Posts Tagged ‘statistical outlier’

June surprises at RoboCrush

Thursday, June 25th, 2009

It’s been an alarmingly fast past June and we blew right past Fathers’ day without a nod.

New models of aggregate trend analysis are unfolding from our initial beta testing and we’ve garnered a bit of underground media interest.

We are attempting to analyze the effects of various variable constraints when applied to model overlays across market sectors. So far the results are ambiguous and disambiguation doesn’t seem possible just through additional testing. It looks like we’ll need a radical refinement of how we approach the modeling aspects in this area.

What we initially thought were statistical outliers look as if they may not be. So we are reexamining our techniques for determining statistical outliers since obviously until we get that right it doesn’t make any sense to start any type of root cause analysis.