com.imsl.stat.AutoARIMA

All Implemented Interfaces:: Serializable, Cloneable

public class AutoARIMA extends Object implements Serializable, Cloneable

Automatically identifies time series outliers, determines parameters of a multiplicative seasonal $\text{ARIMA}(p,0,q)\times(0,d,0)_s $ model and produces forecasts that incorporate the effects of outliers whose effects persist beyond the end of the series.

Class AutoARIMA determines the parameters of a multiplicative seasonal $\text{ARIMA}(p,0,q) \times (0,d,0)_s$ model, and then uses the fitted model to identify outliers and prepare forecasts. The order of this model can be specified or automatically determined through use of an overloaded compute method. Potential missing values in the time series are estimated prior to the parameter and outlier computations.

The $\text{ARIMA}(p,0,q) \times (0,d,0)_s$ model handled by class AutoARIMA has the following form:

$$\phi(B)\Delta_s^d(Y_t-\mu)=\theta(B)a_t,\;t=1,2, \ldots,n,$$ where $$\phi(B)= 1-\phi_1B-\phi_2B^2-\ldots-\phi_pB^p,\; \theta(B)=1-\theta_1B-\theta_2B^2-\ldots-\theta_qB^q,\;\Delta_s^d=(1-B_s)^d $$ and $$B^kY_t = Y_{t-k}$$

It is assumed that all roots of $\phi(B)$ and $\theta(B)$ lie outside the unit circle. Clearly, if $s=1$ the model reduces to the traditional $ \text{ARIMA}(p,d,q)$ model.

$Y_t$ is the unobserved, outlier-free time series with mean $\mu$, and white noise $a_t$. This model is referred to as the underlying, outlier-free model. Class AutoARIMA does not assume that this series is observable. It assumes that the observed values might be contaminated by one or more outliers, whose effects are added to the underlying outlier-free series: $$Y_t^\ast = Y_t+\mbox{outlierEffect}_t\,$$

Outlier identification uses the algorithm developed by Chen and Liu (1993). Outliers are classified into 1 of 5 types:

innovational
additive
level shift
temporary change and
unable to identify

Once the model parameters are estimated and the outliers are identified, class AutoARIMA estimates $Y_t$, the outlier-free series representation of the data, by removing the estimated outlier effects. Parameter estimation and outlier detection are based on methods from class ARMAOutlierIdentification.

Using the information about the adjusted $\text{ARIMA}(p,0,q) \times (0,d,0)_s$ model and the removed outliers, forecasts are then prepared for the outlier-free series. Outlier effects are added to these forecasts to produce a forecast for the observed series, $Y_t^\ast $. If there are no outliers, then the forecasts for the outlier-free series and the observed series will be identical.

Model selection techniques

Users have an option of either specifying specific values for $p,\, q,\,s,\,d$ or have class AutoARIMA automatically select best fit values. Model selection can be conducted in one of three ways listed below depending upon which compute method of class AutoARIMA is invoked.

Technique 1: Automatic ${\bf\text{ARIMA}}(p,0,0) \times(0,d,0)_s$ Selection

This technique, chosen by use of method compute(int maxlag), tries to fit a model of the form $$\phi(B)\Delta_s^d (Y_t-\mu) = a_t$$ to the outlier free series $Y_t$.

It initially searches for the $\text{AR}(p)$ representation with minimum value of the chosen information criterion (AIC, AICC or BIC) for the noisy data, where $p=0,\ldots,\text{maxlag} $.

If the user calls methods setPeriods and setDifferenceOrders prior to invoking the compute method, then the values in arrays periods and orders are included in the search to find an optimum $\text{ARIMA}(p,0,0) \times(0,d,0)_s$ representation of the series. Here, every possible combination of values for s, d in periods and orders, respectively, are examined. The best found model order is then used as input for the parameter and outlier detection routine.

The optimum values for p, q, s and d are returned through method getOptimumModelOrder.

Technique 2: Grid Search

This technique, chosen by means of method compute(int[] arOrders, int[] maOrders), conducts a grid search for p and q using all possible combinations of candidate values in arOrders and maOrders.

If methods setPeriods and setDifferenceOrders are called prior to invoking the compute method, then the grid search is extended to include the candidate values for s and d given in arrays periods and orders, respectively.

