nag_tsa_multi_inputmod_estim (g13be) fits a multi-input model relating one output series to the input series with a choice of three different estimation criteria: nonlinear least squares, exact likelihood and marginal likelihood. When no input series are present, nag_tsa_multi_inputmod_estim (g13be) fits a univariate ARIMA model.

Syntax

[para, xxy, zsp, itc, sd, cm, s, d, ndf, res, sttf, nsttf, ifail] = g13be(mr, mt, para, xxy, 'nser', nser, 'npara', npara, 'kfc', kfc, 'nxxy', nxxy, 'kef', kef, 'nit', nit, 'zsp', zsp, 'iwa', iwa, 'imwa', imwa, 'kpriv', kpriv)

[para, xxy, zsp, itc, sd, cm, s, d, ndf, res, sttf, nsttf, ifail] = nag_tsa_multi_inputmod_estim(mr, mt, para, xxy, 'nser', nser, 'npara', npara, 'kfc', kfc, 'nxxy', nxxy, 'kef', kef, 'nit', nit, 'zsp', zsp, 'iwa', iwa, 'imwa', imwa, 'kpriv', kpriv)

Note: the interface to this routine has changed since earlier releases of the toolbox:

At Mark 23:	isttf, kzef and kzsp were removed from the interface; iwa, imwa, zsp, kfc, nit, kef and kpriv were made optional
At Mark 22:	nxxy was made optional

Description

The Multi-input Model

The output series

y_{t}

, for

t = 1, 2, \dots, n

, is assumed to be the sum of (unobserved) components

z_{i, t}

which are due respectively to the inputs

x_{i, t}

, for

i = 1, 2, \dots, m

Thus

y_{t} = z_{1, t} + \dots + z_{m, t} + n_{t}

where

n_{t}

is the error, or output noise component.

A typical component

z_{t}

may be either

(a)

a simple regression component,

z_{t} = ω x_{t}

(here

x_{t}

is called a simple input), or

(b)

a transfer function model component which allows for the effect of lagged values of the variable, related to

x_{t}

z_{t} = δ_{1} z_{t - 1} + δ_{2} z_{t - 2} + \dots + δ_{p} z_{t - p} + ω_{0} x_{t - b} - ω_{1} x_{t - b - 1} - \dots - ω_{q} x_{t - b - q} .

The noise

n_{t}

is assumed to follow a (possibly seasonal) ARIMA model, i.e., may be represented in terms of an uncorrelated series,

a_{t}

, by the hierarchy of equations

(i)	$\nabla^{d} \nabla_{s}^{D} n_{t} = c + w_{t}$
(ii)	$w_{t} = Φ_{1} w_{t - s} + Φ_{2} w_{t - 2 \times s} + \dots + Φ_{P} w_{t - P \times s} + e_{t} - Θ_{1} e_{t - s} - Θ_{2} e_{t - 2 \times s} - \dots - Θ_{Q} e_{t - Q \times s}$
(iii)	$e_{t} = ϕ_{1} e_{t - 1} + ϕ_{2} e_{t - 2} + \dots + ϕ_{p} e_{t - p} + a_{t} - θ_{1} a_{t - 1} - θ_{2} a_{t - 2} - \dots - θ_{q} a_{t - q}$

as outlined in Description in nag_tsa_uni_arima_estim (g13ae).

Note: the orders

p, q

appearing in each of the transfer function models and the ARIMA model are not necessarily the same;

\nabla^{d} \nabla_{s}^{D} n_{t}

is the result of applying non-seasonal differencing of order

d

and seasonal differencing of seasonality

s

and order

D

to the series

n_{t}

: the differenced series is then of length

N = n - d - s \times D

; the constant term parameter

c

may optionally be held fixed at its initial value (usually, but not necessarily zero) rather than being estimated.

For the purpose of defining an estimation criterion it is assumed that the series

a_{t}

is a sequence of independent Normal variates having mean

0

and variance

σ_{a}^{2}

. An allowance has to be made for the effects of unobserved data prior to the observation period. For the noise component an allowance is always made using a form of backforecasting.

