Tim,
Given you have so little data - I would try
a) prefilter and forecast
Fit a fairly simple ARIMA(0,1,1) model to A and treat 8987 as an outlier -
then predict the fitted series AF with the 3 missing points as forecasts.
Fit another ARIMA(0,1,1) with 7688 as an outlier - then back cast to
look at zoo and ts, and it all depends on what you want to do.
I researched a bit.
I am looking at the application of different prediction methods
(predict.lm etc.) for time series.
I have two series of data.
One contains measurements of 30 years.
The other just 5 years. Both
Dear R-Users,
I put a small sample data set and script.
Aim: combine two partly overlapping series to one by prediction.
Problem: only overlapping data points are predicted.
Question: How do I predict data for rows 1-9 and 14-16?
Thanks in advance for your advince,
Tim
### CODE ###
x -
Hello,
I am currently working in the field of climate and environmental data
analysis which is a lot founded on the analysis, preparation and
combination of time series.
About a bit more than one year ago I started to use python and the
marvellous timeseries module [1]. Which offers a very
look at zoo and ts, and it all depends on what you want to do.
On Wed, Jan 7, 2009 at 2:27 PM, Tim Michelsen
timmichel...@gmx-topmail.de wrote:
Hello,
I am currently working in the field of climate and environmental data
analysis which is a lot founded on the analysis, preparation and
5 matches
Mail list logo
