[R] help in neural networks package for simple 1d tsa-prediction

c2r freenetmail4 at freenet.de
Mon Apr 18 13:06:45 CEST 2011

I am also looking for a sample to predict values for a simple 1d time series.
I did look at various library-samples as in
neuralnet,AMORE,nnet,RSNNS,Qrnn,monmlp e.t.c. 
but did not find a simple 1d-sample that forecasts like in the following
simple arima-sample:

x = arima.sim(list(order=c(1,0,1), ar=.9, ma=-.5), n=100) # simulate some
x.fit = arima(x, order = c(1, 0, 1)) # fit the model and print the results
x.fore=predict(x.fit, n.ahead=10)  
# plot the forecasts
U = x.fore$pred + 2*x.fore$se
L = x.fore$pred - 2*x.fore$se
ts.plot(x,x.fore$pred,col=1:2, ylim=c(minx,maxx))
lines(U, col="blue", lty="dashed")
lines(L, col="blue", lty="dashed") 

Did you meanwhile find a working sample or can anyone show a nn-sample here
to predict
the arima.sim series x from above sample with ploting the next 10 forecasted
values ?

View this message in context: http://r.789695.n4.nabble.com/help-in-neural-networks-package-tp2133927p3457207.html
Sent from the R help mailing list archive at Nabble.com.

More information about the R-help mailing list