Difference between revisions of "Bernoulli distribution"

Line 4: Line 4:
 
= Bernoulli( P ) =
 
= Bernoulli( P ) =
  
Creates a discrete probability distribution with probability P of result 1 and probability (1 - P) of result 0. P is a probability value or array of probabilities, each between 0 and 1. The Bernoulli distribution is the same as:
+
Creates a discrete probability distribution with probability P of 1 (True) and probability (1 - P) of 0 (False). P is a probability value or array of probabilities, between 0 and 1. The result is the equivalent to:
 
  If [[Uniform]](0, 1) < P Then 1 Else 0
 
  If [[Uniform]](0, 1) < P Then 1 Else 0
 +
Or even just:
 +
[[Uniform]](0, 1) < P
 
If P is greater than 1, the distribution is made up of all 1’s. If P is less than 0, the distribution is made up of all 0’s.
 
If P is greater than 1, the distribution is made up of all 1’s. If P is less than 0, the distribution is made up of all 0’s.
  
To generate bernoulli values that are independent over indexes In1, In2, and In3, use:
+
To generate an Array of Bernoulli values that are independent over index I, use:
  Bernoulli( P, Over:In1,In2,In3 )
+
Bernoulli(P, Over: I)
 +
You can extend this to an Array with multiple dimensions, as:
 +
  Bernoulli(P, Over: I, J, K)
  
 
= Library =
 
= Library =

Revision as of 18:14, 13 November 2009


Bernoulli( P )

Creates a discrete probability distribution with probability P of 1 (True) and probability (1 - P) of 0 (False). P is a probability value or array of probabilities, between 0 and 1. The result is the equivalent to:

If Uniform(0, 1) < P Then 1 Else 0

Or even just:

Uniform(0, 1) < P

If P is greater than 1, the distribution is made up of all 1’s. If P is less than 0, the distribution is made up of all 0’s.

To generate an Array of Bernoulli values that are independent over index I, use:

Bernoulli(P, Over: I)

You can extend this to an Array with multiple dimensions, as:

Bernoulli(P, Over: I, J, K)

Library

Distributions

See Also

Comments


You are not allowed to post comments.