Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]


Groups > comp.soft-sys.math.mathematica > #16765

Re: Bug with ProbabilityDistribution

From Barrie Stokes <barrie.stokes@newcastle.edu.au>
Newsgroups comp.soft-sys.math.mathematica
Subject Re: Bug with ProbabilityDistribution
Date 2014-04-10 07:09 +0000
Message-ID <li5g41$3lj$1@smc.vnet.net> (permalink)
Organization Time-Warner Telecom

Show all headers | View raw


Hi Charles

Writing

scriptD = ProbabilityDistribution[
  		Piecewise[{{0, x1 == 1 && x2 == 1}, {1/2, x1 == 1 && x2 == 0}, {0,
     x1 == 0 && x2 == 1}, {1/2, x1 == 0 && x2 == 0}}],
  		{x1, 0, 1, 1}, {x2, 0, 1, 1}
  	],


PDF[  scriptD, {x, y}]  looks interesting, and


CDF[  scriptD, {x, y}]  gives Undefined.



OTOH,

Mean[scriptD ] gives (1=8E2, 0)


And

Variance[scriptD ] gives {1=8E4, 0}


whereas


Covariance[scriptD ] doesn't work.

DiscretePlot3D[ PDF[  scriptD, {x, y}], {x, -2, 2}, {y, -2, 2},
 AxesLabel -> {"x", "y", "PDF"} ]


Corroborates

PDF[  scriptD, {1, 1}]
PDF[  scriptD, {0, 1}]
PDF[  scriptD, {1, 0}]
PDF[  scriptD, {0, 0}]


If you look closely.

 I note that there is documentation in V.9 for Discrete Univariate
Distributions, but I don't see anything under "Discrete Multivariate
Distributions"

Hmmm.

Cheers

Barrie






On 9/04/14 6:14 PM, "CHARLES GILLINGHAM" <cgillingham1@me.com> wrote:

>Evaluate this:
>
>	ProbabilityDistribution[
> 		Piecewise[{{0, x1 == 1 && x2 == 1}, {1/2, x1 == 1 && x2 == 0}, {0, x1
>== 0 && x2 == 1}, {1/2, x1 == 0 && x2 == 0}}],
>		 {x1, 0, 1, 1}, {x2, 0, 1, 1}
>	 ]
>	PDF[%][{1, 1}]
>
>And you get:
>
>	Undefined
>
>But the probability is obviously 0
>
>Is there something I am misunderstanding about how simple Boolean
>probability distributions should be set up?
>
>Thanks.
>
>
>
>

Back to comp.soft-sys.math.mathematica | Previous | Next | Find similar


Thread

Re: Bug with ProbabilityDistribution Barrie Stokes <barrie.stokes@newcastle.edu.au> - 2014-04-10 07:09 +0000

csiph-web