For each transfer function input, you have to decide what values are to be assumed for the pre-period terms

z_{0}, z_{- 1}, \dots, z_{1 - p}

and

x_{0}, x_{- 1}, \dots, x_{1 - b - q}

which are in theory necessary to re-create the component series

z_{1}, z_{2}, \dots, z_{n}

, during the estimation procedure.

The first choice is to assume that all these values are zero. In this case, in order to avoid undesirable transient distortion of the early values

z_{1}, z_{2}, \dots

, you are advised first to correct the input series

x_{t}

by subtracting from all the terms a suitable constant to make the early values

x_{1}, x_{2}, \dots

, close to zero. The series mean

\bar{x}

is one possibility, but for a series with strong trend the constant might be simply

x_{1}

The second choice is to treat the unknown pre-period terms as nuisance parameters and estimate them along with the other parameters. This choice should be used with caution. For example, if

p = 1

and

b = q = 0

, it is equivalent to fitting to the data a decaying geometric curve of the form

A δ^{t}

, for

t = 1, 2, \dots

, along with the other inputs, this being the form of the transient. If the output

y_{t}

contains a strong trend of this form, which is not otherwise represented in the model, it will have a tendency to influence the estimate of

δ

away from the value appropriate to the transfer function model.

In most applications the first choice should be adequate, with the option possibly being used as a refinement at the end of the modelling process. The number of nuisance parameters is then

\max (p, b + q)

, with a corresponding loss of degrees of freedom in the residuals. If you align the input

x_{t}

with the output by using in its place the shifted series

x_{t - b}

, then setting

b = 0

in the transfer function model, there is some improvement in efficiency. On some occasions when the model contains two or more inputs, each with estimation of pre-period nuisance parameters, these parameters may be co-linear and lead to failure of the function. The option must then be ‘switched off’ for one or more inputs.

The Estimation Criterion

This is a measure of how well a proposed set of parameters in the transfer function and noise ARIMA models matches the data. The estimation function searches for parameter values which minimize this criterion. For a proposed set of parameter values it is derived by calculating

(i)

the components

z_{1, t}, z_{2, t}, \dots, z_{m, t}

as the responses to the input series

x_{1, t}, x_{2, t} \dots, x_{m, t}

using the equations (a) or (b) above,

(ii)

the discrepancy between the output and the sum of these components, as the noise

n_{t} = y_{t} - (z_{1, t} + z_{2, t} + \dots + z_{m, t}),

(iii)

the residual series

a_{t}

from

n_{t}

by reversing the recursive equations (i), (ii) and (iii) above.

This last step again requires treatment of the effect of unknown pre-period values of

n_{t}

and other terms in the equations regenerating

a_{t}

. This is identical to the treatment given in Description in nag_tsa_uni_arima_estim (g13ae), and leads to a criterion which is a sum of squares function

S

, of the residuals

a_{t}

. It may be shown that the finite algorithm presented there is equivalent to taking the infinite set of past values

n_{0}, n_{- 1}, n_{- 2}, \dots

, as (linear) nuisance parameters. There is no loss of degrees of freedom however, because the sum of squares function

S

may be expressed as including the corresponding set of past residuals; see page 273 of Box and Jenkins (1976), who prove that

S = \sum_{- \infty}^{n} a_{t}^{2} .

The function

D = S

is the first of the three possible criteria, and is quite adequate for moderate to long series with no seasonal parameters. The second is the exact likelihood criterion which considers the past set

n_{0}, n_{- 1}, n_{- 2}

not as simple nuisance parameters, but as unobserved random variables with known distribution. Calculation of the likelihood of the observed set

n_{1}, n_{2}, \dots, n_{n}

requires theoretical integration over the range of the past set. Fortunately this yields a criterion of the form

D = M \times S

(whose minimization is equivalent to maximizing the exact likelihood of the data), where

S

is exactly as before, and the multiplier

M

is a function calculated from the ARIMA model parameters. The value of

M

is always

\geq 1

, and

M

tends to

1

for any fixed parameter set as the sample size

n

tends to

\infty

. There is a moderate computational overhead in using this option, but its use avoids appreciable bias in the ARIMA model parameters and yields a better conditioned estimation problem.

