[R] Announcement: CRAN packages 'urca' and 'vars' on R-Forge

Dear useR, the CRAN packages 'urca' and 'vars' are now hosted on R-Forge as projects 'AICTS I' and 'AICTS II', respectively. The packages' summary page can be directly accessed via: AICTS I: http://r-forge.r-project.org/projects/urca/ AICTS II: http://r-forge.r-project.org/projects/vars/ All

Re: [R] possible bug in vars package (predict.varest) ???

Hello Spencer, which version of vars are you using? This has been fixed a while ago (see ChangeLog). Incidentally, the data in Canada is quarterly data, as stated in ?Canada. Aside of this, your code snippet works fine. Best, Bernhard ps: There is no need to download the tarball as suggested by

Re: [R] Restricted VAR parameter estimation

Hello Megh, in principle you can do OLS on an equation-per-equation basis. However, in this case the estimator might be asymptotically inefficient. One can use FGLS instead. This is outlined for instance in: Helmut Luetkepohl, 2007. Econometric Analysis with Vector Autoregressive Models,

Re: [R] Seasonality

Hello Alberto, hello Felix, aside of monthplot() and stl(), there is the possibility to use Census X-12-ARIMA. The program can be downloaded from: http://www.census.gov/srd/www/x12a/ It should be mentioned that this is *not* a pure R solution, but one can set up the relevant scripts and

Re: [R] cointegration analysis

Hello Dorina, if you apply ca.jo to a system with more than five variables, a *warning* is issued that no critical values are provided. This is not an error, but documented in ?ca.jo. In the seminal paper of Johansen, only cv for up to five variables are provided. Hence, you need to refer to a

Re: [R] ca.jo

Hello Yihsu, have a look at ?cajorls. With this function a VECM is estimated, whence the cointegration rank has been determined (ca.jo). For further analysis, you might want to consider the function vec2var in package vars and methods irf, fevd and predict, as well as the diagnostic tests that

Re: [R] Combine graphical and textual output

Hello Dieter, aside of Petr's suggestion, you might want to look at the 'relax' package. Here, you can produce html as well as tex for on-the-fly reports. The reports are set up within a tcl/tk window. Best, Bernhard Hi, I would like to know whether anybody knows a simple way to combine

Re: [R] urca package - summary method -

Hi I am using the package urca and I am interested about the KPSS test. That works fine except the method summary did not work in the script, only when it is typed direct in the console the results are shown( not a source file). Hello, which version of urca are using? The problem you

Re: [R] lag orders with ADF.test

Hello! I do not understand what is meant by: aic and bic follow a top-down strategy based on the Akaike's and Schwarz's information criteria in the datails to the ADF.test function. What does a top-down strategy mean? Probably the respective criterion is minimized Hello Martin, are you

Re: [R] time series analysis

Hello John, as a starting point you might also want to have a look at: @book{BOOK, author={Robert S Pindyck and Daniel L Rubinfeld}, title={Econometric Models and Economic Forecasts}, year={1997}, publisher={McGraw-Hill/Irwin}, isbn={0079132928} } The monographies of Hamilton and Lütkepohl

Re: [R] Finding the Min.

?which.min Dear all R users, Suppose I have a dataset like that, data = 1 1.957759e-09 2 1.963619e-09 3 1.962807e-09 4 1.973951e-09 5 1.983401e-09 6 1.990894e-09 7 2.000935e-09 8

Re: [R] problem in adf command

that is, equation with constant and trend is used.if i did not include constant or trend in the equation and run the command then how i can run this command in tseries. Dear Zahid, you can employ ur.df() in package 'urca' or the wrapped functions from 'urca' contained in package 'fSeries',

Re: [R] problem in adf command

ur.df(y, type = c(none, drift, trend), lags = 1) in urca. this gives me all out put .but i need only p.value fromm the output. when i run the following command ur.df(y, type = c(none, drift, trend), lags = 1)$p.value this in response

