Hi, I tried the formula sum(psi*X[(t-1):(t-K)])
but it provides the vector of all observations. Thus, I changed K to k where K<-3 and k<-1:K This yields better results but not what I want since I should get 3 values as K=3. > X[(t-1):(t-k)] [1] 0.1 Warning message: In (t - 1):(t - k) : numerical expression has 3 elements: only the first used Why do I get this error message and how can I avoid it?? Thanks in advance -----Original Message----- From: peter dalgaard [mailto:pda...@gmail.com] Sent: 05 May 2015 11:41 To: T.Riedle Cc: r-help@r-project.org Subject: Re: [R] using filter() to sum up On 04 May 2015, at 21:38 , T.Riedle <tr...@kent.ac.uk> wrote: > Hi everybody, > > I am trying to create a code for the formula in the attachment. I first tried > following code: > > ltau <- m + theta*sum(psi*X[t-k]) > That's not going to work. It might work with something like sum(psi*X[(t-1):(t-K)]) > but it does not work and I get for X[t-k] every third element in my vector > three times which looks as follows: > X[t-k] > [1] -0.25 -0.25 -0.25 0.50 0.50 0.50 -0.44 -0.44 -0.44 0.15 0.15 0.15 > > Thus, I tried the filter() function in R which looks as follows: > ltau <- m + theta* filter(f.USA$UTS, phi(K, omega1, omega2), sides=1, > method="conv") > > Reading the description of this function I am unsure whether this provides > the sum of the k lags. The appreviation "conv" provides, as far as I > understand, the moving average instead of the sum. I would assume that it means convolution. Which is what you have in the formula. > Does anybody have an idea how the R code for the formula attached must look > like? Is the filter() function appropriate? It's barking up the right tree, but do your own checks... -pd > Thanks in advance. > <tau.png>______________________________________________ > R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see > https://stat.ethz.ch/mailman/listinfo/r-help > PLEASE do read the posting guide > http://www.R-project.org/posting-guide.html > and provide commented, minimal, self-contained, reproducible code. -- Peter Dalgaard, Professor, Center for Statistics, Copenhagen Business School Solbjerg Plads 3, 2000 Frederiksberg, Denmark Phone: (+45)38153501 Office: A 4.23 Email: pd....@cbs.dk Priv: pda...@gmail.com
______________________________________________ R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.