Re: [Enigma-devel] Scores - which values make sense

[Andreas Lochmann]

Hello,

you should also use the harmonic average instead
of the arithmetic one:
 harm.avg. = N / (sum_{j=1..N} 1/t_j) )
It weights small times with a greater weight, and
is somewhat canonical when dealing with speeds:
If you first need t_1 and then t_2 for the same distance,
then the time related to the standard-averaged velocity
is just the harmonic average of t_1 and t_2.

We could ask the players from mag-heut.net to send
us their complete 0.92-enigmarc2's. However, this
won't work for most of the new levels.

Greetings,
Andreas


Erich Schubert wrote:

> Hello Ronald,
>  
>
> > An algorithm for PAR calculation (4)?
> >    
>
> average of top 50% of submitted scores?
> The 10% quantile score? (i.e. score such that 10% of submissions are better)?
>
> best regards,
> Erich Schubert
> --
>    erich@(mucl.de|debian.org)      --      GPG Key ID: 4B3A135C    (o_
>  To understand recursion you first need to understand recursion.   //\
>  Wo befreundete Wege zusammenlaufen, da sieht die ganze Welt für   V_/_
>        eine Stunde wie eine Heimat aus. --- Herrmann Hesse
>
>
> _______________________________________________
> Enigma-devel mailing list
> address@hidden
> http://lists.nongnu.org/mailman/listinfo/enigma-devel
>
>