The __General distribution__ is the most flexible of all of the continuous distribution functions. It enables the analyst and expert to tailor the shape of the distribution to reflect, as closely as possible, the opinion of the expert. In Crystal Ball the General distribution can be constructed using the Custom Distribution. It requires two arrays of data, *{x _{i}} and*

*{p*where

_{i}})*{x*is an array of

_{i}}*x*-values with probability densities

*{p*and where the distribution falls between x(1) and x(n). The

_{i}}*{p*values are not constrained to give an area under the curve of 1 since the Crystal Ball software recalibrates the probability scale. The figure below shows a General distribution, using the following data: ({4,7,9,11,15},{0,2,3,0.5,0}).

_{i}}Use of the General distribution is explained in more depth further when discussing eliciting distributions of the expert opinion.