   Rundom BC 1.0 performs the Box-Cox (BC stands for 'Box-Cox')
   data transformation in several settings.

   It uses an iterative procedure for estimating the best transformation
   to normality (one or more samples simultanously) within the family
   of power transformations. It can be also used when not only 
   normality but also homogeneity of variances is important.
   Transformations are defined for positive data values only.
   If some of them are negative - add a constant to all data values.
   Accompanying statistical tests (Shapiro-Wilk's and Brown-Forsythe's tests)
   do not use randomization techniques! Furthermore, they use data values
   before rounding - this is also true for computations of Pearson's r!
   - for more details see
   Sokal R. R. & Rohlf F.J., 1995. Biometry. The principles and practice
   of statistics in biological research. W.H. Freeman and Company, New York.
   
   After some modifications of the procedure (but not the transformation itself),
   it is possible to use it to find the transformation of the X variable that improves
   the linear fit of Y against X.
   - for more details see
   Engineering Statistics Handbook 
   (online; http://www.itl.nist.gov/div898/handbook/index.htm)

   Rundom BC 1.0 can export and import Rundom Projects 2.0 D-Grid data files.
