Based on my very limited experience with ts, it does not handle daily data very well, which leaves us three options: change data to weekly, which I think is probably not acceptablez <- to.weekly(Ad(GSPC))[,4]

z.ts<-ts(as.vector(z),start=as.numeric(c(format(index(z)[1],"%Y"),format(index(z)[1],"%m"))),

frequency=52)

y <-forecast(z.ts)

summary(y)

plot(y)

or assume 365 days (not good for leap years and results are very strange)require(quantmod)

require(forecast)

getSymbols("^GSPC", from='2006-01-06', to=Sys.Date())

z <- Ad(GSPC)

z.ts<-ts(as.vector(z),start=as.numeric(c(format(index(z)[1],"%Y"),format(index(z)[1],"%m"),format(index(z)[1],"%d"))),

frequency=365)

y <-forecast(z.ts)

summary(y)

plot(y) or convert to xts and then plot (ugly example but should get you started)y.xts <- as.xts(cbind(

c(y$x,y$upper[,1]),

c(y$x,y$upper[,2]),

c(y$x,y$lower[,1]),

c(y$x,y$lower[,2]),

c(y$x,rep(y$x[NROW(y$x)],NROW(y$upper)))),

c(index(z),index(last(z))+1:NROW(y$upper)))

plot.zoo(y.xts,screens=1,col=c(2:5,1)) Kenttimelyportfolio.blogspot.com

> Date: Sat, 26 May 2012 14:51:54 -0400

> From:

[hidden email]
> To:

[hidden email]
> Subject: [R-SIG-Finance] plotting with dates

>

> How do I get this to plot with dates ? The x-axis is coming through with

> numbers.

>

> require(quantmod)

> require(forecast)

> getSymbols("^GSPC", from='2006-01-06', to=Sys.Date())

> z <- Ad(GSPC)

> y <-forecast(z)

> summary(y)

> plot(y)

>

> [[alternative HTML version deleted]]

>

> _______________________________________________

>

[hidden email] mailing list

>

https://stat.ethz.ch/mailman/listinfo/r-sig-finance> -- Subscriber-posting only. If you want to post, subscribe first.

> -- Also note that this is not the r-help list where general R questions should go.

[[alternative HTML version deleted]]

_______________________________________________

[hidden email] mailing list

https://stat.ethz.ch/mailman/listinfo/r-sig-finance-- Subscriber-posting only. If you want to post, subscribe first.

-- Also note that this is not the r-help list where general R questions should go.