Solved – Getting started with time series in R

rtime series

With some great help from this forum, I have been able to get up and running with some basic time series analysis in R. Right now, my needs are mostly univariate time series.

Here is my question:

I can read in daily data from database into a data frame. I have two columns, date which is understood by R as POSIXct and the second which is the value of interest and numeric. What is the best, most straightforward way to make this a ts object where R understands the start/end dates and represents daily observations dynamically? It seems to me that I shouldn't be required to (when coercing my object to a ts object) manually tell it the start and end dates when the data frame is already has it.

For some context, I have been able to aggregate other data from daily to weekly, but find myself doing things in ways that just seem long and unnecessary considering R already understands my raw data as time. As you can tell, I am new to R and time series in R, but I figure that since R is so powerful, there probably is a pretty easy way around my issues.

Best Answer

It seems like you need the package xts. Create your time serie using

install.packages('xts')
library(xts)
X = xts(coredata(DF[,2]), order.by=DF[,1])

Then you will be able to manipulate your data easily.

to.weekly(X)  
to.monthly(X)

Please note that you will then manipulate xts objects and not ts. But no worries, you can go back to ts whenever needed.

Related Solutions

Solved – Time series with multiple subjects and multiple variables in R

The Arima function in the forecast package can fit a regression model to the data with an ARIMA model for the errors. The order argument specifies the orders of the ARIMA model, while the argument xreg defines which data object contains the observations of the predictors. E.g., if xreg is a matrix of predictors:

model = Arima(series, order = c(1,1,0), xreg = covariates)

To find the order of the ARIMA process, you can simply use the auto.arima function also found in the forecast package. It automatically locates the best-fitting ARIMA model to the data, “fit” defined by one of three possible information criteria in the ic argument: the AIC (given by aic), the AICc (aicc), or the BIC (bic). E.g.,

model = auto.arima(series, ic = “aic”)

I think you may find this page really helpful, especially the section about R.

Solved – Decomposition of daily time series (several years) with multiple seasonal patterns

As @Aksakal wisely pointed out daily data analysis can reveal a ton of information. Look at http://www.autobox.com/cms/index.php/afs-university/intro-to-forecasting/doc_download/53-capabilities-presentation particularly slides 42-55 for a demonstration of this. One can break out daily-effects, weekly effects , monthly effects , level shifts . local trends in order to reveal pre,contemporary and lag effects of known events. If you wish you can post your data and I can demonstrate this for you. Please use an excel format and indicate the country as holiday effects can be quite different and the start date. If you have any user-suggested causal series like price/promotion etc please add additional columns to your data matrix.

EDIT AFTER RECEIPT OF DATA:

I took the last 5 years of daily data (1/1/2004-12/31/2008) enter image description here and used AUTOBOX in a totally automatic manner. The Actual/Fit and Forecast graph is here . The close-up / forecast for the next 31 days is and here . The plot of the model's residuals suggests sufficiency further supported by the acf of the model's residuals. . The equation is presented in the next 3 pix enter image description here and and . In summary Christmas , Halloween , New Year's and Thanksgiving are suggested important holidays along with a long-weekend effect around a holiday. The data is seasonal with respect to monthly effects and there are 4 day's of the week that appear to be statistically significant [saturday (+) ,sunday (-),monday(-) and tuesday (-) ].In addition there is an identifiable level shift upwards at 11/03/06 and a reversal at 10/31/07. There are significant seasonal pulses (read changes in day-of-the-week-effects at specific points in time ) and a large amount of pulses ( one-time irregularities). Since I started with the US calendar of holidays these outliers may reflect omitted variables ( e.g. Ramadan etc. ) and should be possibly matched to other events. I have presented here a an example listing of these exceptional days which might help you match up with possible new variables that you can add to the model.