Binomial

Am 12.05.2011 10:46, schrieb blutack:

Hi, I need to create a function which generates a Binomial random number
without using the rbinom function. Do I need to use the choose function or
am I better just using a sample?
Thanks.

I think I remember other software who generates binomial data with e.g. 
pi=0.7 by

pi <- 0.7
x <- runif(100)>pi
summary(x)

  -- Alex

Am 12.05.2011 10:46, schrieb blutack:

Hi, I need to create a function which generates a Binomial random
number
without using the rbinom function. Do I need to use the choose
function or
am I better just using a sample?
Thanks.

I think I remember other software who generates binomial data
with e.g. pi=0.7 by

pi <- 0.7
x <- runif(100)>pi
summary(x)

  -- Alex

That needs to be the other way round (and perhaps also convert
it to 0/1):

  x <- 1*(runif(100) < pi)

since Prob(runif > pi) = (1 - pi).

Comparison:

  pi <- 0.7
  x <- runif(100)>pi
  x[1:10]
  #  [1] FALSE  TRUE  TRUE FALSE FALSE  TRUE  TRUE  TRUE FALSE FALSE
  sum(x)/100
  # [1] 0.36

  x <- 1*(runif(100) < pi)
  x[1:10]
  # [1] 0 0 1 1 1 1 1 0 1 0
  sum(x)/100
  # [1] 0.62

Ted

--------------------------------------------------------------------
E-Mail: (Ted Harding) <ted.harding at wlandres.net>
Fax-to-email: +44 (0)870 094 0861
Date: 12-May-11                                       Time: 10:21:26
------------------------------ XFMail ------------------------------

Am 12.05.2011 10:46, schrieb blutack:

Hi, I need to create a function which generates a Binomial random  
number
without using the rbinom function. Do I need to use the choose  
function or
am I better just using a sample?
Thanks.

I think I remember other software who generates binomial data with  
e.g. pi=0.7 by

pi <- 0.7

I hope Allan knows this and is just being humorous here,  but for the  
less experienced in the audience ... Choosing a different threshold  
variable name might be less error prone. `pi` is one of few built-in  
constants in R and there may be code that depends on that fact.

 > pi
[1] 3.141593
 > pi <- 0.7
 > pi
[1] 0.7
 > rm(pi)
 > pi
[1] 3.141593

x <- runif(100)>pi
summary(x)

Another method would be:

  x <- sample(c(0,1) , 100, replace=TRUE,  prob=c(0.7, 0.3) )

David Winsemius, MD
West Hartford, CT

An embedded and charset-unspecified text was scrubbed...
Name: not available
URL: <https://stat.ethz.ch/pipermail/r-help/attachments/20110512/3eec51a0/attachment.pl>

Am 12.05.2011 13:19, schrieb Sarah Sanchez:

Dear R helpers,

I am raising one query regarding this "Binomial" thread with the sole intention of learning something more as I understand R forum is an ocean of knowledge.

I was going through all the responses, but wondered that original query was about generating Binomial random numbers while what the R code produced so far generates the Bernoulli Random no.s i.e. 0 and 1.

True Binomial distribution is nothing but no of Bernoulli trials. As I said I am a moron and don't understand much about Statistics. Just couldn't stop from asking my stupid question.

Oh, yes.
You can generate one B(20,0.7)-distributed random varible by summing up 
the like this:

 > pie <- 0.7
 > x <- runif(20)
 > x
  [1] 0.83108099 0.72843379 0.08862017 0.78477878 0.69230873 0.11229410
  [7] 0.64483435 0.87748373 0.17448824 0.43549622 0.30374272 0.76274317
[13] 0.34832376 0.20876835 0.85280612 0.93810355 0.65720548 0.05557451
[19] 0.88041390 0.68938009
 > x <- runif(20) < pie
 > x
  [1] FALSE FALSE  TRUE FALSE  TRUE  TRUE  TRUE  TRUE FALSE  TRUE FALSE 
  TRUE
[13] FALSE FALSE  TRUE  TRUE FALSE  TRUE FALSE FALSE
 > sum(x)
[1] 10

You could shorten this to

 > sum(runif(20)<0.7)
[1] 12

Which would be the same as

 > rbinom(1,20,0.5)
[1] 6

or even

 > qbinom(runif(1),20,0.5)
[1] 12


Just play around a little, and learn from the help files:

 > ?rbinom

Have fun!

--- On Thu, 5/12/11, David Winsemius<dwinsemius at comcast.net>  wrote:

From: David Winsemius<dwinsemius at comcast.net>
Subject: Re: [R] Binomial
To: "Alexander Engelhardt"<alex at chaotic-neutral.de>
Cc: r-help at r-project.org, "blutack"<x-jess-h-x at hotmail.co.uk>
Date: Thursday, May 12, 2011, 11:08 AM

I hope Allan knows this and is just being humorous here,  but for the less experienced in the audience ... Choosing a different threshold variable name might be less error prone. `pi` is one of few built-in constants in R and there may be code that depends on that fact.

pi

[1] 3.141593

He didn't, or better, he forgot.
Also, that Allan isn't related to me (I think) :)

  - Alex

An embedded and charset-unspecified text was scrubbed...
Name: not available
URL: <https://stat.ethz.ch/pipermail/r-help/attachments/20110512/6d2092b6/attachment.pl>