Time Series frequency problem

classic Classic list List threaded Threaded
1 message Options
Reply | Threaded
Open this post in threaded view
|

Time Series frequency problem

Weena
Hey guys, i'm trying to use the BCDating package.
Using this it is required to work with a time series with frequency 4 (quarterly). Otherwise it says:
"Error in BCDating.peakstroughs(start = start(y), end = end(y), freq = frequency(y),  :
  frequency must be 12 (monthly dates) or 4 (quarterly dates)"
So i have a dataset consisting just of 143 observations (GDP one year given quarterly, which i importet using "import data and then the csv excel file)
To use BC function i have to covert in into a time series:
dat <- ts(y, start = 1, end = 143, frequency=4)
"Values of 4 and 12 are assumed in (e.g.) print methods to imply a quarterly and monthly series respectively."
because its yearly data which is given in quarters i chose frequency 4.
Now the outcome is a vector with 4x the length of 143.
I don't understand what this function actually does.
So what do i have to do regarding my goal.
As you might have noticed i'm a completely new to R.
Any help ?