similar to: Help with TimeSeries

Hi there! I´m a noob when it comes to R and I´m using it to run statisc analysis. With the code for ARIMA below I´m getting this error: Error in solve.default(res$hessian * n.used) :Lapack routine dgesv: system is exactly singular The code is: > s.ts <- ts(x[,7], start = 2004, fre=12) > get.best.arima <- function (x.ts, maxord=c(1,1,1,1,1,1)) + { + best.aic <- 1e8 + n <-

I tried toy problems and there doesn't seem to be a basic problem between lm() and ts objects: X = data.frame(x=c(1,2,7,9), y=c(7,2,3,1)) lm(y ~ x, X) X <- lapply(X, function(x) ts(x, frequency=12, start=c(1994,7))) lm(y ~ x, X) and this works fine - whether you do an lm() before or after making ts objects, it's okay. But I have a situation where things aren't okay.

Hi, suppose I have a time series rt. Why does this code not work? rt <- data n <- length(rt) - 2 at <- vector(length = n) at = rt-(3.75101e-04 + 9.61877e-02 * rt[-1] - 2.48071e-02 * rt[-2]) Thank you, Benjamin

Hello r-help, I have a couple of time-series of different length and I would like to produce a simple overview plot showing the autocorrelation functions of the series. The time-series are stored in a dataframe like this: > test.data item year value 1 xxx 1961 -1.09 2 xxx 1962 0.21 3 xxx 1963 -0.81 [trimmed] 8

Hello I have 2000 univariate timeSeries of about 20 observations each, as the following, I would like to store all of them in one object, sort of a data frame, and to be able to recall each by its column name, which by the way is the same as the first date. Do you know how can I do this. Thank you Felipe Parra GMT 2009-10-12 2009-10-12 0.002346171 2009-10-14 0.002346171 2009-10-21

Hello, Writing to seek help in regard to some unexpected performance anomaly i am observing in using tsoutlers:tso on the mac vs on an AWS cloud server.. I am running the following code with very small dataset of about 208 records. d.dir <- '/Users/darshanpandya/xxxxxx' FNAME <- 'my_data.csv' d.input <- fread(file.path(paste0(d.dir,"/zzz/"),FNAME,fsep =

Hi there, we are looking for a research assistant for a project on analysing timeseries in the field of educational research. We have timeseries of the subjective perception (I understand, I feel good, I am interested etc.) of 109 students (6 different courses, 26 to 72 hours of classroom teaching, 208 to 332 points of measurement). We want to do exemplary analysis of the interaction

Question on timeSeries and S4 classes: Consider the following: library(timeSeries) data <- rnorm(5) treg <- ts(data, frequency=4) t1 <- timeSeries(data, as.Date('2010-04-15') + 1:5) t2 <- as.timeSeries(treg) Now both t1 and t2 are timeSeries objects, yet t2 at ts is a valid slot, while t1 at ts is not. Thus the ts slot is optional. Sorry if I am misunderstanding the way S4

Hello, I try to simulate an ARMA-model using R, but I didn't find any function to generate such timeseries. In Splus there is the function arima.sim which generates AR-, MA- and ARIMA-series. Is there any similar in R? Best regards, Frank Beimfohr -.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.- r-help mailing list -- Read

Test for stationarity (pp-test). In R source code all other command executions I understood, but how I am getting the ssqrtl value ssqrtl <- .C ("R_pp_sum", as.vector(u,mode="double"), as.integer(n), as.integer(l), trm=as.double(ssqru), PACKAGE="ts") please explain the above command. Thanks in advance Ramesh [[alternative HTML version

What can I do? Thanks a lot! [[alternative HTML version deleted]]

Hi Guys, Need your wisdom on this. Say I have a time series (in zoo format) like this > x <- zoo(11:21) > x 1 2 3 4 5 6 7 8 9 10 11 11 12 13 14 15 16 17 18 19 20 21 I want to do a "moving window sampling" of it. The result can either be a matrix or a dataframe like this my.super.moving.window(x, length=3, by=1) 11 12 13 12 13 14 13 14 15 14 15 16 .... 18 19 20

Hi, I'm trying to plot time-series data where each sample breaks down the percentage of CPU time spent in each of four states (usr, nice, sys, idle) 19:08:15 %usr %nice %sys %idle 19:08:16 5 0 10 86 19:08:17 17 0 14 69 19:08:18 5 0 8 87 19:08:19 10 0 10 81 19:08:20 3 0 7 90 19:08:21 4 0 8

I have a timeseries object, ts, and want to get the first date in the series into a string so I can concatenate it with a SQL query. Input and output are shown below. I must be missing something very basic, but I can't seem to pry the data ("2008-07-01") into a string variable. Any suggestions would be appreciated. Thank you, Andrew =====script: class(ts) (ts[1,0]) #returns

Hi all. I'm suddenly having problems with the following: > FUT10Y<-read.table("C:\\FUT10YR.csv",header=TRUE,sep=",") > head(FUT10Y) Date PX_OPEN PX_HIGH PX_LOW PX_LAST 1 1/5/1999 119.0000 119.1875 118.5312 118.6250 2 1/6/1999 118.5938 118.8750 118.2812 118.8438 3 1/7/1999 118.9062 119.0312 118.3750 118.5000 4 1/8/1999 118.4688 118.5625 117.5312

Does anyone know why the following code hangs on the do.call, but works fine when I either comment out the require(timeSeries) or only do 2 levels of a for loop instead of 3? Thanks, Andrew Bierbryer require(timeSeries) num <- 1 x.list <- list() for ( i in 1:10 ) { for ( j in 1:20 ) { for ( k in 1:30 ) { x.list[[num]] <- cbind(num,10)

Hi, I try to calculate the correlation between macroeconomic data from FRED vs Market Data However, since the timeseries are not in synch, the correlation fails. require(quantmod) USPBS =get(getSymbols("USPBS", src="FRED" )) USPBS = USPBS['1983-1-1::'] monDMANEMP = Cl(to.monthly(USPBS)) > length(monDMANEMP) [1] 312 > head(monDMANEMP) USPBS.Close

Hello, I am using plot( ) function to plot time-series. it takes time-series object as an argument but i want to plot predicted data with training set, to compare them. is there any function available? Vibha [[alternative HTML version deleted]]

Hi I want to create a TimeSeries object with already defined dates (in the first vector) so that all the data are coerced as a time series object with the dates as they are. Is there anyone that have an idea what to do? 2010-07-07 3.900833 3.176667 2.754167 2.045833 1.820833 2010-04-21 4.256667 3.356667 2.700000 1.820000 1.576667 2010-02-17 4.322500 3.450000 2.670000 1.792500 1.492500

Dear R-Users, my dataset contains timeseries that are structured into task-specific epochs as labelled by a factor and a boolean variable for labelling each data-point within the series as artefact or non-artefact. Now there's no problem in addressing continuous task-specific time-series that are free from artefacts as long as artefacts extend to either boundary of adjacent timeseries but