If method setDifferenceOrders is not called prior to compute, then $d=0$ by default, and therefore no seasonal adjustment is attempted. The grid search is then restricted to searching for optimum values of p and q only.

The optimum values for p, q, s and d are contained in the array returned by method getOptimumModelOrder.

Technique 3: Specified ${\bf\text{ARIMA}}(p,0,q) \times(0,d,0)_s$ Model

In the third technique, selectable by means of method compute(int p, int q, int s, int d), specific values for p, q, s and d are given. This technique has essentially the same functionality as class ARMAOutlierIdentification but with the additional option of missing value estimation.

Outliers

The algorithm of Chen and Liu (1993) is used to identify outliers. The number of outliers identified is returned via method getNumberOfOutliers. Both the time and classification for these outliers are contained in the matrix returned by method getOutlierStatistics. Outliers are classified into one of five categories based upon the standardized statistic for each outlier type. The time at which the outlier occurred is given in the first column of the returned matrix. The outlier identifier returned in the second column is according to the descriptions in the following table:

Outlier Identifier	Name	General Description
`INNOVATIONAL`	Innovational Outlier (IO)	Innovational outliers persist. That is, there is an initial impact at the time the outlier occurs. This effect continues in a lagged fashion with all future observations. The lag coefficients are determined by the coefficients of the underlying $\text{ARIMA}(p,0,q)\times(0,d,0)_s $ model.
`ADDITIVE`	Additive Outlier (AO)	Additive outliers do not persist. As the name implies, an additive outlier affects only the observation at the time the outlier occurs. Hence additive outliers have no effect on future forecasts.
`LEVEL_SHIFT`	Level Shift (LS)	Level shift outliers persist. They have the effect of either raising or lowering the mean of the series starting at the time the outlier occurs. This shift in the mean is abrupt and permanent.
`TEMPORARY_CHANGE`	Temporary Change (TC)	Temporary change outliers persist and are similar to level shift outliers with one major exception. Like level shift outliers, there is an abrupt change in the mean of the series at the time this outlier occurs. However, unlike level shift outliers, this shift is not permanent. The TC outlier gradually decays, eventually bringing the mean of the series back to its original value. The rate of this decay is modeled using method `setDelta`. The default of `delta = 0.7` is the value recommended for general use by Chen and Liu (1993).
`UNABLE_TO_IDENTIFY`	Unable to Identify (UI)	If an outlier is identified as the last observation, then the algorithm is unable to determine the outlier's classification. For forecasting, a UI outlier is treated as an IO outlier. That is, its effect is lagged into the forecasts.

Except for additive outliers (AO), the effect of an outlier persists to observations following that outlier. Forecasts produced by methods of class AutoARIMA take this into account.

For more information on forecasting an outlier contaminated series, see the description of class ARMAOutlierIdentification.

See Also:

Nested Class Summary

Nested Classes

Modifier and Type

Class

Description

static class

AutoARIMA.NoAcceptableModelFoundException

No appropriate ARIMA model could be found.
Field Summary

Fields

Modifier and Type

Field

Description

static final int

ADDITIVE

Indicates detection of an additive outlier.

static final int

AIC

Indicates that Akaike's information criterion (AIC) is used in the optimum model determination.

static final int

AICC

Indicates that Akaike's corrected information criterion (AICC) is used in the optimum model determination.

static final int

BIC

Indicates that the Bayesian information criterion (BIC) is used in the optimum model determination.

static final int

INNOVATIONAL

Indicates detection of an innovational outlier.

static final int

LEVEL_SHIFT

Indicates detection of a level shift outlier.

static final int

TEMPORARY_CHANGE

Indicates detection of a temporary change outlier.

static final int

UNABLE_TO_IDENTIFY

Indicates detection of an outlier that cannnot be categorized.
Constructor Summary

Constructors

Constructor

Description

AutoARIMA(int[] times, double[] x)

Constructor for AutoARIMA.
Method Summary

Modifier and Type

Method

Description

final void

compute(int maxlag)

Estimates potential missing values, detects and determines outliers and simultaneously fits an optimum model from a set of different $ \text{ARIMA}(p,0,0)\times(0,d,0)_s$ models to the outlier free time series.

final void

compute(int[] arOrders, int[] maOrders)

