Redial Basis Functions
are a large class of approximating functions, computed as a linear combination of non-linear functions of the distances to a set of centres:
 
 
     
 
  Rank (of a matrix)
The number of linearly independent rows columns.
 
 
     
 
  Regularization
A class of methods of avoiding over-fitting to the training set by penalizing the fit by a measure of 'smoothness' of the fitted function.
 
 
     
 
  Resistant Methods
are designed to be little affected by outliers. For example, the median is much resistant than the mean.
 
 
     
 
  R Factor Analysis
Analyzes relationships among variables to identify groups of variables forming latent dimension (factors).
 
 
     
 
  Reliability
Extent to which a variables or set of variables is consistent in what it is intended to measure. If multiple measurements are taken, reliable measures will all be very consistent in their values. If differs from validity in that it does not relate to what should be measured, but instead to how it is measured.
 
 
     
 
  Reverse Scoring
Process of reversing the scores of a variable, which retaining the distributional characteristics, to change the relationships (correlations) between two variables. Used in summated scale construction to avoid a ¡°canceling out¡± between variables with positive and negative factor loadings on the same factor.
 
 
     
 
  Ridge Regression
See shrinkage methods.
 
 
     
 
  Risk
of a classifier is the expected loss from using it. The bayes risk is the lowest attainable risk (using these features).
 
 
     
 
  Robust Methods
are designed to be resistant, and also to have high efficiency near some target distribution. For example, although the median is resistant, it is inefficient compared to a trimmed mean.