.Random.seed <- c(rng.kind, n1, n2, ...) save.seed <- .Random.seed RNGkind(kind=NULL)
kind
|
character or NULL. If kind is a character
string, set R's RNG to the kind desired, if it's NULL,
return the currently used RNG.
|
rng.kind
|
integer code in 0:k for the above kind.
|
n1,n2,...
|
integers. See the details for how many are required
(which depends on rng.kind).
|
.Random.seed is an integer vector, containing the
random number generator (RNG) state for random number generation in R.
RNGkind is a more friendly interface to query or set the kind
of RNG in use.
.Random.seed[1] == 0
The seed, .Random.seed[-1] == r[1:3] is an integer vector of
length 3, where each r[i] is in 1:(p[i] - 1), where
p is the length 3 vector of primes,
p = (30269, 30307, 30323).
The Wichmann-Hill generator has a cycle length of
6.9536e12 (= prod(p-1)/4 ), see p.123 of
Applied Statistics (1984) vol.33 which corrects the original article.
.Random.seed[1] == 1
A multiply-with-carry RNG is used, as recommended by George Marsaglia in his post to the mailing list `sci.stat.math' on September 29, 1997. It has a period of > 2^60 and has passed all tests (according to Marsaglia). The seed is two integers (all values allowed).
.Random.seed[1] == 2
Marsaglia's famous Super-Duper from the 70's. This is the original version which does not pass the MTUPLE test of the Diehard battery. It has a period of about 4.6*10^18 for most initial seeds. The seed is two integers (all values allowed for the first seed: the second must be odd).
We use the implementation as by Reeds et al. (1982-'83), with the additional non-0 seed measure (see note below).
The two seeds are the Tausworthe and Congruence long integers,
respectively.
A one-to-one mapping to S's .Random.seed[1:12] is possible
but we will not publish one, not least as this generator is
not exactly the same as that in recent versions of S-PLUS.
— — to be expanded — —
((Planned additions are "Mersenne-Twister", "Knuth-TAOCP" (from TAOCP, Vol.2, 3rd ed.,1997), "Ecuyer-...", "Eichenauer-..."))
Note: If any of .Random.seed[i] (i>1) is set to
0, it will be substituted with 1 in the next call to a
random number generator, such as runif.
.Random.seed is an integer vector whose first
element codes the kind of RNG and therefore is in 0:k
where {k+1} is the number of available RNGs.
.Random.seed[-1] is used as unsigned long
(32 bits at least); in R, whose integers are C's long,
.Random.seed[i] can therefore be negative for i > 1.
RNGkind returns the RNG in use before the call, invisibly
if kind is not NULL.
A. De Matteis and S. Pagnutti (1993). Long-range Correlation Analysis of the Wichmann-Hill Random Number Generator, Statist. Comput., 3, 67-70.
Marsaglia, G. (1997). A random number generator for C. Discussion
paper, posting on usenet newsgroup sci.stat.math.
Marsaglia, G. and Zaman, A. (1994). Some portable very-long-period random number generators. Computers in Physics, 8, 117-121.
runif, rnorm, ....
runif(1); .Random.seed; runif(1); .Random.seed
## If there is no seed, a ``random'' new one is created:
rm(.Random.seed); runif(1); .Random.seed
RNGkind("Wich")# (partial string matching on 'kind')
p.WH <- c(30269, 30307, 30323)
a.WH <- c( 171, 172, 170)
next.WHseed <- function(i.seed = .Random.seed[-1]) (a.WH * i.seed) %% p.WH
my.runif1 <- function(i.seed = .Random.seed)
{ ns <- next.WHseed(i.seed[-1]); sum(ns / p.WH) %% 1 }
## This shows how `runif(.)' works for Wichmann-Hill, using only R functions:
rs <- .Random.seed
(WHs <- next.WHseed(rs[-1]))
u <- runif(1)
all(next.WHseed(rs[-1]) == .Random.seed[-1])
u == my.runif1(rs)
## ----
.Random.seed
ok <- RNGkind()
RNGkind("Super")#matches "Super-Duper"
RNGkind()
.Random.seed # new, corresponding to Super-Duper
## Reset:
RNGkind(ok)