You can use the PCTLDEF= option to
specify one of five definitions for computing quantile
Let n equal the number of nonmissing values for a
variable, and let x1, x2, ... ,xn represent the ordered
values of the process variable. For the t th percentile, set p =t/100, and
where j is the integer part of np, and
g is the fractional part of np.
np = j + g
The t th percentile (call it y)
can be defined in
five ways, as described in the next five sections.
This uses the weighted average at xnp
where x0 is taken to be x1.
y = (1- g)xj + gxj+1
This uses the observation numbered closest to np
where i is the integer part of np + 1/2.
This uses the empirical distribution function
This uses the weighted average aimed at xp(n+1)
where (n+1)p=j+g, and
where xn+1 is taken to be xn.
y=(1-g)xj + gxj+1
This uses the empirical
distribution function with averaging
Copyright © 1999 by SAS Institute Inc., Cary, NC, USA. All rights reserved.