Subjective Beta distribution | Vose Software

Subjective Beta distribution


Format: BetaSubj(mode, mean, min, max)

 

Uses

The BetaSubj distribution is highly flexible in shape and bounded, so it can be used for attempting to fit to a data set for a bounded variable. In ModelRisk we offer the option of fitting the BetaSubj with known bounds (our general recommendation) or without. The BetaSubj and the Beta4 distribution are the same distribution but with different parameterizations. However, the parameters of the BetaSubj are more intuitive.

An occasional use of the BetaSubj distribution is for expert (subjective) estimates: the mode, minimum and maximum are intuitive parameters to specify in a subjective estimate. The mean is less intuitive, but can be thought of as the balance point of a distribution. Closely related alternatives for subjective estimates are the PERT and Modified PERT distributions.

If the mode is less than the mean, the distribution is right skewed and vice versa. Certain combinations of mode and mean are not possible. Beta Subjective functions in ModelRisk will return an error message when incompatible mode and mean values are encountered.

ModelRisk functions added to Microsoft Excel for the Subjective Beta distribution

VoseBetaSubj generates random values from this distribution for Monte Carlo simulation, or calculates a percentile if used with a U parameter.

VoseBetaSubjObject constructs a distribution object for this distribution.

VoseBetaSubjProb returns the probability density or cumulative distribution function for this distribution.

VoseBetaSubjProb10 returns the log10 of the probability density or cumulative distribution function.

VoseBetaSubjFit generates values from this distribution fitted to data, or calculates a percentile from the fitted distribution.

VoseBetaSubjFitObject constructs a distribution object of this distribution fitted to data.

VoseBetaSubjFitP returns the parameters of this distribution fitted to data.

Beta-subjective distribution equations

 

Navigation