Hey guys,
im sort of a beginner with R, but here's what i need to do.
i need to perform a time series analysis on a set of financial data that
i've been given. im trying to look at the ACF and PACF and fit it to a
particular model (i think its the ARIMA model because i've read that
financial data resembles the random walk, where the ARIMA model fits). is this
correct?
if my data is called "numbers"
ts.plot(numbers)
acf(numbers,30,type='partial')
now, i want to difference at a particular number of lags, and i thought to use
this code:
dnumbers <- diff(numbers, 10)
ts.plot(dnumbers)
acf(dnumbers)
acf(dnumbers, 30,type='partial')
but i get error messages after ts.plot(dnumbers):
Error in matrix(rep.int(tx, k), ncol = k) :
invalid 'nrow' value (too large or NA)
and after acf(dnumbers):
Error in plot.acf(acf.out, ...) : x$lag must have at least 1 column
Am i going about doing this the right way? i want to have a look at differencing
and hope to fit the model from this.
Can someone help me with what is wrong with my code, and any suggestions would
be soo helpful..
Thanks a lot to everyone,
Kon
Click here to find out more POP access for Hotmail is here!
_________________________________________________________________
POP access for Hotmail is here! Click here to find out more
[[alternative HTML version deleted]]
