|
One thing about testing on a single variable experiment, if only two tests are done on each variable (i.e. once on, once off), then one does not know the inherent variability of system. In short, what is the standard deviation of the experiment? Mathematically, this can be represented as
Individual Result = Average + Main Effect of A + Standard Deviation.
If the standard deviation is larger than the one variable’s main effect, then many other factors are at play.
The best test results, the “On & Off” should happen several times and in a random fashion (i.e. On, Off, Off, Off, On, Off, On, On, Off, On). Of course the more samples the better. Then the data can be statistically analyzed to determine the magnitude of the single variable and the magnitude of the inherent variability of the system before any conclusions can be drawn.
__________________
'75 914-6 3.2 (Track Car)
'81 SC 3.6 (Beast)
'993 Cab (Almost Done Restoring)
|