Quote:
Originally Posted by bcbrown
[You must be logged in to view images. Log in or Register.]
I cannot help myself but to note that in the past on this forum I've had interactions with people who were aggressively uninterested in this question when an experiment with a small sample size resulted in an outcome that supported their argument.
|
This is not a very good way to put it.Typically what happens is posters like OP provide real in-game data for analysis. Other posters who dislike the implications of the data will claim the sample size is too small. It's basically a "god of the gaps" argument. You can throw away all data you disagree with, because there is always a chance the data is wrong in some manner.
I think most people understand there is always a risk of the sample size tainting any conclusions drawn. However, most people who claim a sample size is too small do not provide a larger sample size themselves.
So we end up in a conundrum: Do you trust real data that may be flawed due to sample size? Or do you prefer trusting detractors of the data who merely have anecdotes and no data themselves?
Personally I prefer to trust data over anecdotes generally speaking. This is especially true on P99. People have memories from Everquest live, current P99, and previous P99 patches. It's always possible for anecdotes to be from live or a previous p99 patch, rather than how P99 currently works today.