image
Physics Forums Logo
image
image
* Register * Upgrade Blogs Library Staff Rules Mark Forums Read
image
image   image
image

image Equality of Time Series Share It Thread Tools Search this Thread image
Old Jun30-09, 12:12 AM                  #1
kylemacr

kylemacr is Offline:
Posts: 1
Equality of Time Series

Hi All,

I've searched the web up and down, and a few text books, all to no avail.

I have two time series (of 30 elements each), and I'd like to test if they are statistically different from each other (I suppose this could be reworded as, "are they equal" or "is their difference statistically different from zero"). I can't for the life of me figure out how to do that.

any ideas?

Thanks!
  Reply With Quote
Old Jun30-09, 09:21 AM                  #2
g_edgar

g_edgar is Offline:
Posts: 388
Re: Equality of Time Series

Originally Posted by kylemacr View Post
Hi All,

I've searched the web up and down, and a few text books, all to no avail.

I have two time series (of 30 elements each), and I'd like to test if they are statistically different from each other (I suppose this could be reworded as, "are they equal" or "is their difference statistically different from zero"). I can't for the life of me figure out how to do that.

any ideas?

Thanks!
Hire a statistician?
  Reply With Quote
Old Jul1-09, 08:45 PM       Last edited by EnumaElish; Jul1-09 at 08:52 PM..            #3
EnumaElish
 
EnumaElish's Avatar

EnumaElish is Offline:
Posts: 2,217
Recognitions:
Homework Helper Homework Helper
Science Advisor Science Advisor
Re: Equality of Time Series

What kind of equality? See http://en.wikipedia.org/wiki/Random_...ndom_variables

"Equality of means" is relatively easy to test (e.g. t-test). "Equality of distributions" is harder, although I can think of the following:

1. You can study tests for equivalence of distributions, such as Chi-square or Kolmogorov-Smirnov.

2. You can calculate the Gini coefficient then test whether it equals zero. (This may be a version of the K-S test.)

3. If you know their distributions, you can express each series as 30 successive order statistics, and jointly test their equivalence for as many orders as your degrees of freedom will let you. You'll need to derive the distribution of the difference between two order statistics, X(k) - Y(k), for k = 1 through 30, which can take some algebraic work.
  Reply With Quote
image image
Reply
Thread Tools


Similar Threads for: Equality of Time Series
Thread Thread Starter Forum Replies Last Post
time series question roadworx Set Theory, Logic, Probability, Statistics 2 May17-09 08:17 PM
Time Series Modelling logarithmic Calculus & Beyond 0 Oct1-08 10:15 PM
Fourier Time Series islandtrader Advanced Physics 2 May20-08 12:22 AM
Recursive Series Equality ramsey2879 Number Theory 11 Oct10-07 11:24 PM
The time expression of the matter-raditation equality era Magister Advanced Physics 3 Feb26-07 10:39 AM

Powered by vBulletin Copyright ©2000 - 2009, Jelsoft Enterprises Ltd. © 2009 Physics Forums
Sciam | physorgPhysorg.com Science News Partner
image
image   image