The third criterion of marginal likelihood treats the coefficients of the simple inputs in a manner analogous to that given to the past set

n_{0}, n_{- 1}, n_{- 2}, \dots

. These coefficients, together with the constant term

c

used to represent the mean of

w_{t}

, are in effect treated as random variables with highly dispersed distributions. This leads to the criterion

D = M \times S

again, but with a different value of

M

which now depends on the simple input series values

x_{t}

. In the presence of a moderate to large number of simple inputs, the marginal likelihood criterion can counteract bias in the ARIMA model parameters which is caused by estimation of the simple inputs. This is particularly important in relatively short series.

nag_tsa_multi_inputmod_estim (g13be) can be used with no input series present, to estimate a univariate ARIMA model for the output alone. The marginal likelihood criterion is then distinct from exact likelihood only if a constant term is being estimated in the model, because this is treated as an implicit simple input.

The Estimation Procedure

This is the minimization of the estimation criterion or objective function

D

(for deviance). The function uses an extension of the algorithm of Marquardt (1963). The step size in the minimization is inversely related to a parameter

α

, which is increased or decreased by a factor

β

at successive iterations, depending on the progress of the minimization. Convergence is deemed to have occurred if the fractional reduction of

D

in successive iterations is less than a value

γ

, while

α < 1

Certain model parameters (in fact all excluding the

ω

s) are subject to stability constraints which are checked throughout to within a specified tolerance multiple

δ

of machine accuracy. Using the least squares criterion, the minimization may halt prematurely when some parameters ‘stick’ at a constraint boundary. This can happen particularly with short seasonal series (with a small number of whole seasons). It will not happen using the exact likelihood criterion, although convergence to a point on the boundary may sometimes be rather slow, because the criterion function may be very flat in such a region. There is also a smaller risk of a premature halt at a constraint boundary when marginal likelihood is used.

A positive, or zero number of iterations can be specified. In either case, the value

D

of the objective function at iteration zero is presented at the initial parameter values, except for estimation of any pre-period terms for the input series, backforecasts for the noise series, and the coefficients of any simple inputs, and the constant term (unless this is held fixed).

At any later iteration, the value of

D

is computed after re-estimation of the backforecasts to their optimal values, corresponding to the model parameters presented at that iteration. This is not true for any pre-period terms for the input series which, although they are updated from the previous iteration, may not be precisely optimal for the parameter values presented, unless convergence of those parameters has occurred. However, in the case of marginal likelihood being specified, the coefficients of the simple inputs and the constant term are also re-estimated together with the backforecasts at each iteration, to values which are optimal for the other parameter values presented.

Further Results

The residual variance is taken as

erv = \frac{S}{df}

, where

df = N -

(total number of parameters estimated), is the residual degrees of freedom. The pre-period nuisance parameters for the input series are included in the reduction of

df

, as is the constant if it is estimated.

The covariance matrix of the vector of model parameter estimates is given by

erv \times H^{- 1}

where

H

is the linearized least squares matrix taken from the final iteration of the algorithm of Marquardt. From this expression are derived the vector of standard deviations, and the correlation matrix of parameter estimates. These are approximations which are only valid asymptotically, and must be treated with great caution when the parameter estimates are close to their constraint boundaries.

The residual series

a_{t}

is available upon completion of the iterations over the range

t = 1 + d + s \times D, \dots, n

corresponding to the differenced noise series

w_{t}

Because of the algorithm used for backforecasting, these are only true residuals for

t \geq 1 + q + s \times Q - p - s \times P - d - s \times D

, provided this is positive. Estimation of pre-period terms for the inputs will also tend to reduce the magnitude of the early residuals, sometimes severely.

The model component series

z_{1, t}, \dots, z_{m, t}

and

n_{t}

may optionally be returned in place of the supplied series values, in order to assess the effects of the various inputs on the output.

Forecasting Information

For the purpose of constructing forecasts of the output series at future time points

t = n + 1, n + 2, \dots

using nag_tsa_multi_inputmod_forecast_state (g13bh), it is not necessary to use the whole set of observations

y_{t}

and

x_{1, t}, x_{2, t}, \dots, x_{m, t}

, for

t = 1, 2, \dots, m

. It is sufficient to retain a limited set of quantities constituting the ‘state set’ as follows: for each series which appears with lagged subscripts in equations (a), (b), (i), (ii) and (iii) above, include the values at times

n + 1 - k

for

k = 1

up to the maximum lag associated with that series in the equations. Note that (i) implicitly includes past values of

n_{t}

and intermediate differences of

n_{t}

such as

\nabla^{d - 1} \nabla_{s}^{D}

If later observations of the series become available, it is possible to update the state set (without re-estimating the model) using nag_tsa_multi_inputmod_update (g13bg). If time series data is supplied with a previously estimated model, it is possible to construct the state set (and forecasts) using nag_tsa_multi_inputmod_forecast (g13bj).

