Maths abuse

Another week, another set of business lectures. This weeks wisdom was all to do with decision taking and what is apparently known as Decision Theory… The basic concepts seemed fair enough, and the aims are all very laudable, which is to add some rigor and repeatability to the decision process. However, the processes and exercises we were taken through felt like pseudoscience at best. I would love to be convinced by these processes, but they seemed to rely on some very questionable maths. Most if not all of them used weighting values and rankings. These figures do not generally seem to based on measured values, but guesses or expected/desired. Once you have multiplied many of these together, the relative errors seem to add up to make the ‘results’ meaningless. Interestingly there was no discussion on this. What I am still pondering is if there is still some value in the process, as it produces a formal and repeatable system for decision making, as opposed to the traditional nebulous gut-feeling models.
Either way I think there is value in knowing how the theory works, as this is a growing field in use in many companies, so their decision are often driven by these models and methods. One method we played with was an interesting (and expensive) Monte Carlo plug-in for excel, which seems to add serious brute-force techniques to ill defined problems. Now, I suspect many of these methods have been used recently in financial institutions to decide on the wisdom of taking on say.. sub-prime loans, and calculating the value of companies and investments.
Oh dear..

1 Comment so far
Leave a comment

Sadness. To talk, a terraclast, and still, comments there are none!
Where shall we find reflections of our thoughts; our images.
You are this. You are that. You are Elle.
Misgivings, then: perhaps best not to post.

Also, where can I get a nice bit of code to make a gallery?



Leave a comment
Line and paragraph breaks automatic, e-mail address never displayed, HTML allowed: <a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <cite> <code> <del datetime=""> <em> <i> <q cite=""> <strike> <strong>

(required)

(required)