This is a method for analyzing the stability of a circuit with multiple loops. It was first mentioned in section 8.8 of Hendrik W. Bode's book "Network Analysis and Feedback Amplifier Design" (see
http://books.google.com/books?id=RuNSAAAAMAAJ&dq=isbn:0882752421&pgis=1) that was first published in 1945. To quote: "If a circuit is stable when all its tubes have their normal gains, the total number of clockwise and counterclockwise encirclements of the critical point must be equal to each other in the series of Nyquist diagrams for the individual tubes obtained by beginning with all tubes dead and restoring the tubes successively in any order to their normal gains." For more details about Nyquist diagrams, see e.g.
http://en.wikipedia.org/wiki/Nyquist_stability_criterion.
Disabling the active elements ("tubes") here means setting the gain of their internal controlled sources to zero so that the passive impedances seen by the circuit are not changed. This is very difficult to realize with the usual transistor models because they do not offer direct access to these controlled sources.
See also the last paragraph of
http://www.designers-guide.org/Forum/YaBB.pl?num=1163532257/1#1. For an overview of simulation methods for single-loop feedback circuits, see
http://www.geocities.com/frank_wiedmann/loopgain.html.