Wichmann, B. A. and I. D. Hill (1982). An efficient and portable pseudo-random number generator. Applied Statistics, Vol. 31, pp. 188--190. See also corrections and remarks in the same journal by Wichmann and Hill, Vol. 33 (1984) p. 123; McLeod Vol. 34 (1985) pp. 198--200; Zeisel Vol. 35 (1986) p. 89.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....so there is little reason to use these generators. 3. 4 Combined Generators Combining two different generators has been shown (both theoretically and empirically) to produce an improved quality generator in many circumstances [2, 32, 6, 42] Based on an algorithm introduced by Wichmann and Hill [43], L Ecuyer [32] has shown how to additively combine two different 32 bit LCGs to produce a generator that passes all known statistical tests and has a long period of around 10 18 , thus overcoming the major drawbacks of standard 32 bit LCGs. This has been implemented in a program known as RANECU ....

B.A. Wichmann and I.D. Hill, An efficient and portable pseudorandom number generator, Appl. Statist. 31, 188 (1982).

....pair (n,m) n=30 and 50 and m=1, 15, n=100 and m=1, 30, n=200 and m=1, 50, and n=500 and m=5, 10, 15, 20, 30 and 40, one million zero mean unit variance normal white noise were generated. Uniform (0,1) pseudo random independent deviates were computed by using the algorithm AS183 (Wichmann and Hill, 1982). This algorithm has cycle 2.7810 13 . For each combination (n,m) the seeds of the three independent congruential generators have been restated to 12347, 12373 and 12377 (to 25539, 17415 and 9851 for n=500) Then the inverse function method as implemented in AS111 (Beasley and Springer, 1977) ....

Wichmann, B. A. and Hill, I. D. (1982). "An efficient and portable pseudorandom number generator," Applied Statistics, 31, 188-190.

....sample of sixty image blocks, which includes the examples in section 5.4. The sample consists of twenty blocks from each of the test images; the locations of the blocks are the same for all three images, and are chosen from a uniform distribution using the Wichmann and Hill random number generator [32]. Since the images contain widely varying subject matter, we expect this sample to include blocks with differing characteristics. The minimum size of the blocks is eight pixels square: we find that with smaller blocks the value of d rms does not vary sufficiently to give a meaningful result. We ....

Wichmann, B. A. and Hill, I. D.: "An efficient and portable pseudo-random number generator" Applied Statistics 31:188-190 (1982)

....from the diagram on the right of Figure 3.20. The areas in the diagram corresponding to Sections 1 and 4 are each equal in size to one quarter of the total area of the square. 6 Error amounts here and in subsequent sections were generated using an implementation of the Wichmann Hill algorithm [Wichmann and Hill, 1982] . 26 Area Overestimate Underestimate 1 #, #, # 2 #, # # 3 # #, # 4 #, #, # 5 # #, # 6 #, # # Table 3.1: The visual angles are either under or overestimated in each of the 6 areas of Figure 3.20. Angle # is the angle from A to B with vertex V. Angle # is the angle from B to C with ....

B. A. Wichmann and I. D. Hill. An efficient and portable pseudorandom number generator. Applied Statistics, 31:188--190, 1982.

....the computation, but there is a limit to how much you could increase, since multi precision arithmetic is very slow. This limitation suggest the possibility of combining two LCGs. A combination of two LCG generators is advantageous since it provides a longer period and better randomness properties [5, 8, 10]. This combination can be achieved by simply adding the numbers produced by the two LCGs, modulo the smallest value of m for the two generators. It is this kind of combined generator that is used for the parallel random number generator presented here. The maximum period of a linear congruential ....

B.A. Wichmann and I.D. Hill, An efficient and portable pseudorandom number generator, Appl. Stat. 31, 188 (1982).

