[R] Easy acf and pacf for irregular time series in R
a.trapletti at bluewin.ch
Tue Aug 10 14:54:22 CEST 2004
>Is there an easy way to get the acf and pacf for an irregular times
>series? That is, the acf and pacf with lag lengths that are in units of
>time, not observation number.
There are several solutions available depending on the particular
problem, some of them statistically "cleaner" than others:
For example eliminate non-business days (NA's) from the series and
compute the acf and pacf (e.g. with na.remove from tseries).
For example interpolate to get a regular series and compute acf and pacf
(e.g. with approx.irts from tseries).
For example use a methodology which can treat NA's (e.g. use Kalman
filtering from ts (R-1.8.1) now ??) and compute the acf and pacf from
the estimated model...
>Federal Reserve Bank of St. Louis
>The views expressed in this email are the author's and not necessarily
>those of the Federal Reserve Bank of St. Louis or the Federal Reserve
> [[alternative HTML version deleted]]
More information about the R-help