-statistics and their significance levels are also returned. A call to g13dmf is usually made prior to calling this routine in order to calculate the sample cross-correlation matrices.

2

Specification

Fortran Interface

Subroutine g13dnf (

k, n, m, kmax, r0, r, maxlag, parlag, x, pvalue, work, lwork, ifail)

Integer, Intent (In)	::	k, n, m, kmax, lwork
Integer, Intent (Inout)	::	ifail
Integer, Intent (Out)	::	maxlag
Real (Kind=nag_wp), Intent (In)	::	r0(kmax,k), r(kmax,kmax,m)
Real (Kind=nag_wp), Intent (Inout)	::	parlag(kmax,kmax,m)
Real (Kind=nag_wp), Intent (Out)	::	x(m), pvalue(m), work(lwork)

C Header Interface

#include nagmk26.h

void	g13dnf_ ( const Integer k, const Integer n, const Integer m, const Integer kmax, const double r0[], const double r[], Integer maxlag, double parlag[], double x[], double pvalue[], double work[], const Integer lwork, Integer *ifail)

3

Description

Let

W_{t} = {(w_{1 t}, w_{2 t}, \dots, w_{k t})}^{T}

, for

t = 1, 2, \dots, n

, denote

n

observations of a vector of

k

time series. The partial lag correlation matrix at lag

l

P (l)

, is defined to be the correlation matrix between

W_{t}

and

W_{t + l}

, after removing the linear dependence on each of the intervening vectors

W_{t + 1}, W_{t + 2}, \dots, W_{t + l - 1}

. It is the correlation matrix between the residual vectors resulting from the regression of

W_{t + l}

on the carriers

W_{t + l - 1}, \dots, W_{t + 1}

and the regression of

W_{t}

on the same set of carriers; see Heyse and Wei (1985).

P (l)

has the following properties.

(i)	If $W_{t}$ follows a vector autoregressive model of order $p$ , then $P (l) = 0$ for $l > p$ ;
(ii)	When $k = 1$ , $P (l)$ reduces to the univariate partial autocorrelation at lag $l$ ;
(iii)	Each element of $P (l)$ is a properly normalized correlation coefficient;
(iv)	When $l = 1$ , $P (l)$ is equal to the cross-correlation matrix at lag $1$ (a natural property which also holds for the univariate partial autocorrelation function).

Sample estimates of the partial lag correlation matrices may be obtained using the recursive algorithm described in Wei (1990). They are calculated up to lag

m

, which is usually taken to be at most

n / 4

. Only the sample cross-correlation matrices (

\hat{R} (l)

, for

l = 0, 1, \dots, m

) and the standard deviations of the series are required as input to g13dnf. These may be computed by g13dmf. Under the hypothesis that

W_{t}

follows an autoregressive model of order

s - 1

, the elements of the sample partial lag matrix

\hat{P} (s)

, denoted by

{\hat{P}}_{i j} (s)

, are asymptotically Normally distributed with mean zero and variance

1 / n

. In addition the statistic

X (s) = n \sum_{i = 1}^{k} \sum_{j = 1}^{k} {\hat{P}}_{i j} {(s)}^{2}

has an asymptotic

χ^{2}

-distribution with

k^{2}

degrees of freedom. These quantities,

X (l)

, are useful as a diagnostic aid for determining whether the series follows an autoregressive model and, if so, of what order.

4

References

Heyse J F and Wei W W S (1985) The partial lag autocorrelation function Technical Report No. 32 Department of Statistics, Temple University, Philadelphia

Wei W W S (1990) Time Series Analysis: Univariate and Multivariate Methods Addison–Wesley

5

Arguments

1: $k$ – IntegerInput: On entry: $k$ , the dimension of the multivariate time series.

Constraint: $k \geq 1$ .
2: $n$ – IntegerInput: On entry: $n$ , the number of observations in each series.

Constraint: $n \geq 2$ .
3: $m$ – IntegerInput: On entry: $m$ , the number of partial lag correlation matrices to be computed. Note this also specifies the number of sample cross-correlation matrices that must be contained in the array r.

Constraint: $1 \leq m < n$ .
4: $kmax$ – IntegerInput: On entry: the first dimension of the arrays r0, r and parlag and the second dimension of the arrays r and parlag as declared in the (sub)program from which g13dnf is called.

Constraint: $kmax \geq k$ .
5: $r0 (kmax, k)$ – Real (Kind=nag_wp) arrayInput: On entry: if $i \neq j$ , then $r0 (i, j)$ must contain the $(i, j)$ th element of the sample cross-correlation matrix at lag zero, ${\hat{R}}_{i j} (0)$ . If $i = j$ , then $r0 (i, i)$ must contain the standard deviation of the $i$ th series.
6: $r (kmax, kmax, m)$ – Real (Kind=nag_wp) arrayInput: On entry: $r (i, j, l)$ must contain the $(i, j)$ th element of the sample cross-correlation at lag $l$ , ${\hat{R}}_{i j} (l)$ , for $l = 1, 2, \dots, m$ , $i = 1, 2, \dots, k$ and $j = 1, 2, \dots, k$ , where series $j$ leads series $i$ (see Section 9).
7: $maxlag$ – IntegerOutput: On exit: the maximum lag up to which partial lag correlation matrices (along with $χ^{2}$ -statistics and their significance levels) have been successfully computed. On a successful exit maxlag will equal m. If $ifail = 2$ on exit, maxlag will be less than m.
8: $parlag (kmax, kmax, m)$ – Real (Kind=nag_wp) arrayOutput: On exit: $parlag (i, j, l)$ contains the $(i, j)$ th element of the sample partial lag correlation matrix at lag $l$ , ${\hat{P}}_{i j} (l)$ , for $l = 1, 2, \dots, maxlag$ , $i = 1, 2, \dots, k$ and $j = 1, 2, \dots, k$ .
9: $x (m)$ – Real (Kind=nag_wp) arrayOutput: On exit: $x (l)$ contains the $χ^{2}$ -statistic at lag $l$ , for $l = 1, 2, \dots, maxlag$ .
10: $pvalue (m)$ – Real (Kind=nag_wp) arrayOutput: On exit: $pvalue (l)$ contains the significance level of the corresponding $χ^{2}$ -statistic in x, for $l = 1, 2, \dots, maxlag$ .
11: $work (lwork)$ – Real (Kind=nag_wp) arrayWorkspace
12: $lwork$ – IntegerInput: On entry: the dimension of the array work as declared in the (sub)program from which g13dnf is called.

