type TPercentileMethod = ( pctMethodNPlus=0, pctMethodNMinus=1, pctMethodClosestN=2, pctMethodEDF=3, pctMethodEDFAve=4 );
Defines methods for calculatating percentile.
Values
| Name | Description |
|---|---|
| pctMethodClosestN | The 100pth percentile is computed as Zp = X[k] where k+1 equals the integer that is closest to np and X[k-1] is the kth observation when the data are sorted from lowest to highest. |
| pctMethodEDF | The 100pth percentile is computed as Zp = X[k] where k+1 equals the integer part of np if np is exactly an integer or the integer part of np+1 if np is not exactly an integer. X[k-1] is the kth observation when the data are sorted from lowest to highest. Note that EDF stands for empirical distribution function. |
| pctMethodEDFAve | The 100pth percentile is computed as Zp = 0.5*(X[k1] + X[k2])y where k1 and k2 are defined as follows: If np is an integer, k1=k2=np. If np is not exactly an integer, k1 equals the integer part of np and k2 = k1+1. X[k-1] is the kth observation when the data are sorted from lowest to highest. Note that EDF stands for empirical distribution function. |
| pctMethodNMinus | The 100pth percentile is computed as Zp = (1-d)X[k] + dX[k+1] where k+1 equals the integer part of P(n-1)+1, d is the fractional part of p(n+1), and X[k-1] is the kth observation when the data are sorted from lowest to highest. |
| pctMethodNPlus | The 100pth percentile is computed as Zp = (1-d)X[k] + dX[k+1] where k+1 equals the integer part of P(n+1), d is the fractional part of p(n+1), and X[k-1] is the kth observation when the data are sorted from lowest to highest. |