References

Box G E P and Jenkins G M (1976) Time Series Analysis: Forecasting and Control (Revised Edition) Holden–Day

Marquardt D W (1963) An algorithm for least squares estimation of nonlinear parameters J. Soc. Indust. Appl. Math. 11 431

Parameters

Compulsory Input Parameters

1: $mr (7)$ – int64int32nag_int array

The orders vector

(p, d, q, P, D, Q, s)

of the ARIMA model for the output noise component.

p

q

P

and

Q

refer respectively to the number of autoregressive

(ϕ)

, moving average

(θ)

, seasonal autoregressive

(Φ)

and seasonal moving average

(Θ)

parameters.

d

D

and

s

refer respectively to the order of non-seasonal differencing, the order of seasonal differencing and the seasonal period.

Constraints:

$p$ , $d$ , $q$ , $P$ , $D$ , $Q$ , $s \geq 0$ ;
$p + q + P + Q > 0$ ;
$s \neq 1$ ;
if $s = 0$ , $P + D + Q = 0$ ;
if $s > 1$ , $P + D + Q > 0$ ;
$d + s \times (P + D) \leq n$ ;
$p + d - q + s \times (P + D - Q) \leq n$ .

2: $mt (4, nser)$ – int64int32nag_int array

The transfer function model orders

b

p

and

q

of each of the input series. The order arguments for input series

i

are held in column

i

. Row

1

holds the value

b_{i}

, row 2 holds the value

q_{i}

and row 3 holds the value

p_{i}

. For a simple input,

b_{i} = q_{i} = p_{i} = 0

Row 4 holds the value

r_{i}

, where

r_{i} = 1

for a simple input,

r_{i} = 2

for a transfer function input for which no allowance is to be made for pre-observation period effects, and

r_{i} = 3

for a transfer function input for which pre-observation period effects will be treated by estimation of appropriate nuisance parameters.

When

r_{i} = 1

, any nonzero contents of rows 1, 2, and 3 of column

i

are ignored.

Constraint:

mt (4, i) = 1, ​ 2 ​ or ​ 3

, for

i = 1, 2, \dots, nser - 1

3: $para (npara)$ – double array

Initial values of the multi-input model parameters. These are in order, firstly the ARIMA model parameters:

p

values of

ϕ

parameters,

q

values of

θ

parameters,

P

values of

Φ

parameters and

Q

values of

Θ

parameters. These are followed by initial values of the transfer function model parameters

ω_{0}, ω_{1}, \dots, ω_{q_{1}}

δ_{1}, δ_{2}, \dots, δ_{p_{1}}

for the first of any input series and similarly for each subsequent input series. The final component of para is the initial value of the constant

c

, whether it is fixed or is to be estimated.

4: $xxy (ldxxy, nser)$ – double array

ldxxy, the first dimension of the array, must satisfy the constraint

ldxxy \geq nxxy

The columns of xxy must contain the nxxy original, undifferenced values of each of the input series and the output series

x_{t}

in that order.

Optional Input Parameters

1: $nser$ – int64int32nag_int scalar

Default: the second dimension of the arrays mt, xxy. (An error is raised if these dimensions are not equal.)

The total number of input and output series. There may be any number of input series (including none), but always one output series.

Constraints:

$nser \geq 1$ ;
if there are no parameters in the model (that is, $p = q = P = Q = 0$ and $kfc = 0$ ), $nser > 1$ .

2: $npara$ – int64int32nag_int scalar

Default: the dimension of the array para.

The exact number of

ϕ, θ, Φ, Θ

ω, δ

and

c

parameters.

Constraint:

npara = p + q + P + Q + nser + \sum (p_{i} + q_{i})

, the summation being over all the

p_{i} \neq q_{i}

supplied in mt.

c

must be included, whether fixed or estimated.

