similar to: Multivariate Autoregressive Model calibration and residual testing

I wish to estimate sparse causal networks from simulated time series data. Although there's some discussion about this problem in the literature (at least a few authors have used lasso and l(1,2) regularization to enforce sparsity in multivariate autoregressive models, e.g., http://user.cs.tu-berlin.de/~nkraemer/papers/grplasso_causality.pdf), I can't find any R packages with these

Hi, I am trying to use optim to solve a heavy calibration problem. I supply the parameters in vector form. But before entering my target The call is simply: optim(par = parameters, fn = SumLSQ, method = "Nelder-Mead") the function SumLSQ is simply: SumLSQ<-function(parameters, data = timeseries){ print("sumLSQ") nbseries =

Hi! I know that there is function in fBasics package for univariate Jarque-Bera test and a funtion for univariate Ljung-Box test in stats package. But I am wondering if there is a function somewhere to do the tests for multivariate time series? Thanks, John [[alternative HTML version deleted]]

Dear R-users, I used lm() to fit a standard linear regression model to a given data set, which led to a coefficient of determination (R^2) of about 0.96. After checking the residuals I realized that they follow an autoregressive process (AR) of order 1 (and therefore contradicting the i.i.d. assumption of the regression model). I then used gls() [library nlme] to fit a linear

Hello, I am currently testing a Vector AR of dim 3 over not a lot of data (135 * 3 observations) . To test the adequation of my vecot ar, I use the Schwarz Bayesian Criterion and the classic modified Portmanteau test on the residuals (it can be found for instance in http://www.iue.it/PUB/ECO2004-8.pdf , page 15) -> the null hypothesis is "the residuals process are a vectorila white

Hello, I am using the Ljung Box test in R to compute if the resiudals of my fitted model is random or not. I am not sure though what the results mean, I have looked at various sources on the internet and have come up with contrasting explanations (mainly because these info deal with different program languages, like SAS, SPSS, etc). I know that my residuals should appropriate white noise( is

I'm analizing the Argentina stock market (merv) I download the data from yahoo library(tseries) Argentina <- get.hist.quote(instrument="^MERV","1996-10-08","2003-11-03", quote="Close") merv <- na.remove(log(Argentina)) I made the Augmented Dickey-Fuller test to analyse if merv have unit root: adf.test(merv,k=13) Dickey-Fuller = -1.4645,

I'm analizing the Argentina stock market (merv) I download the data from yahoo library(tseries) Argentina <- get.hist.quote(instrument="^MERV","1996-10-08","2003-11-03", quote="Close") merv <- na.remove(log(Argentina)) I made the Augmented Dickey-Fuller test to analyse if merv have unit root: adf.test(merv,k=13) Dickey-Fuller = -1.4645,

Hi all, I am modelling a time series with missing data. *Q1)* However, I am not sure if I should use the next *graphics* to understand my data: *a)* ACF & PACF (original series) *b)* ACF & PACF (residuals) * * *Q2)* I am using *tsdiag*, so I obtain a graphic with 3 plots: stand. residuals vs time; acf for residuals; Ljung-Box for residuals (it is wrong for residuals). I know that using

Dear colleagues, I am new to R and statistics so please keep that in mind. I have doubts on the df calculation of Ljung-Box test (Box.test). The function seems to use always the df=lag=m and not df=m-p-q like suggested in Ljung and Box (1978) paper (that is referenced). Do you agree with this? If so, is there an R package function that computes Ljung-Box test with the degrees of

Hi all I'm using the Box-Ljung test (from within R) to test if a time-series in independently distributed. 2 questions: 1) p-value returned by Box-Ljung: IF I want to test if the time-series is independant at say 0.05 sig-level (it means that prob of erroneously accepting that the time-series is independent is 0.05 right?) --> then do I consider time-series as "independant"

Dear list members, I have 982 quotations of a given stock index and I want to run a Ljung-Box test on these data to test for autocorrelation. Later on I will estimate 8 coefficients. I do not know how many degrees of freedom should I assume in the formula for Ljung-Box test. Could anyone tell me please? Below the formula: Box.test(x, lag = ????, type = c("Ljung-Box"), fitdf = 0)

Full_Name: Peter Solymos Version: 2.8.1 OS: Windows Submission from: (NULL) (129.128.141.92) The help page of the Box.test function (stats) states that the Ljung-Box test was published in: Ljung, G. M. and Box, G. E. P. (1978), On a measure of lack of fit in time series models. Biometrika 65, 553--564. The page numbers are incorrect. The correct citation should be as follows: Ljung, G. M.

Dear R users, I would like to simulate, for 20000 replications, an autoregressive process: y(t)=0.8*y(t-1)+e(t) where e(t) is i.i.d.(0,sigma*sigma), Thank you in advance ____________________________________________________ Écoutez gratuitement le nouveau single de Noir Désir et découvrez d'autres titres en affinité avec vos goûts musicaux

Hello everybody, I've a question about "autoregressive Regressionmodels". Let Y[1],.....,Y[n], be a time series. Given the model: Y[t] = phi[1]*Y[t-1] + phi[2]*Y[t-1] + ... + phi[p]*Y[t-p] + x_t^T*beta + u_t, where x_t=(x[1t],x[2t],....x[mt]) and beta=(beta[1],...,beta[m]) and u_t~(0,1) I want to estimate the coefficients phi and beta. Are in R any functions or packages for

Dear R users, I am trying to find a package that can estimate an autoregressive model for discrete data. I am imagining a Poisson or Gamma process in which the mean (say mu) follows a process such as mu_t = a + b*x + c*mu_{t-1} Suppose I have data on the time-series Poisson outcomes and x and would like to obtain ML estimates for b and c. Does anyone know of a package that can do this

Hello - I need to do simple linear autoregressive model with R software for my thesis. I looked into all your documentation and I am not able to find anything too helpful. Can someone help me with the codes? Thanks Emil [[alternative HTML version deleted]]

Hi, I am trying to replicate Engle and Manganelli's paper Conditional Autoregressive Value at Risk (CAViaR) by Regression Quantiles. I have the Matlab code which I cannot get to work as I have never used Matlab before, does anyone know if there is the same code available to estimate the CAViaR models in R? Thanks, Shane -- View this message in context:

Hi all ! I would like to simulate spatial lattice/areal data with a conditional autoregressive (CAR) structure, for a given neighbouring matrix and for a autocorrelation "rho". Is there any package or function in R to perform it ? I found the function "CARsimu" in the hdeco library, but this is not what I'm looking for Thanks in advance Dae-Jin --

Hello, I am using R for fitting parameters of a time series model. The model is as below. Y(t) = mu + a*X(t) + YN(t) where YN(t) = b*YN(t-1) + innovation and Z(t) follows N(0,1). The main obstacle for me is the autoregressive error term, YN(t). I can't figure out how to estimate the parameters (mu, a, b) with usual 'arima' function in R. What I have tried is.... 1. Do the