similar to: ARMA and prediction

Hi dear sirs, I am wondering why the fit of the time serie x with an arima and the fit of diff(x) with an arma (same coeff p & d) differ one from another here are the output of R: %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% > modelarma<-arma(diff(x),c(7,5)) > modelarma Call: arma(x = diff(x), order = c(7, 5)) Coefficient(s): ar1 ar2 ar3 ar4 ar5 ar6 ar7 ma1 ma2 0.06078

Hi all, I am fitting an ARMA(1,(1,4)) model. y(t) = a*y(t-1) + e(t) + b1*e(t-1) + b4*e(t-4) > arma1.14 <- arma(series, lag=list(ar=1, ma=c(1,4)), + include.intercept = F, qr.tol = 1e-07) works fine: Coefficient(s): ar1 ma1 ma4 0.872 -0.445 0.331 I want to forecast 50 periods. I could not find a 'predict' function for ARMA models. I

On Tue, Oct 13, 2009 at 5:06 PM, Rolf Turner <r.turner@auckland.ac.nz>wrote: > > Not clear to me what the OP really wants. Perhaps the seasonal > model is what's required; perhaps an arima(1,0,4) model with > theta_2 and theta_3 constrained to be 0. The latter can be > achieved with > > arima(x,order=c(1,0,4),fixed=c(NA,NA,0,0,NA,NA)) > > Or perhaps

Dear R users, I'm estimating a mixed effects model in which the spatial correlation is controlled for by the "corGaus" structure. I'm wondering if there is a document or paper that explains how the spatial correlation structure (such as "corExp" or "corGaus") works. Let me use the example and data posted on UCLA's R FAQ webpage to explain my problems.

I need to perform a QR-decomposition of a sparse matrix, so I've been trying to use the Matrix package. Unfortunately I don't seem to be getting exactly the same results as if I had used the qr() command from the base package. Here is an example of what I'm doing. > spdata <-rpois(50,1) > y <- rnorm(10,0,1) > S <-

Hello, I having trouble running the CAPdiscrim function located in biodiversityR. My data tables are as follows: community data frame (called "spdata") Species1... Speciesn site1.. site2.. siten with abundance data as values. Site names are row names. and environmental data (called "envdata") year elevation site1... site2... siten my command

spData <- as.vector(getYahooData("SPY", start="19900101",end="20081231")[,"Close"]) > cr <- cReturns(spData, ttr = "sma", params=c(20)) Error in ind[t - k] <- pos[t - k + 1] - pos[t - k] : replacement has length zero I am getting the above error when running the cReturns function. Any ideas on this? How does one drill down into

Cada vez que intento cargar el paquete "agricolae" me da el siguiente mensaje: Error: package or namespace load failed for 'agricolae' in loadNamespace(i, c(lib.loc, .libPaths()), versionCheck = vI[[i]]): there is no package called 'spData' He intentado todo actualizar los paquetes, volverlos a instalar pero no hay forma. Si sabeis la solución ?? Un saludo. Juan

I am puzzled by the warning message in the output below. It appears whether or not I fit the seasonal term (but the precise point of doing this was to fit what is effectively a second seasonal term). Is there some deep reason why AR parameters ("Warning message: some AR parameters were fixed: ...") should somehow intrude into the fitting of a model that has only MA terms? >

Hello everybody! I have an ARIMA model for a time series. This model was obtained through an auto.arima function. The resulting model is a ARIMA(2,1,4)(2,0,1)[12] with drift (my time series has monthly data). Then I perform a 12-step ahead forecast to the cited model... so far so good... but when I look the plot of my forecast I see that the result is really far from the behavior of my time

Hello, I'm running a number of arima models using the "arima" function. Often, when lag length gets too high, these model don't converge and an error message appears as this: > reg <- arima(y,order=c(7,0,7),xreg=isr) Warning message: In arima(y, order = c(7, 0, 7), xreg = isr) : possible convergence problem: optim gave code=1 In this case, when you print the results

Dear list and Martin, I'm testing different approaches to fit an electricity demand time series and come upon the fracdiff package (v 1.3-1) for fitting fractional ARIMA models. The following questions are motivated by this package. 1. Despite having a help page, the residuals and fitted functions don't seem to have implementation, or did i miss something obvious? Alternatively, having a

Hello R-Users Is there a package in R, that handles Markov (Regime) Switching (ARMA) Models for time series modelling and prediction? Thank you very much. Regards, Andreas.

R-guRus , ARMA function in tseries, seems to be calculating the AR coeff 's as coef <- lm(xx[,1]~xx[,lag$ar+1])$coef [*snipped* from around line 77,] I'd like to modify this model with another term somewhat in these lines lm(xx[,1] ~xx[,lag$ar+1]+mvgsignal)$coef where mvgsignal is a moving average signal based on some indicators, the question is could i simply hack into

Hello, BODY { font-family:Arial, Helvetica, sans-serif;font-size:12px; } Does any one know if there are any functions/packages available in R for robust fitting of ARMA time series models (e.g., similar to the function arima.rob() in S-PLUS)? Many thanks and kind regards, Isabella Isabella R. Ghement, Ph.D. Ghement Statistical Consulting Company 301-7031 Blundell Road,

Hello, Does anyone know about an R-package on multivariate ARMA-GARCH models? Or in Matlab? I would be very grateful if someone could help! Thanks a lot! [[alternative HTML version deleted]]

Hi, I have been fitting a series of data representing a week of Internet traffic (which is daily seasonal and have a general trend toward lower rate at the weekends). Before I do the ARMA fit (which takes care of seasonality with a lag equal to one day), do I have to make sure the data is stationary? From the results and visually, it seems that this was taken care of. But the residual

Hi, I need a function to convert an ARMA process to an "infinite" AR process. I know that in the Stats package exist one to convert an ARMA to MA, but i can't find one function to convert to AR. There exists one? THANKS

I have the following time series model for prediction purposes *Loss_t = b1* Loss_(t-1) + b2*GDP_t + b3*W_(t-1)* where W_t is the usual white noise variable. So this is similar to ARMA(1,1) except that it also contains an extra predictor, GDP at time t. I have only 20 observations on each variable except GDP for which I know till 100 values. And most importantly,I have also calculated

Hi, Let theta be the coefficient in AR(1) model, the components of the correlation structure is equal to 1 for times s = t, and theta^|t-s| for t > s. Could someone do me a favour to give some ideas on the correlation structure in AR(2) model and correlation structure of ARMA(p,q), as well? Thank you Fir [[alternative HTML version deleted]]