3: $kfc$ – int64int32nag_int scalar

Default:

1

Must be set to

0

if the constant

c

is to remain fixed at its initial value, and

1

if it is to be estimated.

Constraint:

kfc = 0

1

4: $nxxy$ – int64int32nag_int scalar

Default: the first dimension of the array xxy.

The (common) length of the original, undifferenced input and output time series.

5: $kef$ – int64int32nag_int scalar

Default:

2

Indicates the likelihood option.

$kef = 1$: Gives least squares.
$kef = 2$: Gives exact likelihood.
$kef = 3$: Gives marginal likelihood.

Constraint:

kef = 1

2

3

6: $nit$ – int64int32nag_int scalar

Default:

1000

The maximum required number of iterations.

$nit = 0$: No change is made to any of the model parameters in array para except that the constant $c$ (if $kfc = 1$ ) and any $ω$ relating to simple input series are estimated. (Apart from these, estimates are always derived for the nuisance parameters relating to any backforecasts and any pre-observation period effects for transfer function inputs.)

Constraint:

nit \geq 0

7: $zsp (4)$ – double array

kzsp = 1

, then zsp must contain the four values used to control the strategy of the search procedure.

$zsp (1)$: Contains $α$ , the value used to constrain the magnitude of the search procedure steps.
$zsp (2)$: Contains $β$ , the multiplier which regulates the value of $α$ .
$zsp (3)$: Contains $δ$ , the value of the stationarity and invertibility test tolerance factor.
$zsp (4)$: Contains $γ$ , the value of the convergence criterion.

kzsp \neq 1

before entry, default values of zsp are supplied by the function. These are

0.01

10.0

1000.0

and

\max (100 \times machine precision, 0.0000001)

, respectively.

Constraint: if

kzsp = 1

zsp (1) > 0.0

zsp (2) > 1.0

zsp (3) \geq 1.0

0 \leq zsp (4) < 1.0

8: $iwa$ – int64int32nag_int scalar

Default:

5 \times (2 \times {ncd}^{2} + nce \times (ncf + 4))

The dimension of the array wa.

It is not practical to outline a method for deriving the exact minimum permissible value of iwa, but the following gives a reasonably good conservative approximation. (It should be noted that if iwa is too small (but not grossly so) then the exact minimum is printed if

kpriv \neq 0

Let

q^{'} = q + (Q \times s)

and

d^{'} = d + (D \times s)

where the orders of the output noise model are

p

d

q

P

D

Q

s

Let there be

l

input series, where

l = nser - 1

Let

\begin{array}{l} m x_{i} = \max (b_{i} + q_{i}, p_{i}), & if ​ r_{i} = 3, for ​ i = 1, 2 \dots, l \\ m x_{i} = 0, & if ​ r_{i} \neq 3, for ​ i = 1, 2 \dots, l \end{array}

where the transfer function model orders for input

i

are given by

b_{i}

q_{i}

p_{i}

r_{i}

Let

q x = \max (q^{'}, m x_{1}, m x_{2}, \dots, m x_{l})

Let

ncd = npara + kfc + q x + \sum_{i = 1}^{l} m x_{i}

and

nce = nxxy + d^{'} + 6 \times q x

Finally, let

ncf = nser

, and then increment

ncf

1

every time any of the following conditions is satisfied. (The last six conditions should be applied separately to each input series, so that, for example, if we have two input series and if

p_{1} > 0

and

p_{2} > 0

then

ncf

is incremented by

2

The conditions are:

\begin{aligned} \begin{array}{r} p > 0 \\ q > 0 \\ P > 0 \\ Q > 0 \\ q x > 0 \\ kfc > 0 \end{array}  \\ \begin{aligned} p > 0 \\ q > 0 \\ P > 0 \\ Q > 0 \end{aligned}\} & and ​ q > 0 ​ and ​ kef > 1 . \\ \begin{aligned} p > 0 \\ q > 0 \\ P > 0 \\ Q > 0 \end{aligned}\} & and ​ kfc > 0 ​ and ​ kef = 3 . \\ \begin{aligned} m x_{i} > 0 \\ p_{i} > 0 \\ p > 0 \\ q > 0 \\ P > 0 \\ Q > 0 \end{aligned}\} & and ​ r_{i} = 1 ​ and ​ kef > 3 ​ separately, for ​ i = 1, 2, \dots, l . \end{aligned}

Then

iwa \geq 2 \times {(ncd)}^{2} + (nce) \times (ncf + 4)

9: $imwa$ – int64int32nag_int scalar

Default:

5 \times (16 \times nser + 7 \times ncd + 3 \times npara + 3 \times kfc + 27)

The dimension of the array mwa.

