Subject: Re: is there a statistician in the house? (long)
From: Seth Gordon <>
Date: Thu, 10 Mar 2005 15:58:11 -0500

"Reputation" can mean different things in different contexts, so maybe I 
should make myself clear: the kind of reputation I am interested in is 
the kind that one gets through giving gifts, and which can lead to 
reciprocal gifts.  (Should I have used "Whuffie" or "karma" instead of 

People with high Google-fu, or with excellent credit ratings, have a 
different kind of good "reputation", which serves them well in other 
contexts, but that's not what I'm interested in here.

[Karsten Self:]
> Problems in reputation management systems generally run into the
> following traps:
>   - Defining what's being measured.  Reputation and/or competence in A
>     is not transative to B.
>   - Skill of the evaluator.  Rater A may have far less competence to
>     judge than B.  How do you weight their inputs?  How do you assess
>     their judgement?
>   - Tuning to test.  Any quality assessment tool must of necessity
>     measure a small number of quantifiable aspects.  Over time, testees
>     tune themselves to maximize test results.
>   - Corruption.  Attempting to influence either test-makers or
>     evaluators.

The Kindness Of Strangers Game does nothing to protect players against 
making bad evaluations of the gifts they receive, or bad decisions about 
who to endorse--just as a laissez-faire market economy does nothing to 
protect consumers against overpaying for a product.

If your guru gives you a blessed amulet, you are free to announce to the 
world that the guru's gift is more precious to you than anything else 
you have ever received, including the CPR you got last week from the guy 
who saw you faint in a restaurant.  If other people choose to endorse 
devotees of the guru, and then find him at the top of their secondary 
rank list, that's the consequence of their choice.

"Simple faith can lead to very complex aveirot."  --Shmarya
// seth gordon // // //