[R] Fitting Arima Model to Daily Time Series

[Jose Iparraguirre]

Paul
Good you ask because as far as I can remember (some people in the forum are experts on both time series and how R handles time series), it's not advisable to use the ts() function in the base package when dealing with daily observations (because of leap years, mostly).

Therefore, you need to use the packages zoo or xts, as explained here:  http://stackoverflow.com/questions/8437620/analyzing-daily-weekly-data-using-ts-in-r 
You can also use the package timeSeries. If you need to take into account weekdays or weekends (that depends on your research question and modelling, of course), R can do it for you as well.

Best,

José




From: Paul Bernal [mailto:paulbernal07 at gmail.com] 
Sent: 11 September 2013 15:41
To: Jose Iparraguirre
Cc: r-help at r-project.org
Subject: Re: [R] Fitting Arima Model to Daily Time Series

Dear Jose, good morning,

First of all, let me thank you for your extremely valuable help. Now I have a question for you:

I have a table containing two fields, the first one is date and the second one is number of transits of vessels. This table contains daily observations for the past 5 years.

The date field has the following format: YYYY-MM-DD

The number of transits field is a regular numeric field.

How can I do to convert this table into a time series object?

Best regards,

Paul



2013/9/11 Jose Iparraguirre <Jose.Iparraguirre at ageuk.org.uk>
Hi Paul,

There are different packages in R to fit an ARIMA model. I would use the forecast package.
In your case, perhaps you would want to explore SARIMA models to include seasonal components?
Anyhow, the first port of call could be the auto.arima() function to select the best fitting representation according to AIC, AICc or BIC -but explore other representations as well.
To fit the models use the function Arima (note the capital "A"). The documentation in the package is very clear and comprehensive; the authors (Rob J Hyndman and George Athanasopoulos) published a free on-line book which will also help you: http://otexts.com/fpp/.
Hope this helps,

José


Prof. José Iparraguirre
Chief Economist
Age UK



-----Original Message-----
From: r-help-bounces at r-project.org [mailto:r-help-bounces at r-project.org] On Behalf Of Paul Bernal
Sent: 10 September 2013 22:54
To: r-help at r-project.org
Subject: [R] Fitting Arima Model to Daily Time Series

Hello everyone,

Hope everyone is doing great. I would like to know how to use the arima function in R to fit arima or arma models to daily data, that is, with period = 365, this taking into account the fact that I have 5 years worth of daily data (so 365 * 5 = my number of observations).

All I want is a very general line of code of I I would do to fit the arima model.

Any help will be greatly appreciated,

Have a wonderful day,

Paul
        [[alternative HTML version deleted]]

______________________________________________
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.

The Wireless from Age UK | Radio for grown-ups.

www.ageuk.org.uk/thewireless


If you're looking for a radio station that offers real variety, tune in to The Wireless from Age UK.
Whether you choose to listen through the website at www.ageuk.org.uk/thewireless, on digital radio (currently available in London and Yorkshire) or through our TuneIn Radio app, you can look forward to an inspiring mix of music, conversation and useful information 24 hours a day.




-------------------------------
Age UK is a registered charity and company limited by guarantee, (registered charity number 1128267, registered company number 6825798).
Registered office: Tavis House, 1-6 Tavistock Square, London WC1H 9NA.

For the purposes of promoting Age UK Insurance, Age UK is an Appointed Representative of Age UK Enterprises Limited, Age UK is an Introducer
Appointed Representative of JLT Benefit Solutions Limited and Simplyhealth Access for the purposes of introducing potential annuity and health
cash plans customers respectively.  Age UK Enterprises Limited, JLT Benefit Solutions Limited and Simplyhealth Access are all authorised and
regulated by the Financial Services Authority.
------------------------------

This email and any files transmitted with it are confide...{{dropped:24}}