CodeCogs

Generates random numbers following a standard normal distribution.

You're viewing an older version of this page (#236). View the current version.

View versions (1)

Interface

#include <codecogs/statistics/distributions/continuous/normal/randomsample.h>

using namespace Statistics::Distributions::Continuous::Normal;

RandomSample(double s = 0.65234) : Stats::Random::Mersenne(s)
~RandomSample()
double genReal()
double sample(double seed=0)

Overview

The general formula for the probability density function of the normal distribution is

$f(x) = \frac{ \mathrm{e} ^ {- (x - \mu) ^ 2 / (2 \sigma ^ 2)}}{\sigma \sqrt{2 \pi}}$

(1)

where $\mu$ is the <em>location parameter</em> and $\sigma$ is the <em>scale parameter</em>. The case where $\mu = 0$ and $\sigma = 1$ is called the standard normal distribution. Therefore the density of this particular distribution, which we also use with this random number generator is

$f(x) = \frac{\mathrm{e} ^ {- x ^ 2 / 2}}{ \sqrt{2 \pi} }$

(2)

Using this class, the diagram below is generated from two distinct sequences of 1000 random numbers. Each pair of numbers are plotted against each other, to illustrate the standard normal behaviour of this non-uniform random number generator.

Speed:

The average running time for generating 100,000,000 random numbers using this class on a 750MHz microprocessor is 37 seconds.

References

NIST/SEMATECH e-Handbook of Statistical Methods, http://www.itl.nist.gov/div898/handbook/
The Newran03 random number generator library of Robert Davies, http://www.robertnz.net/nr03doc.htm

Example 1

The following example displays 40 random floating point numbers from a standard normal distribution. It uses two different generators to achieve this. The first generator uses a particular value to initialize the seed, while the second one is using the system timer. Notice that it was necessary to divide the timer with the MERSENNEDIV value in order to keep the seed in the (0, 1) interval. Since the seed of the first generator is never changed, the first 20 numbers will always remain the same. However since the second generator is initialized via the system timer, the next 20 numbers will obviously vary with each execution of the program.

#include <iostream>
#include <time.h>
#include <codecogs/statistics/distributions/continuous/normal/randomsample.h>
using namespace std;

int main() 
{
    Stats::Dists::Continuous::Normal::RandomSample A(0.335);
    Stats::Dists::Continuous::Normal::RandomSample B(time(0) / MERSENNEDIV);

    for (int i = 0; i < 20; ++i)
        cout << A.genReal() << endl;
    cout << endl;

    for (int i = 0; i < 20; ++i)
        cout << B.genReal() << endl;
    return 0;
}

Below you will find 20 numbers corresponding to the output of the first generator :

Members of RandomSample

CLASS METHOD

RandomSample

Constructor that sets up the class variables and initializes the associated random number generator with the given seed.

Parameters

Default value = 0.65234

CLASS METHOD

RandomSample

CLASS METHOD

genReal

CLASS METHOD

sample

This function is a simple wrapper around the randomsample class provided in this module. It uses a static to keep a single instance of this class, so that each call to this function returns a new random number. As a result this function is not necessarily thread safe, in the sense that with identical initial seed, the sequence of random numbers may differ on a multitasking or multi threaded system.

The seed is only set on the first call to this function. Thereafter this parameter is ignored. If you do no want to set the seed, then we suggest you use the system clock the first time you call this function, i.e.

#include <time.h>
...
sample(time(0) / MERSENNEDIV);

If you require more advance behaviour, we strongly recommend that directly use the underlying class randomsample that is provided with this module.

Parameters

seed

sets the initial seed for the random generator. Only used in the first call to this function