Re: [R] Error message using normality test in vars

I'm running a vector-time series model with the vars package. When I test the univariate and multivariate normality of the residuals using normality(), I get the results, but also this warning Warning messages: 1: longer object length is not a multiple of shorter object length in: b2

Re: [R] solution to a regression with multiple independent variable

Hello John, you can derive these estimators by considering a step-wise approach: 1) Derive the estimators by evaluating a model with demeaned variables, i.e. consider (\tilde{X}'\tilde{x})^-1 \tilde{x}'\tilde{y}, where \tilde{...} refers to the demeaned variables. 2) Obtain the estimate of the

Re: [R] Multivariate regression

Hello Ravi, have you considered the SUR method proposed by Zellner? An implementation of it is provided in CRAN-package 'systemfit' (see ?systemfit for more information). Best, Bernhard Suppose I have a multivariate response Y (n x k) obtained at a set of predictors X (n x p). I would like to

Re: [R] .arch.uni in function call in arch test of vars package

The arch test requires a varest object and I am trying to write one that will use R-metrics arima, arch, Garch objects, or at least a vector. Also the arch function has the following line of code that I can not find the function anywhere archs.resids - apply(resids, 2, function(x)

Re: [R] Multivariate AR - prediction

Hello Alexander, try package CRAN package 'vars'. Best, Bernhard Hi, does anybody know how to predict a multivariate AR within R? If I just estimate a multi AR-object and plug it into predict I get an error from the aperm - just works for univariates. thx alex

[R] Omegahat-site down?

Dear R-list subscriber, is it possible that the omegahat-site is down? I was looking for package 'RDCOMClient', but could not establish a connection. In case somebody has the latest binary zip-file for Windows, would she/he mind to send it directly to my emaim adress stated in the signature?

[R] CRAN package: update of 'vars' submitted

Dear useR! an updated version of package 'vars' has been shipped to CRAN lately. Information on package 'vars': == Title: VAR Modelling Version: 0.1.3 Date: 2006-07-27 Author:Bernhard Pfaff Maintainer:Bernhard Pfaff bernhard at

Re: [R] KPSS test

Hello Sachin, a sequential testing procedure is described in the useR! book: @Book{, title = {Analysis of Integrated and Cointegrated Time Series with R}, author = {B. Pfaff}, publisher = {Springer}, edition = {First}, address = {New York}, year = {2006}, note =

Re: [R] Cointegration Test in R

Hello Dennis, have you considered the function bh6lrtest() in the package urca? To my knowledge, there is no other package available that offers VECM functionalities. Best, Bernhard ps: As you migth be interested in VAR and SVAR too: I am currently working on such a package which should be

Re: [R] extract p-value from urppTest

Hello Anne, the function 'ur.pp' contained in the package 'urca' has been ported into the package 'fSeries' (see the documentaion of ?urppTest). help(ur.pp-class, package=urca) will tell you that p-values are not part of this class, i.e., these are not computed but critical values are returned.

Re: [R] urppTest Z-tau? Z-alpha?

Hello Anne, you will find the necessary details in the following paper, its publication in 'Biometrika' is cited in ?ur.pp. http://cowles.econ.yale.edu/P/cp/p07a/p0706.pdf Best, Bernhard Hello, Could someone give me a hint about what might be the difference between running urppTest with

Re: [R] Net courses for R?

Hello Scott, see: http://www.statistics.com/content/courses/R/index.html http://www.statistics.com/content/courses/graphicsR/index.html http://www.statistics.com/content/courses/modelingR/index.html there has been a recent posting on this list, if I recall it correctly. Best, B.

[R] Link to useR! 2006 from ww.r-project.org not working

I noticed that: http://www.r-project.org/useR-2006/ seems to be inexistent (page not found). Best, Bernhard Dr. Bernhard Pfaff Global Structured Products Group (Europe) Invesco Asset Management Deutschland GmbH Bleichstrasse 60-62 D-60313 Frankfurt am Main Tel: +49(0)69 298 07230 Fax:

Re: [R] What are the differences between ACF and PACF in time seriesanalysis?

