Assembly: ImslCS (in ImslCS.dll) Version: 6.5.0.0
Syntax
C# |
---|
[SerializableAttribute] public class ARMAOutlierIdentification |
Visual Basic (Declaration) |
---|
<SerializableAttribute> _ Public Class ARMAOutlierIdentification |
Visual C++ |
---|
[SerializableAttribute] public ref class ARMAOutlierIdentification |
Remarks
Consider a univariate time series that can be described by the following multiplicative seasonal ARIMA model of order :
Here, . B is the lag operator, , is a white noise process, and denotes the mean of the series .Outlier detection and parameter estimation
In general, is not directly observable due to the influence of outliers. Chen and Liu (1993) distinguish between four types of outliers: innovational outliers (IO), additive outliers (AO), temporary changes (TC) and level shifts (LS). If an outlier occurs as the last observation of the series, then Chen and Liu's algorithm is unable to determine the outlier's classification. In class ARMAOutlierIdentification, such an outlier is called a UI (unable to identify) and is treated as an innovational outlier.
In order to take the effects of multiple outliers occurring at time points into account, Chen and Liu consider the following model:
Here, is the observed outlier contaminated series, and and denote the magnitude and dynamic pattern of outlier j, respectively. is an indicator function that determines the temporal course of the outlier effect, otherwise. Note that operates on via .The last formula shows that the outlier free series can be obtained from the original series by removing all occurring outlier effects:
The different types of outliers are characterized by different values for :- for an innovational outlier,
- for an additive outlier,
- for a level shift outlier and
- for a temporary change outlier.
Class ARMAOutlierIdentification is an implementation of Chen and Liu's algorithm. It determines the coefficients in and and the outlier effects in the model for the observed series jointly in three stages. The magnitude of the outlier effects is determined by least squares estimates. Outlier detection itself is realized by examination of the maximum value of the standardized statistics of the outlier effects. For a detailed description, see Chen and Liu's original paper (1993).
Intermediate and final estimates for the coefficients in and are computed by the Compute methods from classes ARMA and ARMAMaxLikelihood. If the roots of or lie on or within the unit circle, then the algorithm stops with an appropriate exception. In this case, different values for p and q should be tried.
Forecasting
From the relation between original and outlier free series,
it follows that the Box-Jenkins forecast at origin t for lead time l, , can be computed as Therefore, computation of the forecasts for is done in two steps:- Computation of the forecasts for the outlier free series .
- Computation of the forecasts for the original series by adding the multiple outlier effects to the forecasts for .
Step 1: Computation of the forecasts for the outlier free series
Since
where the Box-Jenkins forecast at origin t for lead time l, , can be computed recursively as Here, andStep 2: Computation of the forecasts for the original series by adding the multiple outlier effects to the forecasts for
The formulas for for the different types of outliers are as follows:
Innovational outlier (IO)
Additive outliers (AO)
Level shifts (LS)
Temporary changes (TC)
Innovational outliers (IO)
Additive outliers (AO)
Level shifts (LS)
Temporary changes (TC)
From these formulas, the forecasts can be computed easily. The percent probability limits for and are given by where is the percentile of the standard normal distribution, is an estimate of the variance of the random shocks, and the weights are the coefficients in For a detailed explanation of these concepts, see chapter 5:"Forecasting" in Box, Jenkins and Reinsel (1994).