Estimates potential missing values, detects and determines outliers and simultaneously fits an optimum model from a set of different $ \text{ARIMA}(p,0,q)\times(0,d,0)_s$ models to the outlier free time series.

final void

compute(int p, int q, int s, int d)

Estimates potential missing values, detects and determines outliers and simultaneously fits an $\text{ARIMA}(p,0,q)\times(0,d,0)_s $ model to the outlier free time series.

final void

forecast(int nForecast)

Computes forecasts, associated probability limits and $\psi$ weights for the given outlier contaminated time series.

double

getAIC()

Returns Akaike's information criterion (AIC) for the optimum model.

double

getAICC()

Returns Akaike's Corrected Information Criterion (AICC) for the optimum model.

double[]

getAR()

Returns the final autoregressive parameter estimates of the optimum model.

double

getBIC()

Returns the Bayesian Information Criterion (BIC) for the optimum model.

int[]

getCompleteTimes()

Returns all time points at which the original series was observed, including values for times with missing values in x.

double[]

getCompleteTimeSeries()

Returns the original series with potentially missing values replaced by estimates.

double

getConstant()

Returns the constant parameter estimate for the optimum model.

double[]

getDeviations()

Returns the deviations used for calculating the forecast confidence limits.

double[]

getForecast()

Returns forecasts for the original outlier contaminated series.

double[]

getMA()

Returns the final moving average parameter estimates of the optimum model.

int

getNumberOfOutliers()

Returns the number of outliers detected.

int[]

getOptimumModelOrder()

Returns the order $(p,0,q)\times(0,d,0)_s$ of the optimum model.

double[]

getOutlierFreeForecast()

Returns forecasts for the outlier free series.

double[]

getOutlierFreeSeries()

Returns the outlier free series.

int[][]

getOutlierStatistics()

Returns the outlier statistics.

double[]

getPsiWeights()

Returns the $\psi$ weights of the infinite order moving average form of the model.

double[]

getResiduals()

Returns the residuals.

double

getResidualStandardError()

Returns the residual standard error of the outlier free series.

void

setAccuracyTolerance(double epsilon)

Sets the tolerance value controlling the accuracy of the parameter estimates.

void

setConfidence(double confidence)

Sets the confidence level for calculating confidence limit deviations returned by getDeviations.

void

setCriticalValue(double critical)

Sets the critical value used as a threshold during outlier detection.

void

setDelta(double delta)

Sets the dampening effect parameter.

void

setDifferenceOrders(int[] orders)

Defines the orders of the periodic differences used in the determination of the optimum model.

void

setMaximumARLag(int maxARLag)

Defines the maximum AR lag used in the determination of the optimum (s,d) combination of method compute(int[] arOrders, int[] maOrders).

void

setModelSelectionCriterion(int infoCriterion)

Sets the model selection criterion.

void

setPeriods(int[] periods)

Defines the periods used in the determination of the optimum model.

void

setRelativeError(double relativeError)

Sets the stopping criterion for use in the nonlinear equation solver.

Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Field Details
- INNOVATIONAL
  
  public static final int INNOVATIONAL
  
  Indicates detection of an innovational outlier.
  See Also:
  
  Constant Field Values
- ADDITIVE
  
  public static final int ADDITIVE
  
  Indicates detection of an additive outlier.
  See Also:
  
  Constant Field Values
- LEVEL_SHIFT
  
  public static final int LEVEL_SHIFT
  
  Indicates detection of a level shift outlier.
  See Also:
  
  Constant Field Values
- TEMPORARY_CHANGE
  
  public static final int TEMPORARY_CHANGE
  
  Indicates detection of a temporary change outlier.
  See Also:
  
  Constant Field Values
- UNABLE_TO_IDENTIFY
  
  public static final int UNABLE_TO_IDENTIFY
  
  Indicates detection of an outlier that cannnot be categorized.
  See Also:
  
  Constant Field Values
- AIC
  
  public static final int AIC
  
  Indicates that Akaike's information criterion (AIC) is used in the optimum model determination.
  See Also:
  
  Constant Field Values
- AICC
  
  public static final int AICC
  
  Indicates that Akaike's corrected information criterion (AICC) is used in the optimum model determination.
  See Also:
  
  Constant Field Values
- BIC
  
  public static final int BIC
  
  Indicates that the Bayesian information criterion (BIC) is used in the optimum model determination.
  See Also:
  
  Constant Field Values
Constructor Details
- AutoARIMA
  
  public AutoARIMA(int[] times, double[] x)
  
  Constructor for AutoARIMA.
  
  Parameters:
  
  times - an int array of length nObs, where nObs is the number of observed time series values, containing the time points $t_1,\ldots,t_{\text{nObs}}$ at which the time series was observed. It is required that $t_1,\ldots,t_{\text{nObs}}$ are in strictly increasing order. Times for missing values are identified as non-incremental gaps in this series. A gap of missing values in x is assumed if the difference between two consecutive values is greater than 1, i.e. $t_{i+1}-t_i>1$. The difference is the number of missing values in the gap.
  
  x - a double array containing the observations $Y_1^\ast,Y_2^\ast,\ldots,Y_{\text{nObs}}^\ast $ at the times given in array times. This series can contain outliers and missing observations.

Method Details

compute

public final void compute(int maxlag) throws ARMA.MatrixSingularException, ARMA.TooManyCallsException, ARMA.IncreaseErrRelException, ARMA.NewInitialGuessException, ARMA.IllConditionedException, ARMA.TooManyITNException, ARMA.TooManyFcnEvalException, ARMA.TooManyJacobianEvalException, ARAutoUnivariate.TriangularMatrixSingularException, ARMAMaxLikelihood.NonInvertibleException, ARMAMaxLikelihood.NonStationaryException, ZeroPolynomial.DidNotConvergeException, SingularMatrixException, ARMA.ResidualsTooLargeException, AutoARIMA.NoAcceptableModelFoundException

Estimates potential missing values, detects and determines outliers and simultaneously fits an optimum model from a set of different $ \text{ARIMA}(p,0,0)\times(0,d,0)_s$ models to the outlier free time series.

Parameters:

maxlag - the maximum value for p allowed when fitting $\text{ARIMA}(p,0,0)\times(0,d,0)_s$ models to the given series, $0\le p\le \text{maxlag}$. It is required that $ 1 \le \text{maxlag} \le$ x.length. The optimum $\text{ARIMA}(p,0,0)\times(0,d,0)_s$ model is determined according to the model selection criterion chosen by the user, see method setModelSelectionCriterion.

Throws:

ARMA.MatrixSingularException - is thrown if the input matrix is singular.

ARMA.TooManyCallsException - is thrown if the number of calls to the function has exceeded the maximum number of iterations times the number of moving average (MA) parameters + 1.

ARMA.IncreaseErrRelException - is thrown if the bound for the relative error is too small.

ARMA.NewInitialGuessException - is thrown if the iteration has not made good progress.

ARMA.IllConditionedException - is thrown if the problem is ill-conditioned.

ARMA.TooManyITNException - is thrown if the maximum number of iterations is exceeded.

ARMA.TooManyFcnEvalException - is thrown if the maximum number of function evaluations is exceeded.

ARMA.TooManyJacobianEvalException - is thrown if the maximum number of Jacobian evaluations is exceeded.

ARAutoUnivariate.TriangularMatrixSingularException - is thrown if the input matrix to ARAutoUnivariate is singular.

ARMAMaxLikelihood.NonInvertibleException - is thrown if the intermediate or final maximum likelihood estimates for the time series are noninvertible.

ARMAMaxLikelihood.NonStationaryException - is thrown if the intermediate or final maximum likelihood estimates for the time series are non-stationary.

ARMAMaxLikelihood.InitialMAException - is thrown if the initial values provided for the moving average terms are noninvertible. In this case, ARMAMaxLikelihood terminates and does not compute the time series estimates.

ZeroPolynomial.DidNotConvergeException - is thrown if the algorithm computing the roots of the AR- or MA- polynomial does not converge.

SingularMatrixException - is thrown if during the computation of a small perturbation of the matrix product $A^TA$, it is found that A, the matrix used in the determination of the $\omega$ weights, is singular.

ARMA.ResidualsTooLargeException - is thrown if the residuals computed in one step of the Least Squares estimation of the ARMA coefficients become too large.

AutoARIMA.NoAcceptableModelFoundException - is thrown if no appropriate ARIMA model for the given time series could be found.
compute

public final void compute(int[] arOrders, int[] maOrders) throws ARMA.MatrixSingularException, ARMA.TooManyCallsException, ARMA.IncreaseErrRelException, ARMA.NewInitialGuessException, ARMA.IllConditionedException, ARMA.TooManyITNException, ARMA.TooManyFcnEvalException, ARMA.TooManyJacobianEvalException, ARAutoUnivariate.TriangularMatrixSingularException, ARMAMaxLikelihood.NonInvertibleException, ARMAMaxLikelihood.NonStationaryException, ZeroPolynomial.DidNotConvergeException, SingularMatrixException, ARMA.ResidualsTooLargeException, AutoARIMA.NoAcceptableModelFoundException

Estimates potential missing values, detects and determines outliers and simultaneously fits an optimum model from a set of different $ \text{ARIMA}(p,0,q)\times(0,d,0)_s$ models to the outlier free time series.

Parameters:

arOrders - an int array containing all possible AR orders to consider in the optimum model search. It is required that all values in arOrders are greater than or equal to zero.

maOrders - an int array containing all possible MA orders to consider in the optimum model search. It is required that all values in maOrders are greater than or equal to zero.

Throws:

ARMA.MatrixSingularException - is thrown if the input matrix is singular.

ARMA.TooManyCallsException - is thrown if the number of calls to the function has exceeded the maximum number of iterations times the number of moving average (MA) parameters + 1.

ARMA.IncreaseErrRelException - is thrown if the bound for the relative error is too small.

ARMA.NewInitialGuessException - is thrown if the iteration has not made good progress.

ARMA.IllConditionedException - is thrown if the problem is ill-conditioned.

ARMA.TooManyITNException - is thrown if the maximum number of iterations is exceeded.

ARMA.TooManyFcnEvalException - is thrown if the maximum number of function evaluations is exceeded.

ARMA.TooManyJacobianEvalException - is thrown if the maximum number of Jacobian evaluations is exceeded.

ARAutoUnivariate.TriangularMatrixSingularException - is thrown if the input matrix to ARAutoUnivariate is singular.

ARMAMaxLikelihood.NonInvertibleException - is thrown if the intermediate or final maximum likelihood estimates for the time series are noninvertible.

ARMAMaxLikelihood.NonStationaryException - is thrown if the intermediate or final maximum likelihood estimates for the time series are non-stationary.

ARMAMaxLikelihood.InitialMAException - is thrown if the initial values provided for the moving average terms are noninvertible. In this case, ARMAMaxLikelihood terminates and does not compute the time series estimates.

ZeroPolynomial.DidNotConvergeException - is thrown if the algorithm computing the roots of the AR- or MA- polynomial does not converge.

SingularMatrixException - is thrown if during the computation of a small perturbation of the matrix product $A^TA$, it is found that A, the matrix used in the determination of the $\omega$ weights, is singular.

ARMA.ResidualsTooLargeException - is thrown if the residuals computed in one step of the Least Squares estimation of the ARMA coefficients become too large.

AutoARIMA.NoAcceptableModelFoundException - is thrown if no appropriate ARIMA model for the given time series could be found.
compute

public final void compute(int p, int q, int s, int d) throws ARMA.MatrixSingularException, ARMA.TooManyCallsException, ARMA.IncreaseErrRelException, ARMA.NewInitialGuessException, ARMA.IllConditionedException, ARMA.TooManyITNException, ARMA.TooManyFcnEvalException, ARMA.TooManyJacobianEvalException, ARAutoUnivariate.TriangularMatrixSingularException, ARMAMaxLikelihood.NonInvertibleException, ARMAMaxLikelihood.NonStationaryException, ZeroPolynomial.DidNotConvergeException, SingularMatrixException, ARMA.ResidualsTooLargeException, AutoARIMA.NoAcceptableModelFoundException

Estimates potential missing values, detects and determines outliers and simultaneously fits an $\text{ARIMA}(p,0,q)\times(0,d,0)_s $ model to the outlier free time series.

Parameters:

p - a non-negative scalar int, the order of the AR part of the model.

q - a non-negative scalar int, the order of the MA part of the model.

s - a positive scalar int, the period of the difference used in the model.

d - a non-negative scalar int, the order of the difference used in the model.

Throws:

ARMA.MatrixSingularException - is thrown if the input matrix is singular.

ARMA.TooManyCallsException - is thrown if the number of calls to the function has exceeded the maximum number of iterations times the number of moving average (MA) parameters + 1.

