similar to: ts and stl functions - still a problem

Hi, I have imported a csv file into R which contains one column (the rate er 100,000 population of a disease, by month over 11 years) I coerced into a time series using the following function, tstkr<-ts(tkr,deltat=1/12) This seems to work fine, and when I check for the class of the object using class(tstkr) I get "ts" as the response. When I try to use the stl function in

Hi, I have imported a csv file into R which contains one column (the rate er 100,000 population of a disease, by month over 11 years) I coerced into a time series using the following function, tstkr<-ts(tkr,deltat=1/12) This seems to work fine, and when I check for the class of the object using class(tstkr) I get "ts" as the response. When I try to use the stl function in stats

Hello, Does anyone know of a way I can speed this up? Basically I'm attempting to get the data item on the same row as the report date for each report date available. In reality, I have over 11k of columns, not just A, B, C, D and I have to do that over 100 times. My solution is slow, but it works. The loop is slow because of merge. # create sample data z.dates =

Hi, I have a monthly time series with missing values and I would use stl function to identify seasonality. I tried all settings of na.action but the result is the same: stl(tm245,s.window=11, na.action=na.pass) Error in stl(tm245, s.window = 11, na.action = na.pass) : NA/NaN/Inf in foreign function call (arg 1) Can you help me? Thanks Andrea Toreti [[alternative HTML version

Hi, I'm dealing with time series. I usually use stl() to estimate trend, stagionality and residuals. I test for normality of residuals using shapiro.test(), but I can't test for autocorrelation and heteroskedasticity. Is there a way to perform Durbin-Watson test and Breusch-Pagan test (or other simalar tests) for time series? I find dwtest() and bptest() in the package lmtest, but it

Hello, Thank you for your help/advice! The issue here is speed/efficiency. I can do what I want, but its really slow. The goal is to have the ability to do calculations on my data and have it adjusted for look-ahead. I see two ways to do this: (I'm open to more ideas. My terminology: Unadjusted = values not adjusted for look-ahead bias; adjusted = values adjusted for look-ahead bias.) 1) I

I am running R 1.2.2 under Linux. When using the function stl in the ts library, how can I save the seasonal component? What I would like was something like: library(ts) data(nottem) data.stl <- stl(nottem, "per") x <- data.stl$sea This what I get: > x NULL I would, however, like to store in x the seasonal component. Thanks in advance. Francisco. -- Francisco

I have a data set of monthly river flows from 1960-2000, which are similar in structure to the nottem data: > klam.flow Oct Nov Dec Jan Feb Mar Apr May Jun Jul Aug Sep 1961 1461 1716 2524 1773 1906 2005 1756 1575 1387 983 1094 1382 1962 1907 2253 1985 1907 1769 1676 2634 1386 929 766 968 1309 ... I tried plotting with > ts.plot(klam.flow) Which quickly led me to

Hi all, How can the label of the x-axes in the plot() of a stl.object be adapted? e.g., When plotting: plot(stl(nottem, "per")) In the labels of the x-axes is “time”. How can this be changed to e.g., “Time (dekade) “? It does not work with xlab or others anymore… Thanks, Jan _______________________________________________________________________ Ir. Jan Verbesselt Research

Dear R-help, Reccently I've been working on sample size estimates for our forensic scientists and have to make the work accessible to them, preferably in some Windows based graphical form. The obvious choise was Tk via R, so I now have a couple of very nice, user friendly front ends for calculating betas and beta-binomials which run equally well under Windows and other systems (same code -

Hello, >From the date time stamps I see that not only do I have the results of the build in 'gnuwin32/front-ends' but I can also see the time stamps have changed in the main bin directory so I assume that the result of 'make all recommended' also copies the results there. Now on to the packages. I was interested in following the flow of 'stl' so I added the following

can you recommend a good manual for R that starts with a data set and gives demonstrations on what can be done using R? I downloadedR Langauage definition and An introduction to R but haven't found them overly useful. I'd really like to be able to follow some tutorials using a dataset or many datasets. The datasets I have available on R are Data sets in package 'datasets':

Hi All, I'm new to R and am trying to run a unit root test on the vector "y" (a time series of inflation (i.e. changes in the Consumer Price Index quarter on quarter)). I've run the Augmented-Dickey-Fuller Test below (R's URCA package). It gives me an error that it cannot find the function ur.df unless I comment out the third last line of code (see below). I try to call

Hi all, Does anyone know how ts objects ts(base) can be used within the 'seas' package? I would like to obtain seasonal statistics of regular time-series and for example look at the result of the plot.seas.var() function or use the change function() to look at change between periods or time-series. The nottem time-series are similar to the time-series we are analyzing (but with

Hi, i want to create an object which contains different classes: for example i have some time series and test if ARIMA models are best than HoltWinters models: for each of my time serie i want to collect in an unique object which model was the best: for some it will be an HoltWinters class and for some other an Arima class. is there any solution?? thanks in advance, with my best, erik sauleau

Hello everybody, I want to use the nnet library and my problem is that the algorithm seems to accept only class as target when the neural is fiiting. So the output when I use predict.nnet is also a class. Is it possible to have numeric variable as target ? If yes, what is the syntax ? Thank you. Cordialement, R?gis CHARIGNON

Hi, Assume that we may model the Nottingham temperature data (nottem) or Sunspot data (sunspot) set by a nonparametric autoregressive model of the form Yt = m(Yt-1) + et. Using the kernel estimation method, produce the resulting plots. We may use the fucntion tsmooth(x,y,"notmal",bandwidth=0.01). How can i define x and y using data nottem and sunspot?

Hi, This is actually a theory question. I'm a bit confused by the s.window parameter in the stl() function (which is in the ts package). For example, in the stl documentation it uses the nottem data, and then: plot(stl(nottem, s.win = 4, t.win = 50, t.jump = 1)) What does it mean by s.win = 4? Is it because a year has 4 seasons (namely Spring, Summer, Autumn and Winter)? If so will it

R-users, i have some time series and use HEGY seasonal UR tests in the uroot package. But i have problems with interpretation of t and F statistics. Is there any critical values for these tests in R? is anybody ever write a bootstrap of these tests? thanks for advance, with all my bests, erik. ================================= Erik-André SAULEAU SEAIM Centre Hospitalier 87, Avenue

Dear R-list, I try to use StructTS for some univariate time series, with a type="BSM". I have two questions: 1-in the "fitted" value of the object, it seems to me that for getting back fitted values, one have to add level, slope and seasonal (or "level" contains already the two other ones) 2-i am really circumspect about the results of "KalmanForecast"