Extracting binary variables from economic data: Is there a quantum view?

Some economic variables are inherently binary, like a credit event declared by the International Swaps and Derivatives Association (ISDA).  Others can be viewed in different ways.  In the process of extracting them, it’s natural to ask if they could be used in models that allowed them to take on multiple values simultaneously.

For example, the U.S. Energy Information Administration (EIA) keeps track of petroleum inventories of various types.  All of the time series have unique labels, and the data can be downloaded in CSV form for analysis.  The graphs below have been downloaded from the EIA and have their series names attached.

In the first graph below, we see the month-end U.S. stocks of 15-to-500ppm sulfur fuel oil.   Reductions in sulfur were mandated in 2006, and the decline in stocks is evident.  

Extracting binary variables from economic data: Is there a quantum view?

  The production (and inevitable month-end storage) of low sulfur fuel oil followed quickly, as shown in the graph below (shorter time scale from 2005 to the present).  

Extracting binary variables from economic data: Is there a quantum view?

  For our purposes however, the more interesting plot is the high sulfur fuel stocks shown below.  There is a strong periodic component, which plausibly looks like an annual cycle.

Extracting binary variables from economic data: Is there a quantum view?

Here’s the frequency analysis, which tells us a little more.  There’s a definite yearly component, but the peak is asymmetric.  There are clearly some years where the cycle took longer to complete.  

Extracting binary variables from economic data: Is there a quantum view?

  Material in storage means that money is not being made.  It Is also possible that the people responsible for estimating demand simply made a mistake, in which case there may have been other mistakes in hedging that extend beyond the drawdown of the high sulfur stocks.

The binary variable of LATE versus NOT LATE can serve as an input to a more complex model.   There are several ways to do this classically.  However, in theory we could construct a model where LATE and NON LATE could be processed simultaneously.  The question now is whether we can do this in practice – and if not now, when?

Add Comment
1 Answer(s)

With all due respect to the underlying Quantum Mechanics model of the Nature, the |LATE> and |NOT LATE> is not mutually exclusive in real, classical ( non-quantum ) world, if for no other reason, due to a parallel multi-level fractality, driven within an externally given seasonality of the market dynamics.

Answered on May 11, 2016.
Add Comment

Your Answer

By posting your answer, you agree to the Terms & Privacy policy.