Programmatically Computing the Area under the Normal Curve

In my last blog entry I presented a function called ChiSquare which accepts as input a computed Chi-square value and its associated degrees of freedom, and returns the probability that the Chi-square value occurred by chance. Such a function can be used to write a Chi-square test method, or a G test method. I forgot to mention that the ChiSquare method, which was an implementation of ACM algorithm 299, calls and uses a helper function named Gauss. The Gauss function accepts a standard normal z value and returns the probability under the Normal curve from –infinity to z. So for example, if z = 0.0 then Gauss(z) returns 0.5000, or Gauss(1.645) returns 0.9500 (1.645 is the critical z-value for a 0.05 significance level). My Gauss function is based on ACM algorithm 209 and written in C# and is:

public static double Gauss(double z)
{
// input = z-value (-inf to +inf)
// output = p under Normal curve from -inf to z
// e.g., if z = 0.0, function returns 0.5000
// ACM Algorithm #209
double y; // 209 scratch variable
double p; // result. called ‘z’ in 209
double w; // 209 scratch variable

if (z == 0.0)
    p = 0.0;
else
{
    y = Math.Abs(z) / 2;
    if (y >= 3.0)
    {
      p = 1.0;
    }
    else if (y < 1.0)
    {
      w = y * y;
      p = ((((((((0.000124818987 * w
        – 0.001075204047) * w + 0.005198775019) * w
        – 0.019198292004) * w + 0.059054035642) * w
        – 0.151968751364) * w + 0.319152932694) * w
        – 0.531923007300) * w + 0.797884560593) * y * 2.0;
    }
    else
    {
      y = y – 2.0;
      p = (((((((((((((-0.000045255659 * y
        + 0.000152529290) * y – 0.000019538132) * y
        – 0.000676904986) * y + 0.001390604284) * y
        – 0.000794620820) * y – 0.002034254874) * y
        + 0.006549791214) * y – 0.010557625006) * y
        + 0.011630447319) * y – 0.009279453341) * y
        + 0.005353579108) * y – 0.002141268741) * y
        + 0.000535310849) * y + 0.999936657524;
    }
}