Constraint:

imwa \geq (16 \times nser) + (7 \times ncd) + (3 \times npara) + (3 \times kfc) + 27

, where the derivation of

ncd

is shown under iwa.

If imwa is too small then if

kpriv \neq 0

it is printed.

10: $kpriv$ – int64int32nag_int scalar

Default:

0

Must not be set to

0

, if it is required to monitor the course of the optimization or to print out the requisite minimum values of iwa or imwa in the event of an error of the type

ifail = 6

7

. The course of the optimization is monitored by printing out at each iteration the iteration count (itc), the residual sum of squares (s), the objective function (d) and a description and value for each of the parameters in the para array. The descriptions are PHI for

ϕ

, THETA for

θ

, SPHI for

Φ

, STHETA for

Θ

, OMEGA/SI for

ω

in a simple input, OMEGA for

ω

in a transfer function input, DELTA for

δ

and CONSTANT for

c

. In addition SERIES 1, SERIES 2, etc. indicate the input series relevant to the OMEGA and DELTA parameters.

kpriv must be set to

0

if the print-out of the above information is not required.

Output Parameters

1: $para (npara)$ – double array

The latest values of the estimates of these parameters.

2: $xxy (ldxxy, nser)$ – double array

the columns of xxy hold the corresponding values of the input component series

z_{t}

in place of

x_{t}

and the output noise component

n_{t}

in place of

y_{t}

, in that order.

3: $zsp (4)$ – double array

Contains the values, default or otherwise, used by the function.

4: $itc$ – int64int32nag_int scalar

The number of iterations carried out.

$itc = - 1$: Indicates that the only estimates obtained up to this point have been for the nuisance parameters relating to backforecasts, unless the marginal likelihood option is used, in which case estimates have also been obtained for simple input coefficients $ω$ and for the constant $c$ (if $kfc = 1$ ). This value of itc usually indicates a failure in a consequent step of estimating transfer function input pre-observation period nuisance parameters.
$itc = 0$: Indicates that estimates have been obtained up to this point for the constant $c$ (if $kfc = 1$ ), for simple input coefficients $ω$ and for the nuisance parameters relating to the backforecasts and to transfer function input pre-observation period effects.

5: $sd (npara)$ – double array

The npara values of the standard deviations corresponding to each of the parameters in para. When the constant is fixed its standard deviation is returned as zero. When the values of para are valid, the values of sd are usually also valid. However, if an exit value of

ifail = 3

8

10

, then the contents of sd will be indeterminate.

6: $cm (ldcm, npara)$ – double array

The first npara rows and columns of cm contain the correlation coefficients relating to each pair of parameters in para. All coefficients relating to the constant will be zero if the constant is fixed. The contents of cm will be indeterminate under the same conditions as sd.

7: $s$ – double scalar

The residual sum of squares,

S

, at the latest set of valid parameter estimates.

8: $d$ – double scalar

The objective function,

D

, at the latest set of valid parameter estimates.

9: $ndf$ – int64int32nag_int scalar

The number of degrees of freedom associated with

S

10: $res (nxxy)$ – double array

The values of the residuals relating to the differenced values of the output series. The remainder of the first nxxy terms in the array will be zero.

11: $sttf (isttf)$ – double array

The nsttf values of the state set array.

12: $nsttf$ – int64int32nag_int scalar

The number of values in the state set array sttf.

13: $ifail$ – int64int32nag_int scalar

ifail = 0

unless the function detects an error (see Error Indicators and Warnings).

Error Indicators and Warnings

Note: nag_tsa_multi_inputmod_estim (g13be) may return useful information for one or more of the following detected errors or warnings.