Constraint: $lwork \geq (5 m + 6) k^{2} + k$ .
13: $ifail$ – IntegerInput/Output: On entry: ifail must be set to $0$ , $- 1 or 1$ . If you are unfamiliar with this argument you should refer to Section 3.4 in How to Use the NAG Library and its Documentation for details.
For environments where it might be inappropriate to halt program execution when an error is detected, the value $- 1 or 1$ is recommended. If the output of error messages is undesirable, then the value $1$ is recommended. Otherwise, if you are not familiar with this argument, the recommended value is $0$ . When the value $- 1 or 1$ is used it is essential to test the value of ifail on exit.

On exit: $ifail = 0$ unless the routine detects an error or a warning has been flagged (see Section 6).

6

Error Indicators and Warnings

If on entry

ifail = 0

- 1

, explanatory error messages are output on the current error message unit (as defined by x04aaf).

Errors or warnings detected by the routine:

$ifail = 1$

On entry,	$k < 1$ ,
or	$n < 2$ ,
or	$m < 1$ ,
or	$m \geq n$ ,
or	$kmax < k$ ,
or	$lwork < (5 m + 6) k^{2} + k$ .

$ifail = 2$: The recursive equations used to compute the sample partial lag correlation matrices have broken down at lag $maxlag + 1$ . All output quantities in the arrays parlag, x and pvalue up to and including lag maxlag will be correct.

$ifail = - 99$: An unexpected error has been triggered by this routine. Please contact NAG.
See Section 3.9 in How to Use the NAG Library and its Documentation for further information.

$ifail = - 399$: Your licence key may have expired or may not have been installed correctly.
See Section 3.8 in How to Use the NAG Library and its Documentation for further information.

$ifail = - 999$: Dynamic memory allocation failed.
See Section 3.7 in How to Use the NAG Library and its Documentation for further information.

7

Accuracy

The accuracy will depend upon the accuracy of the sample cross-correlations.

8

Parallelism and Performance

g13dnf is threaded by NAG for parallel execution in multithreaded implementations of the NAG Library.

g13dnf makes calls to BLAS and/or LAPACK routines, which may be threaded within the vendor library used by this implementation. Consult the documentation for the vendor library for further information.

Please consult the X06 Chapter Introduction for information on how to control and interrogate the OpenMP environment used within this routine. Please also consult the Users' Note for your implementation for any additional implementation-specific information.

9

Further Comments

The time taken is roughly proportional to

m^{2} k^{3}

If you have calculated the sample cross-correlation matrices in the arrays r0 and r, without calling g13dmf, then care must be taken to ensure they are supplied as described in Section 5. In particular, for

l \geq 1

{\hat{R}}_{i j} (l)

must contain the sample cross-correlation coefficient between

w_{i (t - l)}

and

w_{j t}

The routine g13dbf computes squared partial autocorrelations for a specified number of lags. It may also be used to estimate a sequence of partial autoregression matrices at lags

1, 2, \dots

by making repeated calls to the routine with the argument nk set to

1, 2, \dots

. The

(i, j)

th element of the sample partial autoregression matrix at lag

l

is given by

W (i, j, l)

when nk is set equal to

l

on entry to g13dbf. Note that this is the ‘Yule–Walker’ estimate. Unlike the partial lag correlation matrices computed by g13dnf, when

W_{t}

follows an autoregressive model of order

s - 1

, the elements of the sample partial autoregressive matrix at lag

s

do not have variance

1 / n

, making it very difficult to spot a possible cut-off point. The differences between these matrices are discussed further by Wei (1990).

Note that g13dbf takes the sample cross-covariance matrices as input whereas this routine requires the sample cross-correlation matrices to be input.

10

Example

This example computes the sample partial lag correlation matrices of two time series of length

48

, up to lag

10

. The matrices, their

χ^{2}

-statistics and significance levels and a plot of symbols indicating which elements of the sample partial lag correlation matrices are significant are printed. Three * represent significance at the

0.5

% level, two * represent significance at the 1% level and a single * represents significance at the 5% level. The * are plotted above or below the central line depending on whether the elements are significant in a positive or negative direction.

NAG Library Routine Document

g13dnf (multi_corrmat_partlag)

▸▿ Contents

1 Purpose

2 Specification

3 Description

4 References

5 Arguments

6 Error Indicators and Warnings

7 Accuracy

8 Parallelism and Performance

9 Further Comments

10 Example

10.1 Program Text

10.2 Program Data

10.3 Program Results

1

Purpose