Re: [R] Modeling Time Series with Missing Observations

2017-03-24 Thread Berend Hasselman
There is also a package imputeTS, which may be able to do what you want. It has a nice Introduction vignette and also appears to have nice plot functions Berend Hasselman > On 24 Mar 2017, at 02:11, David Winsemius wrote: > > There's also an irts-package "irregular time series" > > Sent fr

Re: [R] Modeling Time Series with Missing Observations

2017-03-23 Thread David Winsemius
There's also an irts-package "irregular time series" Sent from my iPhone > On Mar 23, 2017, at 3:42 PM, John C Frain wrote: > > Google "arima missing data r" will bring up several references including > http://stats.stackexchange.com/questions/104565/how-to-use-auto-arima-to-impute-missing-val

Re: [R] Modeling Time Series with Missing Observations

2017-03-23 Thread John C Frain
Google "arima missing data r" will bring up several references including http://stats.stackexchange.com/questions/104565/how-to-use-auto-arima-to-impute-missing-values. There are several other useful results in that search. John C Frain 3 Aranleigh Park Rathfarnham Dublin 14 Ireland www.tcd.ie/Ec

Re: [R] Modeling Time Series with Missing Observations

2017-03-23 Thread Jeff Newmiller
Even the most basic introduction to R discusses the use of NA for missing data. Injecting values that could be mistaken for actual readings is a dangerous approach. You can use the merge function to introduce missing rows into zoo objects or data frames. -- Sent from my phone. Please excuse my

[R] Modeling Time Series with Missing Observations

2017-03-23 Thread Paul Bernal
Dear all, Hope you are doing well. I am trying to model the historical number of transits of a particular market segment, but the problem is that I have missing data. I am working with monthly data, so I have 12 observations per year (in general). The problem is that, when I bring the data from t