Comment on "Algorithm for normal random numbers"

M I J  Probert

Comment on "Algorithm for normal random numbers"

Physics

Research output: Contribution to journal › Letter › peer-review

Abstract

We have performed some simple statistical tests on the recently proposed algorithm for generating normally distributed random numbers and we find that it has some serious flaws with regard to practical application. In particular, we find that there is a statistically significant difference between the sample mean and that expected when using the original authors' recommended parameters of the algorithm. Only by significantly increasing these parameters, at the cost of considerable extra computational effort, do we get satisfactory statistics.

Original language	English
Article number	058701
Number of pages	2
Journal	Physical Review E
Volume	6305
Issue number	5
Publication status	Published - May 2001

Cite this

@article{00794d3826674e94a69efa1c77584055,

title = "Comment on {"}Algorithm for normal random numbers{"}",

abstract = "We have performed some simple statistical tests on the recently proposed algorithm for generating normally distributed random numbers and we find that it has some serious flaws with regard to practical application. In particular, we find that there is a statistically significant difference between the sample mean and that expected when using the original authors' recommended parameters of the algorithm. Only by significantly increasing these parameters, at the cost of considerable extra computational effort, do we get satisfactory statistics.",

author = "Probert, {M I J}",

year = "2001",

month = may,

language = "English",

volume = "6305",

journal = "Physical Review E",

issn = "1539-3755",

publisher = "American Physical Society",

number = "5",

}

TY - JOUR

T1 - Comment on "Algorithm for normal random numbers"

AU - Probert, M I J

PY - 2001/5

Y1 - 2001/5

N2 - We have performed some simple statistical tests on the recently proposed algorithm for generating normally distributed random numbers and we find that it has some serious flaws with regard to practical application. In particular, we find that there is a statistically significant difference between the sample mean and that expected when using the original authors' recommended parameters of the algorithm. Only by significantly increasing these parameters, at the cost of considerable extra computational effort, do we get satisfactory statistics.

AB - We have performed some simple statistical tests on the recently proposed algorithm for generating normally distributed random numbers and we find that it has some serious flaws with regard to practical application. In particular, we find that there is a statistically significant difference between the sample mean and that expected when using the original authors' recommended parameters of the algorithm. Only by significantly increasing these parameters, at the cost of considerable extra computational effort, do we get satisfactory statistics.

M3 - Letter

SN - 1539-3755

VL - 6305

JO - Physical Review E

JF - Physical Review E

IS - 5

M1 - 058701

ER -