I am far from an expert on these subjects, but it covers something which has been intriguing me over the last few days. The Einstein@HOME program is described as follows:
Einstein@Home is a program that uses your computer’s idle time to search for spinning neutron stars (also called pulsars) using data from the LIGO and GEO gravitational wave detectors. Einstein@Home is a World Year of Physics 2005 project supported by the American Physical Society (APS)and by a number of international organizations.
(A bit like Seti@Home but that seems to have lost some popularity of late)
Now this is a nice bit of software which runs from something called the BOINC manager, where you can get to view your current work unit, see stats, visit the forums etc.
The question I have, is about the “user statistics” it shows. As you can see in the screen shots, there is choice of “user total” or “user average” and to me, the two don’t seem to match up. I am led to believe the average is “recent average” rather than a simple (total / days) type. But even so, it seems odd – especially as I have had the software running almost constantly for little or no return in the way of work units.
Any feedback or commentary welcome. Given the steady climb shown by the total figures, the mountain-like averages seem somewhat… odd.
I assumed that the first one was cumulative and the recent averages was a weekly average number. However, that doesn’t hold up because that would mean that the weekly averages were also going up dramatically. Otherwise it is quite difficult to understand. how it gets those dramatic wobbles from tiny fluctuations in teh first chart, but still follows its upward trend.
Did that sound moderately like I knew what I was talking about? No, I didn’t think so either.
There is no end of leeway when it comes to stats. There are always things like Tukey’s hinges you can call on, thus bluffing even other statisticians.
Pingback: Why Dont You Blog? » Stats cant lie
Pingback: Why Dont You Blog?