On 26-07-2013, at 16:18, Przemek Gawin <arl3nu at gmail.com> wrote:
> This post has NOT been accepted by the mailing list yet.
> This post was updated on Jul 26, 2013; 4:40pm.
> Hello,
>
> Two days ago I started my journey with R, and right now I'm struck on
> Holtwinters, and have no idea, what I'm doing wrong. So now, I'll
show
> step by step what I've been doing. Actually it is a part of
"Introducy
> Time Series with R".
>
> 1) I download data from
> http://www.massey.ac.nz/~pscowper/ts/motororg.dat due to port
> blockage. Save it as motororg.txt
>
> 2) Inserting this code:
> Motor.dat <- read.table("motororg.txt", header = T)
> attach(Motor.dat)
> Comp.hw1 <- HoltWinters(complaints, beta = 0, gamma = 0)
>
> 3) Baang! Error here.
> "Error in decompose(ts(x[1L:wind], start = start(x), frequency = f),
> seasonal) :
> time series has no or less than 2 periods"
>
Your complaints vector is not a timeseries.
From the section Arguments of HoltWinters:
gamma parameter used for the seasonal component. If set to FALSE, an
non-seasonal model is fitted.
So use gamma=FALSE.
Don't use attach().
Use Motor.dat$complaints in the HoltWinter call
or
Comp.hw1 <- with(Motor.dat, HoltWinters(complaints, beta = 0, gamma =
FALSE))
Berend
> 4) Actually it has, and I turned it on with attach command?
>
> Motor.dat
> complaints
> 1 27
> 2 34
> 3 31
> 4 24
> 5 18
> 6 19
> 7 17
> 8 12
> 9 26
> 10 14
> 11 18
> 12 33
> 13 31
> 14 31
> 15 19
> 16 17
> 17 10
> 18 25
> 19 26
> 20 18
> 21 18
> 22 10
> 23 4
> 24 20
> 25 28
> 26 21
> 27 18
> 28 23
> 29 19
> 30 16
> 31 10
> 32 24
> 33 11
> 34 11
> 35 13
> 36 27
> 37 18
> 38 20
> 39 21
> 40 6
> 41 9
> 42 29
> 43 12
> 44 19
> 45 14
> 46 19
> 47 16
> 48 23
>
> Can you tell me what I am doing wrong?
>
> PS
>
> I tried to make complaints.ts as well but I didn't work either.
>
> ______________________________________________
> R-help at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide
http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.