Hello Michael, see as an online resource: http://www.statsoft.com/textbook/sttimser.html or get hold on a time series analysis textbook, like one of the monographies written by Hamilton; Luetkepohl; Brockwell Davis; Harvey or Box Jenkins, to name but a few. In a nutshell, PACF 'eliminates'

Re: [R] Is there a way....

Hello Levent, there has recently been a thread on the ESS list by using setnu in EMACS: https://stat.ethz.ch/pipermail/ess-help/2006-April/003450.html Bernhard -Ursprüngliche Nachricht- Von: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] Im Auftrag von Uwe Ligges Gesendet: Mittwoch, 26.

Re: [R] Bloomberg Data Import to R

Hello Sumanto, your question might be more appropriately been posted to the R-sig-finance list: [EMAIL PROTECTED] (I have cc'ed this mail to this list). To my knowledge neither a function nor a CRAN-package does exist. However, on the last useR! conference Dirk Edelbuettel presented a

Re: [R] reducing learning curves?

Hello Michael, you might want to utilise Emacs/ESS. ESS provides auto-completion by using TAB for a process buffer '*R*' and C-cTAB for a source file '*.R' (ess-mode). As far as debugging is concerned, R offers: ?browser ?debug ?trace for example. Additionally, there is a CRAN package named

Re: [R] R vs. Excel (R-squared)

Hello Lance, this was discussed on the list lately, see: http://tolstoy.newcastle.edu.au/~rking/R/help/06/01/18934.html Bernhard -Ursprüngliche Nachricht- Von: Lance Westerhoff [mailto:[EMAIL PROTECTED] Gesendet: Dienstag, 24. Januar 2006 17:51 An: r-help@stat.math.ethz.ch Betreff:

Re: [R] Obtaining the adjusted r-square given the regression coef ficients

Hello Alexandra, R2 is only defined for regressions with intercept. See a decent econometrics textbook for its derivation. HTH, Bernhard -Ursprüngliche Nachricht- Von: Alexandra R. M. de Almeida [mailto:[EMAIL PROTECTED] Gesendet: Mittwoch, 11. Januar 2006 03:48 An:

Re: [R] Q about RSQLite

Hello Liu, this might be caused by NA entries in your SQLite table. Have a look at the following code: (test - data.frame(matrix(c(1:10, NA, NA), ncol=2, nrow=6))) con - dbConnect(SQLite(), dbname = test.db) dbWriteTable(con, test, test, type=BLOB, overwrite=TRUE) d1 - dbReadTable(con, test)

Re: [R] cointegration rank

. That is, the data is 'pre-filtered' by the impact of the dummy variables. HTH, Bernhard Another question on cointegration... Is it possible to insert in the model dummy variables restricted in the cointegration space? Many thanks, Carlo On Nov 21, 2005 01:23 PM, Pfaff, Bernhard Dr. [EMAIL PROTECTED

Re: [R] cointegration rank

Dear R - helpers, I am using the urca package to estimate cointegration relations, and I would be really grateful if somebody could help me with this questions: After estimating the unrestriced VAR with ca.jo I would like to impose the rank restriction (for example rank = 1) and then obtain the

Re: [R] cointegration rank

as exogenous. Many thanks! Carlo Hello Carlo, you can use the 'dumvar' argument for his purpose, and exclude the relevant variables from your data matrix 'x'. HTH, Bernhard On Nov 21, 2005 11:21 AM, Pfaff, Bernhard Dr. [EMAIL PROTECTED] wrote: Dear R - helpers, I am using the urca package

Re: [R] How can I test temporal autocorrelation of binary data?

Depending on what you are really want to infer from the autocorrelations, you want to consider the runs-test, too. HTH, Bernhard If you mean you want to test that there is no autocorrelation, then there is some information on using the Ljung-Box test on such data in the working paper

[R] COM objects with early bindings in R

Dear list member, I am using the packages RDCOMClient and SWinTypeLibs and try to import a COM object (created in Delphi) in R that is of type 'early binding' instead of late 'late binding'. Is there a possibility to do this in R? Currently, the following returns an error message: l1 =