To learn more about EpiX Analytics' work, please visit our modeling applications, white papers, and training schedule.

Page tree

 

Binomial(p,1)      

Yes-No(p)           

Bernoulli equations

Crystal Ball parameter restrictions

 

 

The Bernoulli distribution is a Binomial distribution with n = 1. The Bernoulli distribution returns a 1 with probability p and a zero otherwise. The Bernoulli distribution (also called the Yes/No(p) distribution) can be substituted with the Binomial(p, 1) distribution. Two examples of the Bernoulli(p) distribution are shown below:

 

Uses

The Bernoulli distribution is very useful for modeling a risk event that may or may not occur. The figure below illustrates a model to estimate the impact of a set of risks that may impinge on a project:

 

 

 

The model is explained here. Another model with conditional probabilities is also provided here.

 

The Rademacher distribution has equal probability of returning a value of -1 or 1. Thus:

 

Rademacher() =  2*Bernoulli(0.5) - 1

 

 


  • No labels