Services & Resources / Wolfram Forums
-----
 /
MathGroup Archive
2002
*January
*February
*March
*April
*May
*June
*July
*August
*September
*October
*November
*December
*Archive Index
*Ask about this page
*Print this page
*Give us feedback
*Sign up for the Wolfram Insider

MathGroup Archive 2002

[Date Index] [Thread Index] [Author Index]

Search the Archive

Re: Quantile function

  • To: mathgroup at smc.vnet.net
  • Subject: [mg35374] Re: [mg35316] Quantile function
  • From: BobHanlon at aol.com
  • Date: Wed, 10 Jul 2002 02:19:39 -0400 (EDT)
  • Sender: owner-wri-mathgroup at wolfram.com

In a message dated 7/8/02 3:37:12 AM, a at a.a writes:

>When using the quantile function:
>
>In[7]:=
>Quantile[dist, 0.8]
>
>Out[7]=
>0.841621
>
>can anyone tell me how to get more accuracy?
>

Needs["Statistics`NormalDistribution`"]

dist = NormalDistribution[0, 1];

Quantile[dist, 0.8]

0.841621

The display is truncated for output.  The InputForm shows this.

Quantile[dist, 0.8] // InputForm

0.8416212335729144

NumberForm will display additional digits but only up to the maximum 
consistent with machine precision.

NumberForm[Quantile[dist, 0.8], 20]

0.841621233572914

For precision beyond machine precision you need to use exact or higher 
precision numbers in the definition of the distribution (as above) and in 
the call to Quantile.

N[Quantile[dist, 8/10], 20]

0.84162123357291420518

Quantile[dist, N[8/10, 20]]

0.84162123357291420518


Bob Hanlon
Chantilly, VA  USA


  • Prev by Date: Re: Simplify inequalities
  • Next by Date: RE: Simplify inequalities
  • Previous by thread: Re: Quantile function
  • Next by thread: entering problem