Errors or warnings detected by the function:

$ifail = 1$

On entry,	$kfc < 0$ ,
or	$kfc > 1$ ,
or	$ldxxy < nxxy$ ,
or	$ldcm < npara$ ,
or	$kef < 1$ ,
or	$kef > 3$ ,
or	$nit < 0$ ,
or	$nser < 1$ ,
or	$nser = 1$ and there are no parameters in the model ( $p = q = P = Q = 0$ and $kfc = 0$ ).

$ifail = 2$: On entry, there is inconsistency between npara and kfc on the one hand and the orders in arrays mr and mt on the other, or one of the $r_{i}$ , stored in $mt (4, i) \neq 1$ , $2$ or $3$ .

$ifail = 3$: On entry or during execution, one or more sets of $δ$ parameters do not satisfy the stationarity or invertibility test conditions.

$ifail = 4$

On entry,	when $kzsp = 1$ , $zsp (1) \leq 0.0$ ,
or	$zsp (2) \leq 1.0$ ,
or	$zsp (3) < 1.0$ ,
or	$zsp (4) < 0.0$ ,
or	$zsp (4) \geq 1.0$ .

$ifail = 5$: On entry, iwa is too small by a considerable margin. No information is supplied about the requisite minimum size.

$ifail = 6$: On entry, iwa is too small, but the requisite minimum size is returned in $mwa (1)$ , which is printed if $kpriv \neq 0$ .

$ifail = 7$: On entry, imwa is too small, but the requisite minimum size is returned in $mwa (1)$ , which is printed if $kpriv \neq 0$ .

$ifail = 8$: This indicates a failure in nag_linsys_real_posdef_solve_1rhs (f04as) which is used to solve the equations giving the latest estimates of the parameters.

$ifail = 9$: This indicates a failure in the inversion of the second derivative matrix. This is needed in the calculation of the correlation matrix and the standard deviations of the parameter estimates.

$ifail = 10$: On entry or during execution, one or more sets of the ARIMA ( $ϕ$ , $θ$ , $Φ$ or $Θ$ ) parameters do not satisfy the stationarity or invertibility test conditions.

$ifail = 11$: On entry, isttf is too small. The state set information will not be produced and if $kzef \neq 0$ array xxy will remain unchanged. All other arguments will be produced correctly.

$ifail = 12$: The function has failed to converge after nit iterations. If steady decreases in the objective function, $D$ , were monitored up to the point where this exit occurred, then the exit probably occurred because nit was set too small, so the calculations should be restarted from the final point held in para.

$ifail = 13$: On entry, isttf is too small (see $ifail = 11$ ) and nit iterations were carried out without the convergence conditions being satisfied (see $ifail = 12$ ).

$ifail = - 99$: An unexpected error has been triggered by this routine. Please contact NAG.

$ifail = - 399$: Your licence key may have expired or may not have been installed correctly.

$ifail = - 999$: Dynamic memory allocation failed.

Accuracy

The computation used is believed to be stable.

Further Comments

The time taken by nag_tsa_multi_inputmod_estim (g13be) is approximately proportional to

nxxy \times itc \times {npara}^{2}

Example

After the full

11

iterations, the following are computed and printed out: the final values of the para parameters and their standard errors, the correlation matrix, the residuals for the

36

differenced values, the values of

z_{t}

and

n_{t}

, the values of the state set and the number of degrees of freedom.

Open in the MATLAB editor: g13be_example

function g13be_example


fprintf('g13be example results\n\n');

% orders
mr = [int64(1); 0; 0; 0; 0; 1; 4];
% transfer function
mt = zeros(4, 2, 'int64');
mt(1:4,1) = [1;      0;       1;       3];

% Parameters
para = [0;     0;     2;     0.5;     0];

% series data
xxy = [8.075, 105;    7.819, 119;     7.366, 119;     8.113, 109;
       7.380, 117;    7.134, 135;     7.222, 126;     7.768, 112;
       7.386, 116;    6.965, 122;     6.478, 115;     8.105, 115;
       8.060, 122;    7.684, 138;     7.580, 135;     7.093, 125;
       6.129, 115;    6.026, 108;     6.679, 100;     7.414,  96;
       7.112, 107;    7.762, 115;     7.645, 123;     8.639, 122;
       7.667, 128;    8.080, 136;     6.678, 140;     6.739, 122;
       5.569, 102;    5.049, 103;     5.642,  89;     6.808,  77;
       6.636,  89;    8.241,  94;     7.968, 104;     8.044, 108;
       7.791, 119;    7.024, 126;     6.102, 119;     6.053, 103];
nxxy = size(xxy,1);

