what was not said, he just rips the guy and implies deceit. If you are doing your homework, then you should understand what he is saying and what he is not saying. Remember Parsing the FED? In order to understand clearly, you need to have the Greenspan perspective. You get that from his testimony to the Senate Banking Committee in Oct 08 where he explains very very clearly that the best of the best (supposedly those working at the FED) in Forecasting (what Greenspan does now privately and essentially what he did publicly at the FED) are wrong 40 percent of the time.

The implication of that is what?

Got the answer?

Watch , the written comments given by Greenspan at the beginning are well worth listening to and then you skip ahead to minute 108 to listen to the explanation in plain English that the very best forecasts are wrong 40 percent of the time meaning that the average forecast is more often wrong than it is right. Now if you are making a lot of bets and your average is wrong 40 percent of the time this is not such a bad thing, on average you win as long as you have a consistent exit strategy for both winners and losers. When you are making very few very long term bets however, with no particular pre-planned exit strategy and nothing going on simultaneously, you are playing a different game.  At least Greenspan was honest enough to say that his premises, (ideology is the word he used) were wrong and he recognizes that. Whoops. Well, this is bad when you are assuming he is always right but not particularly bad when you have his perspective which is that he is quite often wrong. Unfortunately the 'I was wrong' explanation is generally not what people in this country want to hear. Which is exactly why education is failing to advance at the rate that it might otherwise advance at. Students are taught both implicitly and explicitly that the phrase 'I was wrong' is anathema.

In justification of Greenspan for not apologizing or stating again that he was wrong and that there was some sort of problem with him being wrong you might look at it this way.

The fact is that the forecasts were wrong.

The assumption was that the forecasts would be wrong.

So there was nothing wrong and no need to apologize only to understand the second statement. Which Mr. Greenspan appears to be assuming that everyone understands.

The follow on from this of course is that if the forecasting business is not a single factor process i.e. that if your forecast of one thing is always multi factor involving essentially forecasts of one thing based on forecasts of other things which of course any economic analysis is and you have this error rate of wrong more than half the time then you would simply multiply the probability of being wrong on one factor with each other factor to determine the probability of being wrong on any multi factor analysis. Guess it is a good thing that the FED is not getting paid on accuracy and no one is keeping very close score of private economic forecast records. If anyone was then it would be a sparsely populated profession.

Saturday, March 13, 2010

Are you a scientist? Are you willing to experiment on yourself?

.....So Easterlin as an economist caused some distress in the profession with these results.
So what is the puzzle here? The puzzle is related to the affective forecasting that most people believe that circumstances like becoming richer will make them happier. It turns out that people's beliefs about what will make them happier are mostly wrong, and they are wrong in a directional way, and they are wrong very predictably. And there is a story here that I think is interesting. ......
So if you are intrigued i.e. a scientist, you need to go here  and read the whole series of talks.

This guy is a scientist (if you are unfamiliar with him, Wikipedia or links in the link are good places to learn more) so what he is doing here is proposing a theory and claiming that there is empirical evidence to support his conclusions. If you are a scientist, you will work with him and through the process of self reflection (free for everyone) analyze his theories and change your mind (or not).

Oh, the contra-positive, you are a sheep. You choose.