|
|
Re: Correct way to normalize an rmsd-based distance metric used in
repeated trials of pairs
Posted:
Mar 20, 2012 9:51 AM
|
|
I have started testing the relationship between sample size and
average rmsd in repeated different "real-life" scenario that ae
similar to the artificial scenario used above.
The correlation appears to hover about -0.50, from -0.57 down to -0.40
"in real life", and is never positive. That is, the more trials you
do, the smaller the rmsd.
Assuming these consistently negative but moderate correlations can be
considered "semi-significant", this tells me that the more trials one
does, the more chance there is for each pair of necklaces to fall to
the desktop in a similar way.
But I have no idea if I'm reasoning correctly here - that's why I
asked the question in general.
|
|
