com.numericalmethod.suanshu.stats.test.timeseries.adf

Class ADFFiniteSampleDistribution

java.lang.Object

com.numericalmethod.suanshu.stats.distribution.univariate.EmpiricalDistribution

com.numericalmethod.suanshu.stats.test.timeseries.adf.ADFFiniteSampleDistribution

All Implemented Interfaces:

ProbabilityDistribution, java.io.Serializable

public class ADFFiniteSampleDistribution
extends EmpiricalDistribution

This class computes the finite sample distribution of the augmented Dickey-Fuller (ADF) test statistics.

There are three main versions of the test and thus three possible asymptotic distributions:

1. NO_CONSTANT: test for a unit root without drift or time trend;
2. CONSTANT: test for a unit root with drift;
3. CONSTANT_TIME: test for a unit root with drift and deterministic time trend.

The p-values in R are interpolated using the values from Table 4.2, p. 103 of Banerjee et al. (1993).

See Also:

• D. A. Dickey and W. A. Fuller, “Distribution of the Estimators for Autoregressive Time Series with a Unit Root,” J. Amer. Stat. Assoc., vol. 74, pp. 427–431, 1979.
• E. Said and D. A. Dickey, "Testing for Unit Roots in Autoregressive Moving Average Models of Unknown Order," Biometrika, vol. 71, 599–607, 1984.
• A. Banerjee et al., "Cointegration, Error Correction, and the Econometric Analysis of Non-Stationary Data," Oxford, Oxford University Press, 1993, ch. 4, pp. 99-135.

, Serialized Form

Field Summary

Fields

Modifier and Type	Field and Description
boolean	lagAdjust indicate whether the distribution is adjusted for lags
int	lagOrder the lag order used to calculate the test statistics; lagOrder = 0 yields the Dickey-Fuller distribution
int	nSim the number of simulations
int	sampleSize the (finite) sample size
AugmentedDickeyFuller.TrendType	trend the type of augmented Dickey-Fuller (ADF) test
int	truncation the number of truncated values

Constructor Summary

Constructors

Constructor and Description
ADFFiniteSampleDistribution(int sampleSize) Construct the finite sample distribution for the augmented Dickey-Fuller test statistics.
ADFFiniteSampleDistribution(int sampleSize, AugmentedDickeyFuller.TrendType trend) Construct the finite sample distribution for the augmented Dickey-Fuller test statistics.
ADFFiniteSampleDistribution(int sampleSize, AugmentedDickeyFuller.TrendType trend, boolean lagAdjust, int lagOrder) Construct the finite sample distribution for the augmented Dickey-Fuller test statistics.
ADFFiniteSampleDistribution(int sampleSize, AugmentedDickeyFuller.TrendType trend, boolean lagAdjust, int lagOrder, int truncation, int nSim) Construct the finite sample distribution for the augmented Dickey-Fuller test statistics.

Method Summary

Methods inherited from class com.numericalmethod.suanshu.stats.distribution.univariate.EmpiricalDistribution

cdf, density, entropy, kurtosis, mean, median, moment, nSamples, quantile, skew, toArray, variance

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Field Detail

sampleSize

public final int sampleSize

the (finite) sample size

trend

public final AugmentedDickeyFuller.TrendType trend

the type of augmented Dickey-Fuller (ADF) test

lagAdjust

public final boolean lagAdjust

indicate whether the distribution is adjusted for lags

lagOrder

public final int lagOrder

the lag order used to calculate the test statistics; lagOrder = 0 yields the Dickey-Fuller distribution

truncation

public final int truncation

the number of truncated values

nSim

public final int nSim

the number of simulations

Constructor Detail

ADFFiniteSampleDistribution

public ADFFiniteSampleDistribution(int sampleSize,
                                   AugmentedDickeyFuller.TrendType trend,
                                   boolean lagAdjust,
                                   int lagOrder,
                                   int truncation,
                                   int nSim)

Construct the finite sample distribution for the augmented Dickey-Fuller test statistics.

Parameters:

sampleSize - the (finite) sample size

trend - the type of augmented Dickey-Fuller test

lagAdjust - indicator of whether the distribution is adjusted for lags

lagOrder - the lag order; lagOrder = 0 yields the Dickey-Fuller distribution

truncation - the number of truncated values

nSim - the number of simulations

ADFFiniteSampleDistribution

public ADFFiniteSampleDistribution(int sampleSize,
                                   AugmentedDickeyFuller.TrendType trend,
                                   boolean lagAdjust,
                                   int lagOrder)

Construct the finite sample distribution for the augmented Dickey-Fuller test statistics. The number of truncated values is 50.

Parameters:

sampleSize - the (finite) sample size

trend - the type of augmented Dickey-Fuller test

lagAdjust - indicator of whether the distribution is adjusted for lags

lagOrder - the lag order; lagOrder = 0 yields the Dickey-Fuller distribution

ADFFiniteSampleDistribution

public ADFFiniteSampleDistribution(int sampleSize,
                                   AugmentedDickeyFuller.TrendType trend)

Construct the finite sample distribution for the augmented Dickey-Fuller test statistics. We do not adjust for the lag.

Parameters:

sampleSize - the (finite) sample size

trend - the type of augmented Dickey-Fuller test

ADFFiniteSampleDistribution

public ADFFiniteSampleDistribution(int sampleSize)

Construct the finite sample distribution for the augmented Dickey-Fuller test statistics. We test for a unit root with drift and deterministic time trend.

Parameters:

sampleSize - the (finite) sample size