similar to: predict.arima

Hello everyone, Since my question is quite theorical, I am not sure whether it is the right place to ask, but anyway... I am working on time series and I looked at some way to fit my data through arima models. Since these data are updated frequently, I was looking at a way to update the model "on line" (to get a kind of recursive estimation) So the next step was to express the arima

I am trying to use KalmanSmooth to smooth a time series fitted by arima (and with missing values), but the $smooth component of the output baffles me. Look at the following example: testts <- arima.sim(list(ar=0.9),n=100) testts[6:14] <- NA testmod <- arima(testts, c(1,0,0)) testsmooth <- KalmanSmooth(testts, testmod$model) par(mfrow=c(2,1)) plot(testsmooth$smooth,

>From the help document on KalmanLike, KalmanRun, etc., I see the linear Gaussian state space model is a <- T a + R e y = Z' a + eta following the book of Durbin and Koopman. In practice, it is useful to run Kalman filtering/smoothing/forecasting with exogenous factor: a <- T a + L b + R e y = Z' a + M b + eta where b is some known vector (a function of time). Some other

Hi, I am trying to forecast a model using predict.Arima I found arima model for a data set: x={x1,x2,x3,...,x(t)} arima_model = arima(x,order=c(1,0,1)) I am forecasting the next N lags using predict: arima_pred = predict(arima_model,n.ahead = N, se.fit=T) If I have one more point in my series, let's say x(t+1). I do not want to recalibrate themodel, I just want to forecast the next N-1

Hi, i'm beginner in Bayesian methods, I'm reading the documentation about dlm package and kalman filters, I'm looking for a example of transformation of ARIMA in a state space equivalent to use the dlm package and calcualte the hyperparameters. Someone can help me about it?. If it's possible with a arima(1,0,1) example, or more complex model. While I have more examples best for me.

Here is my problem: Autoregressive models are very interesting in forecasting consumptions (eg water, gas etc). Generally time series of this type have a long history with relatively simple patterns and can be useful to add external regressors for calendar events (holydays, vacations etc). arima() is a very powerful function but kalman filter is very slow (and I foun difficulties of estimation)

Hi all, Forecasting from an arima model is easy with predict. But I can't manage to backcast : invent data from the model before the begining of the sample. The theory is easy : take your parameters, reverse your data, forecast, and then reverse the forecast I've tried to adapt the predict function to do that (i'm not sure that the statistical procedure is fine (with the residuals),

Hi, I'm using R for some arima models. In the past I used for arima models Rats and Tsp. Using the R arima function, I get only the statistics sigma^2 and log likelihood; with Rats and Tsp it is possible to obtain more statistics, such as R, R square, Durbin Watson, standard error, etc. Is it possible using R to have the statistics mentioned? My best regards,

Hello, Does anyone know how the parameter estimates are calculated for xreg variables when called as part of an arima() command, or know of any literature that provides this info? In particular, I was wondering if there is a quick way to compare different combinations of "xreg" variables in the arima() fit in the same way that you would in multiple regression (using AIC & R^2

I'm searching a method to estimate the hyper-parameters in arima models. I'm reading about r-inla package, but in the examples section only talk about the AR part of the arima, but i need help about the MA part too. I'm beginner in Bayesian methods, I'm reading the documentation about dlm package and kalman filters, but the computacional cost of inla i think is better, but only

Hola! I got problems using an objects returned from arima (in KalmanSmooth(my.ts, ModArima$model), because my.ts showed up to have storage mode "integer" (is.integer(my.ts was TRUE). Should storage.mode() of a ts be allowed to be integer, should ts() someplace say storage.mode(ts.out) <- "double", or maybe inside arima() storage.mode(x) <- "double"

Anyone know how to esimate parameters in the system: x[k]=Ax[k-1]+ B + Gv[k-1] y[k]=x[k]+Du[k]+Hw[k] a system with exogenous u[k] in the measurement eq., v,w are iid, both eq. are gaussian. Thanks, Oyvind --------------------------------- [[alternative HTML version deleted]]

(re-formulate, re-send, without html) for vector y = c(1,2,3,4,5), H = 0.66 manual calculations using the equations below give a = c(1,1.66,2.55,3.51,4.50). KalmanRun with these parameters gives res$states = (1,1,1,1,1)! for Kalman Filter Durbin/Koopman give at p67 eqs 4.13: v = y - Z a, F = Z P Z' + H, K = T P Z' / F + H, a[t+1] = T a + K v, P[t+1] = T P L'

Dear all, I'd like to discuss about a possible bug in function StructTS of stats package. It seems that the function returns wrong value of the log-likelihood, as the added constant to the relevant part of the log-likelihood is misspecified. Here is an simple example: > data(Nile) > fit <- StructTS(Nile, type = "level") > fit$loglik [1] -367.5194 When computing the

Hello all, I have been using R's time series capabilities to perform analysis for quite some time now and I am having some questions regarding its reliability. In several cases I have had substantial disagreement between R and other packages (such as gretl and the commercial EViews package). I have just encountered another problem and thought I'd post it to the list. In this case,

Hello R users, Hope everyone is doing great. I have a dataset that is in .csv format and consists of two columns: one named Period (which contains dates in the format yyyy_mm) and goes from 1995_10 to 2007_09 and the second column named pcumsdry which is a volumetric measure and has been formatted as numeric without any commas or decimals. I imported the dataset as pauldataset and made use of

I'm playing with predict.Arima in the 3/19/02 development snapshot of R-devel. The following produces an error message because x is not of class "ts": R> x <- rnorm(20) R> obj <- arima(x, c(2,0,0)) R> predict(obj) Error in round(x, digits) : Non-numeric argument to mathematical function Granted the documentation for arima says x should be a time-series, but

Hi, Few days ago I posted a question to r-sig-finance, which I thought would be an easy one. To my surprise I have received no replies, which makes me think that it is either harder than I thought, or that it makes no sense. I am reposting the message (with some modifications) on the R-help in a hope to get some leads, suggestions for alternatives, etc. My apologies to those who had seen this on

Hi, the function makeARIMA(), designed to construct some state space representation of an ARIMA model, uses a C function called getQ0, which can be found at the end of arima.c in R source files (library stats). getQ0 takes two arguments, phi and theta, and returns the covariance matrix of the state prediction error at time zero. The reference for getQ0 (cited by help(arima)) is:

Dear All, R 1.9.1, Windows When copying and pasting a few lines from the 'predict.Arima' help, I get an error message: > data(lh) > predict(arima(lh, order = c(3,0,0)), n.ahead = 12) Error in eval(expr, envir, enclos) : Object "xreg" not found On the other hand, the following is OK: > data(lh) > predict(arima0(lh, order = c(3,0,0)), n.ahead = 12) $pred Time