[R] simple plotting wcor (Rssa) question

Hello, I try to plot w-correlation matrix of singular spectrum analysis by using the package Rssa. This is an example: library(Rssa) s - ssa(co2) w - wcor(s, groups = 1:20) plot(w,cex.label=3),scales=list(at=c(10,20,30,40))) However cex.label dos not have any effect. Also I would like to

Re: [R] simple plotting wcor (Rssa) question

On 08/27/2014 11:18 AM, Ingo Wardinski wrote: Hello, I try to plot w-correlation matrix of singular spectrum analysis by using the package Rssa. This is an example: library(Rssa) s - ssa(co2) w - wcor(s, groups = 1:20) plot(w,cex.label=3),scales=list(at=c(10,20,30,40))) I was wrong

[R] using postscript() for multiple individual files

Hello, I try to plot some results of an analysis to multiple individual postscript files, like: postscript(A1_zonflow.ps,onefile=F) plot(s, type = vectors, idx = 1:12,main=) dev.off() # postscript(vectors_paired_zonflow.ps,onefile=F) plot(s, type = paired, idx = 1:12,plot.contrib =

Re: [R] using postscript() for multiple individual files

On 07/19/2014 01:25 PM, Duncan Murdoch wrote: On 19/07/2014, 5:41 AM, Ingo Wardinski wrote: Hello, I try to plot some results of an analysis to multiple individual postscript files, like: postscript(A1_zonflow.ps,onefile=F) plot(s, type = vectors, idx = 1:12,main=) dev.off

Re: [R] using postscript() for multiple individual files

On 07/19/2014 07:17 PM, William Dunlap wrote: Wrap all your calls to plot() with print(). E.g., change plot(s, type=vectors, idx=1:12, main=) to print(plot(s, type=vectors, idx=1:12, main=) Some plot methods require their output to be printed to display, some don't. Some help files

[R] prediction of time series with nearest neighbor

G'day, I wonder if there exists a package that deals with the prediction of time series based on a method proposed by Farmer Sidorowich (1987) and further developments by others. This method relies on the state space representation of a time series and uses the nearest neighbor of a state

[R] F-test question

G'day I try do compute some F-statistics of a singular spectrum analysis of a timeseries sv I run: require(Rssa) s - ssa(sv) summary(sv) Min. 1st Qu. MedianMean 3rd Qu.Max. -4.238 2.761 6.594 6.324 10.410 15.180 r1 - reconstruct(s,groups = list(1:5)) r2 -

[R] discontinous ssa forecast

Hello, I compute a singular spectrum ananlysis of a time series using ssa of the Rssa package. Then I compute the forecast based on the results of the singular spectrum ananlysis (ssa). Here I observe that the original time series and the forecast are discontinous. How can I force the forecast