27.03.2013 Views

SPSS® 12.0 Command Syntax Reference

SPSS® 12.0 Command Syntax Reference

SPSS® 12.0 Command Syntax Reference

SHOW MORE
SHOW LESS

You also want an ePaper? Increase the reach of your titles

YUMPU automatically turns print PDFs into web optimized ePapers that Google loves.

154 <strong>Syntax</strong> <strong>Reference</strong><br />

Subcommand Order<br />

<strong>Syntax</strong> Rules<br />

Operations<br />

standard errors of prediction (SEP#1). (For variable naming and labeling conventions, see<br />

“New Variables” on p. 1734.)<br />

• By default, ARIMA will iterate up to a maximum of 10 unless one of three termination criteria<br />

is met: the change in all parameters is less than the TSET CNVERGE value (the default<br />

value is 0.001); the sum-of-squares percentage change is less than 0.001%; or the<br />

Marquardt constant exceeds 10 9 (1.0E9).<br />

• At each iteration, the Marquardt constant and adjusted sum of squares are displayed. For<br />

the final estimates, the displayed results include the parameter estimates, standard errors,<br />

t ratios, estimate of residual variance, standard error of the estimate, log likelihood,<br />

Akaike’s information criterion (AIC) (Akaike, 1974), Schwartz’s Bayesian criterion<br />

(SBC) (Schwartz, 1978), and covariance and correlation matrices.<br />

• Subcommands can be specified in any order.<br />

• VARIABLES can be specified only once.<br />

• Other subcommands can be specified more than once, but only the last specification of<br />

each one is executed.<br />

• The CONSTANT, NOCONSTANT, NOLOG, LN, and LOG specifications are optional keywords<br />

on the MODEL subcommand and are not independent subcommands.<br />

• If differencing is specified in models with regressors, both the dependent series and the<br />

regressors are differenced. To difference only the dependent series, use the DIFF or SDIFF<br />

function on CREATE to create a new series (see CREATE in the SPSS <strong>Syntax</strong> <strong>Reference</strong><br />

Guide).<br />

• When ARIMA is used with the PREDICT command to forecast values beyond the end of<br />

the series, the original series and residual variable are assigned the system-missing value<br />

after the last case in the original series.<br />

• The USE and PREDICT ranges cannot be exactly the same; at least one case from the USE<br />

period must precede the PREDICT period. (See USE and PREDICT in the SPSS <strong>Syntax</strong> <strong>Reference</strong><br />

Guide<br />

• If a LOG or LN transformation is specified, the residual (error) series is reported in the<br />

logged metric; it is not transformed back to the original metric. This is so the proper diagnostic<br />

checks can be done on the residuals. However, the predicted (forecast) values<br />

are transformed back to the original metric. Thus, the observed value minus the predicted<br />

value will not equal the residual value. A new residual variable in the original metric can<br />

be computed by subtracting the predicted value from the observed value.<br />

• Specifications on the P, D, Q, SP, SD, and SQ subcommands override specifications on<br />

the MODEL subcommand.

Hooray! Your file is uploaded and ready to be published.

Saved successfully!

Ooh no, something went wrong!