TS_PARTIAL_AUTOCORRELATION function [Time Series]

Calculates the sample partial autocorrelation function of a stationary time series.

TS_PARTIAL_AUTOCORRELATION (timeseries_expression, lagmax, lag_elem)

OVER (window-spec)

This function returns an outlier-free time series. TS_PARTIAL_AUTOCORRELATION calls the function imsls_d_autocorrelation and imsls_d_partial_autocorrelation in the IMSL libraries.

The arguments of TS_PARTIAL_AUTOCORRELATION map to the IMSL library functions imsls_d_autocorrelation and imsls_d_partial_autocorrelation as follows:

params = imsls_d_autocorrelation(n_objs, z[], lagmax, 0);

result = imsls_d_partial_autocorrelation(lagmax, params, 0);

For detailed information on how the IMSL functions imsls_d_autocorrelation and imsls_d_partial_autocorrelation perform time series calculations, see IMSL Numerical Library User’s Guide: Volume 2 of 2 C Stat Library.

This example shows an input data table, a SQL statement containing the TS_PARTIAL_AUTOCORRELATION function, and the data values returned by the function. This example uses the following table (called DATASET) as its input data. The DATASET table contains 50 rows of time series data:

The following SQL statement returns the first element from an array containing partial autocorrelations of data from the data column:

select ts_partial_autocorrelation(data,1,1) over (order by rownum rows between unbounded preceding and unbounded following) as res FROM DATASET

Sybase IQ returns 50 rows, each containing the same value: