Dust flux, Vostok ice core

Dust flux, Vostok ice core
Two dimensional phase space reconstruction of dust flux from the Vostok core over the period 186-4 ka using the time derivative method. Dust flux on the x-axis, rate of change is on the y-axis. From Gipp (2001).

Friday, April 18, 2014

Are Kitco gold experts contrary indicators?

In response to recent debate, we ask the titular question (data originally from this IKN post).

I don't think so, although there is a very slight trend to that effect.

To test the idea, we plot the Kitco bearish and bullish opinion percentages against the performance of GLD the following week.

First up--the bulls.


I've plotted it the same way as the last time, although perhaps an argument can be made that I should switch the axes. There is a slight negative correlation, which would favour Otto's assertion that the experts are contrary indicators. But with r = -0.113, it is a weak correlation. By comparison, the correlation between bullish opinions and the previous week's performance of GLD was above 0.7.

And now the bears . . .


This time there is a weak positive correlation (r = 0.17), which favours the contrary indicator idea (high numbers of bears are followed by higher gold price)

At least since the beginning of September, 2013 (at which point gold was about $100 higher than at present).

Then I tried increasing the difference--maybe those Kitco experts are contrary indicators for GLD behaviour farther in the future.



If we compare the performance of GLD two weeks after the experts' prognostications (i.e., GLD's performance during the second week, not over the entire two week period), we get a reasonable correlation (r^2 = 0.21) - but this seems to suggest that you could bet along with the experts as long as you delay a week. So the current bullish posture favours a gold decline not this coming week, but the week after.

Given that r^2 was about 0.5 for the lagging indicator, that is still the favoured hypothesis. So given Kitco's bearish stance, your best bet is still to go back in time a week and short gold.

It does occur to me that a longer series, that covers a period where gold was performing well over a sustained period, may give a different result.

8 comments:

  1. Leaving aside the Time Lord thing, I've already noted in a couple of places (admittedly intuitively) that the contrary indication is more obvious on the "strong signal" weeks, i.e. when any option gets more than 50% of the term-used-loosely-expert opinion. In other words, the more vehement the term-used-loosely-expert opinions, the more likely it is to be wrong. Isn't that the archetypical definition of contrary indicator?

    ReplyDelete
    Replies
    1. You may have something there. It's harder to test and the series isn't long. You have 8 'yes' and 12 'no' for the strong survey (leaving out the :not really"). If you were testing a coin for fairness, flipped it 20 times and had 8 heads and 12 tails, it would be really hard to argue it wasn't random. With a fair coin, you will obtain such a result about 12% of the time (bear in mind that 10 heads and 10 tails exactly only occurs about 17.5% of the time).

      If you had 800 heads and 1200 tails, you could be certain it was not random. But 20 trials is too few for this sort of system.

      Delete
    2. Agreed the sample is small as stands today, it's the weak point (well, one of the weak points). By the way, we now add this week's result and get 8/13.

      Theory time: In the end, we can i believe agree* these people are collectively demonstrating ignorance about their specialist market. What we're likely picking up on is their (kneejerk?) psychological responses, not their quant analysis. Therefore it does fulfill what you'd want from a sloppy set of predictions and have at least the potential for a decent contrary indicator. Also good is how almost certainly having no effect whatsoever on its target (gold bullion price), so can be considered independent.


      *please beg to differ if necessary

      Delete
    3. Agreed. I don't want to see you (or anyone else) lose real money at this.

      Delete
  2. I don't have a problem with the sample size. We already know what's determining the outcome of the survey: recency effect.

    Statistically speaking r~0.1 is too weak a correlation for you to make any money. r>.5 is better but still not great.

    Put your money in the S&P 500 and go away for 10 years.

    ReplyDelete
    Replies
    1. For some reason my eyes insist you are talking about a "regency effect".

      Delete
  3. You could do a 3D graph with the time in the future as the additional axes. Maybe avereaging or not?

    ReplyDelete