Thanks, I see I have my homework cut out for me. Since these metrics are Oracle metrics, I am pretty familiar by sight as to which ones may have correlation. All I need is to put the 10-15 charts of the 300 all on 2-3 pages so I can spot them easily. If it turns out that 5 really were not very good matches, I will spot it visually right away. JL's demonstration at Hotsos 06 of how various SYSSTATS should be read together made me think about this a bit and I am looking for ways to see correlation easily in areas I would not have thought to look. The charts however include OS stats, waits and a ton of other things. - Ethan On 4/21/06, Mark W. Farnham <mwf@xxxxxxxx> wrote: > > This is called piecewise multiple linear regression. A net search will > find you some references to using data mining in this regard. In your case > time is the relevant smoothing spline. > > >