Site Comparison Statistics - Which site is fishiest?

[Josem]

I have a database of over 2million mined hands at Party at $0.50/$1 unlimited texas hold them.

I would like to compare this to similar databases at other sites. I think this has value in determining which site has the "worst" players.

1) What are decent sample sizes for this sort of data for a good chance of getting an answer to this question?

2) What can be done to reduce any biases in the data?

3) Is anyone willing to participate in sharing the data from other sites?*

4) What would the best way of progressing this be?

5) What data comparisons would you be interested in?

6) Any other feedback/comments/criticism/abuse?


*Presumably the hhs themselves can remain confidential - I'm only interested in the aggregated statistical data

[i]After several searches I haven't been able to find previous threads on this topic... if anyone knows any, links would be handy. I'm surprised this hasn't been done.