% Marginnal likelihood
kef = int64(3);

% Fit model
[para, xxy, zsp, itc, sd, cm, s, d, ndf, res, sttf, nsttf, ifail] = ...
  g13be( ...
         mr, mt, para, xxy, 'kef', kef);

%  Display results
fprintf('The number of iterations carried out is %4d\n\n', itc);
fprintf('Final values of the parameters and their standard deviations\n\n');
fprintf('   i          parameter                sd\n\n');
ivar = [1:numel(para)]';
fprintf('%4d%20.6f%20.6f\n', [ivar para sd]');
fprintf('\n');
[ifail] = x04ca( ...
                 'General', ' ', cm, 'The correlation matrix is');

fprintf('\nThe residuals and the z and n values are\n\n');
fprintf('   i          res             z             n\n\n');
ndv = nxxy - mr(2) - mr(5)*mr(7);
ival = double([1:ndv]');
fprintf('%4d%15.3f%15.3f%15.3f\n', [ival res xxy(1:ndv,:)]');
ival = double([ndv+1:nxxy]');
fprintf('%4d%30.3f%15.3f\n', [ival xxy(ndv+1:nxxy,:)]');
fprintf('\nThe state set consists of %4d values\n\n', nsttf);
disp(sttf');
fprintf('\nThe number of degrees of freedom is %4d\n', ndf);

g13be example results

The number of iterations carried out is   11

Final values of the parameters and their standard deviations

   i          parameter                sd

   1            0.380924            0.166379
   2           -0.257786            0.178178
   3            8.956084            0.948061
   4            0.659641            0.060239
   5          -75.435521           33.505341

 The correlation matrix is
          1       2       3       4       5
 1   1.0000 -0.1839 -0.1775 -0.0340  0.1394
 2  -0.1839  1.0000  0.0518  0.2547 -0.2860
 3  -0.1775  0.0518  1.0000 -0.3070 -0.2926
 4  -0.0340  0.2547 -0.3070  1.0000 -0.8185
 5   0.1394 -0.2860 -0.2926 -0.8185  1.0000

The residuals and the z and n values are

   i          res             z             n

   1          0.397        180.567        -75.567
   2          3.086        191.430        -72.430
   3         -2.818        196.302        -77.302
   4         -9.941        195.460        -86.460
   5         -5.061        201.594        -84.594
   6         14.053        199.076        -64.076
   7          2.624        195.211        -69.211
   8         -5.823        193.450        -81.450
   9         -2.147        197.179        -81.179
  10         -0.216        196.217        -74.217
  11         -2.517        191.812        -76.812
  12          7.916        184.544        -69.544
  13          1.423        194.322        -72.322
  14         11.936        200.369        -62.369
  15          5.117        200.990        -65.990
  16         -5.672        200.468        -75.468
  17         -5.681        195.763        -80.763
  18         -1.637        184.025        -76.025
  19         -1.019        175.360        -75.360
  20         -2.623        175.492        -79.492
  21          3.283        182.162        -75.162
  22          6.896        183.857        -68.857
  23          5.395        190.797        -67.797
  24          0.875        194.327        -72.327
  25         -4.153        205.558        -77.558
  26          6.206        204.261        -68.261
  27          4.208        207.104        -67.104
  28         -2.387        196.423        -74.423
  29        -11.803        189.924        -87.924
  30          6.435        175.158        -72.158
  31          1.342        160.761        -71.761
  32         -4.924        156.575        -79.575
  33          4.799        164.256        -75.256
  34         -0.074        167.783        -73.783
  35         -6.023        184.483        -80.483
  36         -6.427        193.055        -85.055
  37         -2.527        199.390        -80.390
  38          2.039        201.302        -75.302
  39          0.243        195.695        -76.695
  40         -3.166        183.738        -80.738

The state set consists of    6 values

    6.0530  183.7384   -5.7855   -0.1645    0.1800   -3.0977


The number of degrees of freedom is   34

PDF version (NAG web site, 64-bit version, 64-bit version)

Chapter Contents

Chapter Introduction

NAG Toolbox