ARMA.IncreaseErrRelException - is thrown if the bound for the relative error is too small.

ARMA.NewInitialGuessException - is thrown if the iteration has not made good progress.

ARMA.IllConditionedException - is thrown if the problem is ill-conditioned.

ARMA.TooManyITNException - is thrown if the maximum number of iterations is exceeded.

ARMA.TooManyFcnEvalException - is thrown if the maximum number of function evaluations is exceeded.

ARMA.TooManyJacobianEvalException - is thrown if the maximum number of Jacobian evaluations is exceeded.

ARAutoUnivariate.TriangularMatrixSingularException - is thrown if the input matrix to ARAutoUnivariate is singular.

ARMAMaxLikelihood.NonInvertibleException - is thrown if the intermediate or final maximum likelihood estimates for the time series are noninvertible.

ARMAMaxLikelihood.NonStationaryException - is thrown if the intermediate or final maximum likelihood estimates for the time series are non-stationary.

ARMAMaxLikelihood.InitialMAException - is thrown if the initial values provided for the moving average terms are noninvertible. In this case, ARMAMaxLikelihood terminates and does not compute the time series estimates.

ZeroPolynomial.DidNotConvergeException - is thrown if the algorithm computing the roots of the AR- or MA- polynomial does not converge.

SingularMatrixException - is thrown if during the computation of a small perturbation of the matrix product $A^TA$, it is found that A, the matrix used in the determination of the $\omega$ weights, is singular.

ARMA.ResidualsTooLargeException - is thrown if the residuals computed in one step of the Least Squares estimation of the ARMA coefficients become too large.

AutoARIMA.NoAcceptableModelFoundException - is thrown if no appropriate ARIMA model for the given time series could be found.
setPeriods

public void setPeriods(int[] periods)

Defines the periods used in the determination of the optimum model.

Parameters:

periods - an int array containing all possible periods that can be applied to the original series after insertion of missing values. All elements of periods must be positive. By default, periods is a one-element array with periods[0] = 1;
setDifferenceOrders

public void setDifferenceOrders(int[] orders)

Defines the orders of the periodic differences used in the determination of the optimum model.

Parameters:

orders - an int array containing all possible orders for each difference given in periods. All elements in orders must be non-negative. By default, orders is a one-element array with orders[0] = 0.
setMaximumARLag

public void setMaximumARLag(int maxARLag)

Defines the maximum AR lag used in the determination of the optimum (s,d) combination of method compute(int[] arOrders, int[] maOrders).

Parameters:

maxARLag - a scalar int, the maximum AR lag used in the computation of the optimum (s,d) combination for method compute(int[] arOrders, int[] maOrders). It is required that maxARLag is greater than zero and smaller than the original series after replacement of potential missing values. By default, maxARLag = 10.
getOptimumModelOrder

public int[] getOptimumModelOrder()

Returns the order $(p,0,q)\times(0,d,0)_s$ of the optimum model. Note that one of the compute methods must be invoked first before calling this method. Otherwise, an IllegalStateException exception is thrown.

Returns:

an int array of length 4 containing the values p, q, s and d for the optimum model.
setDelta

public void setDelta(double delta)

Sets the dampening effect parameter.

Parameters:

delta - a double scalar, the dampening effect parameter used in the detection of a Temporary Change Outlier (TC). delta must be greater than 0 and less than 1. Default: delta = 0.7.
setCriticalValue

public void setCriticalValue(double critical)

Sets the critical value used as a threshold during outlier detection.

Parameters:

critical - a double scalar, the critical value used as a threshold for the statistics used in the outlier detection. critical must be greater than zero. Default: critical = 3.0.
setAccuracyTolerance

public void setAccuracyTolerance(double epsilon)

Sets the tolerance value controlling the accuracy of the parameter estimates.

Parameters:

epsilon - a double scalar, a positive tolerance value controlling the accuracy of parameter estimates during outlier detection. Default: epsilon = 0.001.
setRelativeError

public void setRelativeError(double relativeError)

Sets the stopping criterion for use in the nonlinear equation solver.

Parameters:

relativeError - a double positive scalar containing the stopping criterion for use in the nonlinear equation solver used in the least-squares algorithm. Default: relativeError = 2.2204460492503131e-012.
getResidualStandardError

public double getResidualStandardError()

Returns the residual standard error of the outlier free series. Note that one of the compute methods must be invoked first before calling this method. Otherwise, an IllegalStateException exception is thrown.