....as an abbreviation for the number of non zero wavelet coefficients for the relevant deformation. The algorithms were written in C and compiled and run on a Sun UltraSparc. For Simulated Annealing the Wichmann and Hill random number generator was used with a different seed for each deformation (Wichmann Hill, 1982). 7.1 ICM Algorithm Table 1 shows the results from the ICM algorithm for different values of ff. The mean CPU time taken to run this algorithm was 8 minutes 45 seconds. As ff increases, the SSE increases but fewer coefficients are used to define f . When ff 0:5 the algorithm finds an exact ....

Wichmann, B.A., & Hill, I.D. 1982. An Efficient and Portable Pseudo-Random Number Generator. Journal of the Royal Statistical Society, Series C, 31, 188--190.

....new generators in addition to the original lagged Fibonacci generator are now available. The generators are identified by an integer: 0 The original XLISP STAT generator, Marsaglia s portable generator from CMLIB. This is a lagged Fibonacci generator. 1 L Ecuyer s [5] version of the Wichmann Hill [9] generator, also used in Bratley, Fox and Schrage, 1, program UNIFL] 2 Marsaglia s Super Duper, as used in S. 3 Combined Tausworthe generator of Tezuka and L Ecuyer [8] The default generator is generator 1. Generator 0 has a period of 2 32 . All three new generators have periods on the order ....

Wichmann, B. A. and Hill, I. D. (1982) "An efficient and portable pseudo-random number generator, " (Corr: V33 p123), Applied Statistics 31, 188--190.

....as an abbreviation for the number of non zero wavelet coefficients for the relevant deformation. The algorithms were written in C and compiled and run on a Sun UltraSparc. For Simulated Annealing the Wichmann Hill random number generator was used with a different seed for each deformation (Wichmann Hill, 1982). 7.1 ICM Algorithm Table 1 shows the results from the ICM algorithm for different values of ff. Convergence always occurred within seven iterations and the mean CPU time taken to run this algorithm was 8 minutes 45 seconds. As ff increases, the SSE increases but fewer coefficients are used to ....

Wichmann, B.A., & Hill, I.D. 1982. An Efficient and Portable Pseudo-Random Number Generator.

....normal data were generated using the Box Muller method (see Ripley [65] All the experiments were performed twice using two uniform pseudo random number generators based on completely different algorithms. The first generator used was the well known Wichmann and Hill algorithm (Wichmann and Hill [79]) the second was an inversive non linear congruential generator described in Eichenauer and Lehn [21] see also Eichenauer Herrman [22] The results of this investigation were very similar when using either random number generator. For each of the switch point experiments we drew 1000 ....

B. A. Wichmann and J. D. Hill. Algorithm AS183. An efficient and portable pseudorandom number generator. Appl. Statist., 31:188--190, 1982. See also 33:p123.

.... 31 Gamma 1 of Lewis, Goodman, and Miller [4] and both the add with carry and subtract with borrow Fibonacci generators of Marsaglia and Zaman [5] Other algorithms that would be expected to pass, but which have not been explicitly tested, include the combination generators of Wichmann and Hill [6] and L Ecuyer [3] and the x 2 mod N generators of Blum, Blum, and Shub [1] In order to allow users to assess the suitability of the algorithm for their particular application, the implementation must describe the algorithm it uses and must document some of its properties. The predefined ....

B. A. Wichmann and I. D. Hill. An Efficient and Portable Pseudo-Random Number Generator. Applied Statistics 31:188--190, 1982.

No context found.

Wichmann, B. A. and I. D. Hill (1982). An efficient and portable pseudo-random number generator. Applied Statistics, Vol. 31, pp. 188--190. See also corrections and remarks in the same journal by Wichmann and Hill, Vol. 33 (1984) p. 123; McLeod Vol. 34 (1985) pp. 198--200; Zeisel Vol. 35 (1986) p. 89.

No context found.

B. A. Wichmann and I. D. Hill. "An Efficient and Portable Pseudo-Random Number Generator". Applied Statistics 31:188-190, 1982.

No context found.

Wichmann, B.A., and I.D. Hill, 1982, "An Efficient and Portable Pseudo-random Number Generator," Applied Statistics 31: 188-190.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC