This program calculates user-specified percentiles of a data set. A percentile is the value of a variable below which a certain percent of observations fall. In other words, 75% of the values in a data set fall below the 75th percentile of the data. Computing percentiles is really nothing more than counting in a sorted input array. A box-and-whisker plot usually will display the 25th, 50th, and 75th percentiles.
A commercial version of this program, containing a DIMENSION keyword, can be purchased from the Coyote Store. The DIMENSION keyword allows the user to calculate the percentiles over a particular dimension of a multi-dimensional data set.
The return value is either a scalar or vector of data values corresponding to
the number of percentiles asked for with the
Percentiles keyword, or a -1 if
there is an error in the program.
- data in required
The data from which percentiles are desired. A vector or an array.
- Percentiles in optional type=float
Set this keyword to a scalar or vector of values between 0.0 and 1.0 to indicate the percentile desired. A value of 0.5 indicates the 50th percentile. Default value is [0.25, 0.50, 0.75].
To return percentile values for 0.25, 0.50, and 0.75 of a data set:
IDL> data = Randomu(3L, 100) * 100 IDL> Print, cgPercentiles(data, Percentiles=[0.25, 0.5, 0.75]) 27.4920 45.3172 69.3138
FANNING SOFTWARE CONSULTING:
David W. Fanning 1645 Sheely Drive Fort Collins, CO 80526 USA Phone: 970-221-0438 E-mail: email@example.com Coyote's Guide to IDL Programming: http://www.idlcoyote.com
Copyright (c) 2013, Fanning Software Consulting, Inc.
Written, 3 June 2013 by David W. Fanning.
|Modification date:||Fri Mar 27 11:07:36 2015|