Returns:

a double scalar containing the standard error of the outlier free series.
getResiduals

public double[] getResiduals()

Returns the residuals. Note that one of the compute methods must be invoked first before invoking this method. Otherwise, getResiduals throws an IllegalStateException exception.

Returns:

a double array containing the residuals for the outlier and gap free series at the final parameter estimation point.
getNumberOfOutliers

public int getNumberOfOutliers()

Returns the number of outliers detected.

Returns:

an int scalar containing the number of outliers detected. The compute method must be invoked first before invoking this method. Otherwise, the method throws an IllegalStateException exception.

getOutlierStatistics

public int[][] getOutlierStatistics()

Returns the outlier statistics.

Returns:

a double array of length nOutliers by 2, where nOutliers is the number of detected outliers, containing the outlier statistics. The first column contains the time at which the outlier was observed (time ranging from


         times[0]

to times[times.length - 1]) and the second column contains an identifier indicating the type of outlier observed. Outlier types fall into one of five categories:

Identifier	Outlier type
`INNOVATIONAL`	Innovational Outliers (IO)
`ADDITIVE`	Additive Outliers (AO)
`LEVEL_SHIFT`	Level Shift Outliers (LS)
`TEMPORARY_CHANGE`	Temporary Change Outliers (TC)
`UNABLE_TO_IDENTIFY`	Unable to Identify (UI)

If the number of detected outliers equals zero, then an array of length zero is returned.

getAIC

public double getAIC()

Returns Akaike's information criterion (AIC) for the optimum model.

Returns:

a double scalar containing Akaike's information criterion (AIC) for the optimum outlier free series. One of the compute methods must be called before invoking this method. Otherwise, an IllegalStateException exception is thrown.
getAICC

public double getAICC()

Returns Akaike's Corrected Information Criterion (AICC) for the optimum model.

Returns:

a double scalar containing Akaike's Corrected Information Criterion (AICC) for the optimum outlier free series. One of the compute methods must be called before invoking this method. Otherwise, an IllegalStateException exception is thrown.
getBIC

public double getBIC()

Returns the Bayesian Information Criterion (BIC) for the optimum model.

Returns:

a double scalar containing the Bayesian Information Criterion (BIC) for the optimum outlier free series. One of the compute methods must be called before invoking this method. Otherwise, an IllegalStateException exception is thrown.

setModelSelectionCriterion

public void setModelSelectionCriterion(int infoCriterion)

Sets the model selection criterion.

Parameters:

infoCriterion - an int scalar indicating the model selection criterion used in the search for the optimum model.

infoCriterion	Model selection criterion
`AIC`	Akaike's information criterion (AIC)
`AICC`	Akaike's corrected information criterion (AICC)
`BIC`	Bayesian information criterion (BIC)

By default, AIC is chosen.

getMA

public double[] getMA()

Returns the final moving average parameter estimates of the optimum model. Note that one of the compute methods must be invoked first before invoking this method. Otherwise, the method throws an IllegalStateException exception.

Returns:

a double array containing the final moving average parameter estimates. If the optimum model has no MA component then a zero-length array is returned.
getAR

public double[] getAR()

Returns the final autoregressive parameter estimates of the optimum model. Note that one of the compute methods must be invoked first before invoking this method. Otherwise, the method throws an IllegalStateException exception.

Returns:

a double array containing the final autoregressive parameter estimates. If the optimum model has no AR component then a zero-length array is returned.
getConstant

public double getConstant()

Returns the constant parameter estimate for the optimum model. Note that one of the compute methods must be invoked first before invoking this method. Otherwise, the method throws an IllegalStateException exception.

Returns:

a double scalar containing the constant parameter estimate for the optimum model.
getCompleteTimeSeries

public double[] getCompleteTimeSeries()

Returns the original series with potentially missing values replaced by estimates.

Returns:

a double array containing the original time series with missing values replaced by estimates. One of the compute methods must be called before invoking this method. Otherwise, an IllegalStateException exception is thrown.
getCompleteTimes

public int[] getCompleteTimes()

Returns all time points at which the original series was observed, including values for times with missing values in x.

