Does a parametric distribution exist that is well known to fit this type of variable?

See also: Fitting distributions to data, Fitting in ModelRisk, Analyzing and using data introduction

Many types of variable have been observed to closely follow specific distribution types without any mathematical rationale being available to explain such close matching. Examples abound with the Normal distribution: the weight of babies and other measures that come from nature which is how the Normal distribution got its name; measurement errors in engineering, variables that are the sum of other variables (e.g. means of samples from a population), etc. They probably come from some Central Limit effect. Variables that are the product of a number of factors tend to look somewhat Lognormal through CLT too. However, there are many other examples for distributions like the Pareto and Rayleigh, some of which we note in the description of each distribution.

If a distribution is known to be a close fit to the type of variable being modelled, usually as a result of published academic work, and you are comfortable with using that distribution for your variable, all that remains is to determine the parameters values.



Monte Carlo simulation in Excel. Learn more


Adding risk and uncertainty to your project schedule. Learn more



For Microsoft Excel

Download your free copy of ModelRisk Basic today. Professional quality risk modeling software and no catches

Download ModelRisk Basic now


For Primavera & Microsoft Project

Download your free copy of Tamara Basic today. Professional quality project risk software and no catches.

Download Tamara Basic now