[mathcad] RE: rgeom mistake?

Author: Oakley, Philip SELEX UK Posted: Wed, 11 Jan 2006 17:15:26 +0000

>From V11 manual.You can access numerical recipes (Press et al) on the web. Sorry about the confusion over the zero - thought you meant it returned zero where a real>0 was expected. Also just because the particular experiment can have zero trials doesn't mean a distribution can't include a coefficient 'zero' [one could win by default..]

Philip

rgeom Random Numbers

Syntax rgeom(m, p)

Description Returns a vector of m random numbers having the geometric distribution.

Arguments

m integer, m > 0

p real number, 0 <p <1

Algorithm Inverse cumulative density method (Press et al., 1992)

See also rnd

From: Oakley, Philip (SELEX) (UK)
Sent: 11 January 2006 16:49
To: Mathcad Discussion List
Subject: [mathcad] RE: rgeom mistake?

Have you checked your zero tolerance? try multiplying the result by 10^300 (or suitable large number) to see if it just 'very small'
Philip

From: Marc Artzrouni "mailto:marc.artzrouni"
Sent: 11 January 2006 15:26
To: Mathcad Discussion List
Subject: [mathcad] rgeom mistake?

*** WARNING ***

This mail has originated outside your organization,
either from an external partner or the Global Internet.
Keep this in mind if you answer this message.

Hi:
When using rgeom to simulate the geometric random variable G I have values of 0 - which isn't possible for the "trial number
on which the first success occurs". The Help file (and my 2001i manual) have p(1-p)^k for the probability
of G=k. An exponent k explains why G can indeed by 0 - however every probability textbook I check
tells me the exponent is k-1, not k, with a smallest possible value of G equal to 1 and not 0.
Can anyone confirm that this is a mistake, and let me know whether it's been fixed in
more recent versions ?
Many thanks

Marc Artzrouni

Marc Artzrouni

Département de Mathématiques (IPRA)

Université de Pau - BP 1155

64013 Pau Cedex

FRANCE

Home page/page perso:

http://www.univ-pau.fr/~artzroun/

**********************************

tel: + 33 - (0)5 59 40 75 50

fax: + 33 - (0)5 59 40 75 55

e-mail: "marc.artzrouni"

**********************************

********************************************************************
This email and any attachments are confidential to the intended
recipient and may also be privileged. If you are not the intended
recipient please delete it from your system and notify the sender.
You should not copy it or use it for any purpose nor disclose or
distribute its contents to any other person.
********************************************************************

********************************************************************
This email and any attachments are confidential to the intended
recipient and may also be privileged. If you are not the intended
recipient please delete it from your system and notify the sender.
You should not copy it or use it for any purpose nor disclose or
distribute its contents to any other person.
********************************************************************

[View Complete Thread]

Previous by date: [mathcad] DSP method, Mark Smith
Next by date: [mathcad] Re: DSP method, David Burton
Previous thread: [mathcad] RE: rgeom mistake?, Oakley, Philip SELEX UK
Next thread: [mathcad] Re: DSP method, David Burton

Ready to buy?

For more pricing information:
Visit our webstore, call us on +1 800 724 8380 or email us at info@adeptscience.com

Featured Downloads

Mathcad 14 demo

Mathcad 14 Brochure

Mathcad or Excel?

Mathcad Customer Story: Man B&W Diesel

Mathcad Customer Story: Stork Fokker Aerospace

Mathcad White Paper - Moving beyond the limitations of spreadsheets

Product Reviews

"Our work ranges from complex medical imaging research to large-scale mapping and diagrams and we need a tool that is able to handle anything we investigate. With Mathcad, we are able to manipulate and analyse our data quickly while at the same time documenting our work, for sharing and publication. We also use it for pilot studies conducted in support of research grant applications. It is an end-to-end tool for research and development."
Dr. Kenneth Castleman, President of Advanced Digital Imaging Research (ADIR), Houston, Texas

"Mathcad is an integral product for my work... With Mathcad, itís easy to disseminate design calculations because the documents look like real math. Thereís very little I canít do in Mathcad. The main benefits come from the format, which resemble a typed set of calculations. These programs are easier to develop by engineers and easier for others to follow and review since the logic is expressed in a familiar manner. The format is what places Mathcad head and shoulders above other programs of a similar function."
Andre Pavlov, Structural Engineer, Florida Department of Transportation