Returns:

an int array of length times[times.length-1]-times[0]+1 containing the times at which the time series (including missing values) was observed. One of the compute methods must be called before invoking this method. Otherwise, an IllegalStateException exception is thrown.
getOutlierFreeSeries

public double[] getOutlierFreeSeries()

Returns the outlier free series.

Returns:

a double array containing the original time series with estimated missing values after removal of any outlier effects. One of the compute methods must be called before invoking this method. Otherwise, an IllegalStateException exception is thrown.
forecast

public final void forecast(int nForecast)

Computes forecasts, associated probability limits and $\psi$ weights for the given outlier contaminated time series. Note that one of the compute methods must be invoked first before invoking this method. Otherwise, the method throws an IllegalStateException exception.

Parameters:

nForecast - an int scalar representing the number of forecasts that will be computed. nForecast must be greater than 0. Forecast origin is the time point of the last observed value in the time series, $t_\text{nObs}$. Forecasts are computed for lead times $1, 2, \ldots, \text{nForecast}$, i.e. time points $t_\text{nObs}+1, t_\text{nObs}+2,\ldots,t_\text{nObs}+\text{nForecast}$.
setConfidence

public void setConfidence(double confidence)

Sets the confidence level for calculating confidence limit deviations returned by getDeviations.

Parameters:

confidence - a double scalar specifying the confidence level used in computing forecast confidence intervals. Typical choices for confidence are 0.90, 0.95, and 0.99. confidence must be greater than 0.0 and less than 1.0. Default: confidence = 0.95.
getDeviations

public double[] getDeviations()

Returns the deviations used for calculating the forecast confidence limits.

Returns:

a double array of length nForecast containing the deviations from each forecast for calculating forecast confidence intervals. The confidence level is specified in confidence. Method forecast must be invoked before this method is called. Otherwise, an IllegalStateException exception is thrown. By default, confidence = 0.95.
getForecast

public double[] getForecast()

Returns forecasts for the original outlier contaminated series.

Returns:

a double array of length nForecast containing the forecasts for the original series. Forecast origin is the time point of the last observed value in the time series, $t_\text{nObs}$. Forecasts are returned for lead times $1, 2, \ldots, \text{nForecast}$, i.e. time points $t_\text{nObs}+1, t_\text{nObs}+2,\ldots,t_\text{nObs}+\text{nForecast}$. Method forecast must be invoked before this method is called. Otherwise, an IllegalStateException exception is thrown.
getOutlierFreeForecast

public double[] getOutlierFreeForecast()

Returns forecasts for the outlier free series.

Returns:

a double array of length nForecast containing the forecasts for the outlier free series. Forecast origin is the time point of the last observed value in the time series, $t_\text{nObs}$. Forecasts are returned for lead times $1, 2, \ldots, \text{nForecast}$, i.e. time points $t_\text{nObs}+1, t_\text{nObs}+2,\ldots,t_\text{nObs}+\text{nForecast}$. Method forecast must be invoked before this method is called. Otherwise, an IllegalStateException exception is thrown.
getPsiWeights

public double[] getPsiWeights()

Returns the $\psi$ weights of the infinite order moving average form of the model.

Returns:

a double array of length nForecast containing the $\psi$ weights of the infinite order moving average form of the optimum model for the outlier free series. Method forecast must be invoked before this method is called. Otherwise, an IllegalStateException exception is thrown.

Class AutoARIMA

Nested Class Summary

Field Summary

Constructor Summary

Method Summary

Methods inherited from class java.lang.Object

Field Details

INNOVATIONAL

ADDITIVE

LEVEL_SHIFT

TEMPORARY_CHANGE

UNABLE_TO_IDENTIFY

AIC

AICC

BIC

Constructor Details

AutoARIMA

Method Details

compute

compute

compute

setPeriods

setDifferenceOrders

setMaximumARLag

getOptimumModelOrder

setDelta

setCriticalValue

setAccuracyTolerance

setRelativeError

getResidualStandardError

getResiduals

getNumberOfOutliers

getOutlierStatistics

getAIC

getAICC

getBIC

setModelSelectionCriterion

getMA

getAR

getConstant

getCompleteTimeSeries

getCompleteTimes

getOutlierFreeSeries

forecast

setConfidence

getDeviations

getForecast

getOutlierFreeForecast

getPsiWeights