--hXth9cGL35Nvpk4x Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-Transfer-Encoding: quoted-printable On Sun, Sep 23, 2012 at 02:37:48AM +0200, Mariusz Gromada wrote: > W dniu 2012-09-22 21:53, Pawel Jakub Dawidek pisze: > > Mariusz, can you confirm my findings?=20 >=20 > Pawel, >=20 > Your conclusions can be easily confirmed by shape analysis of the EDF.=20 > Usually maximum quantile difference (called D-statistic) gives you a=20 > kind of overview, function shape gives you a strong feeling, p-value=20 > gives you a formal proof. > D-statistic values (your data): >=20 > 6bit: 0.33% > 7bit: 0.29% > 8bit: 0.27% > 9bit: 0.21% > 10bit: 6.34% > 11bit: 19.07% > 12bit: 54.80% >=20 > What I would say: increasing the number of bits from 6 to 9 does not=20 > affect distribution "uniformity", reaching the tenth bit results in=20 > sudden increase in the difference measure - the more bits, the more=20 > difference is observed. Distribution shape analysis for the 10th bit=20 > shows non-linear function. Lack of "randomness" in the quntile=20 > difference curve - chart shows completely lack of noise (pure=20 > functional relation). These are very strong indicators that starting=20 > from 10th bit distribution was changed and is no longer uniform. >=20 > To formally confirm above conclusion for i.e. 5% significance level,=20 > which means that confidence level is 95%, I need some extra data=20 > regarding sample sizes. Please pass to me number of collected=20 > observations in each 6-12 bit experiment. Total number of observations was 162833. --=20 Pawel Jakub Dawidek http://www.wheelsystems.com FreeBSD committer http://www.FreeBSD.org Am I Evil? Yes, I Am! http://tupytaj.pl --hXth9cGL35Nvpk4x Content-Type: application/pgp-signature -----BEGIN PGP SIGNATURE----- Version: GnuPG v2.0.19 (FreeBSD) iEYEARECAAYFAlBfJ/IACgkQForvXbEpPzQJ+wCbBzLCJZkjhz6vQr0MuBiXXEqT HiIAnj9DLk6BvR+JiGmlUOviNaKY5Rhk =DrJs -----END PGP SIGNATURE----- --hXth9cGL35Nvpk4x--