Services & Resources / Wolfram Forums
-----
 /
MathGroup Archive
1999
*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 1999

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

Search the Archive

Statistics

  • To: mathgroup at smc.vnet.net
  • Subject: [mg18421] Statistics
  • From: "Roberto Diego" <r-diego at develnet.es>
  • Date: Wed, 7 Jul 1999 00:11:15 -0400
  • Sender: owner-wri-mathgroup at wolfram.com

I'm a little ashamed for posting this simple (not for me) question to the
impresive intelectual power out there, especialy because I guess there must
be a simple answer. I feel fustrated as I can't get there.

The question is:

I think there must exist an expression for the variance of a random time
series in wich each element equals the previous plus a fixed (1/100)
quantity times a uniform random variable in the range {-1,1}. I construct
the series using:

data=Table[NestList[#+(1/100)*Random[Integer,{-1,1}]&,30,1000]];

this simulates the levels of the variable, now:

rendata=Table[Log[data[[i+1]]/data[[i]]],{i,1,1000}];

convert the levels to rates of change.

What I'm looking for is an expression for the variance of rendata as a
function of the starting point in the level (30 in the above case) and a
step size (1/100).

Thanks a lot

Roberto Diego






  • Prev by Date: Polar coordinates
  • Next by Date: Series[] problem
  • Previous by thread: Polar coordinates
  • Next by thread: Series[] problem