SeriesA: Series A, Chemical Process Concentration Readings

In FitAR: Subset AR Model Fitting

Description

Chemical process concentration readings for every 2 hours.

Usage

data(SeriesA)

Format

ts object with attribute "title"

Details

Box and Jenkins (1970) fit an ARMA(1,1) and ARIMA(0,1,1) to this series. Cleveland(1971) suggested a subset AR(1,2,7). McLeod and Zhang (2006) fit a subset ARz(1,2,6,7) parameterized with the partial autocorrelations.

Source

Box and Jenkins (1970). Time Series Analysis: Forecasting and Control.

References

Cleveland, W.S. (1971) The inverse autocorrelations of a time series and their applications. Technometrics 14, 277-298.

McLeod, A.I. and Zhang, Y. (2006). Partial autocorrelation parameterization for subset autoregression. Journal of Time Series Analysis, 27, 599-612.

Examples

data(SeriesA)
#fit subset models
FitAR(SeriesA, c(1,2,7), ARModel="ARp")
FitAR(SeriesA, c(1,2,6,7), ARModel="ARz")

Example output

Loading required package: lattice
Loading required package: leaps
Loading required package: ltsa
Loading required package: bestglm
Chemical process concentrations
AR(7). LS Fit.
length of series = 197 ,  number of parameters = 3
loglikelihood = 232.962 ,  AIC = -459.9 ,  BIC =  -450.1 , UBIC =  -443
Chemical process concentrations
AR(7). MLE.  Mean estimated using the sample mean
length of series = 197 ,  number of parameters = 5
loglikelihood = 231.694 ,  AIC = -453.4 ,  BIC =  -437 , UBIC =  -430.9

FitAR documentation built on May 2, 2019, 3:22 a.m.