Message-ID: <1320089912253-3960790.post@n4.nabble.com>
Date: 2011-10-31T19:38:32Z
From: Ritz
Subject: Equidistant time spacing of time series data
I am running ARMA model on time series data. Data consists of price changes
in S&P 500 during the day, recorded at 4 predefined time stamps( 8:30,
10:30,10:15, 3:12, hence non equidistant)
My question is, do I need to worry about the data being non equidistant?
If so, how do I modify my series to account for it?
Or is it safe to assume data as being equidistant,as it may not have a
strong influence on the final forecast?
Thanks!
-Ritz
--
View this message in context: http://r.789695.n4.nabble.com/Equidistant-time-spacing-of-time-series-data-tp3960790p3960790.html
Sent from the R help mailing list archive at Nabble.com.