![TS_LACK OF FIT function [Time Series]](arrow-left.gif){kind=icon}
![TS_MAX_ARMA_AR function [Time Series]](arrow-right.gif){kind=icon}
This function is available only with RAP – The Trading Edition Enterprise.
Performs the lack-of-fit test for a univariate time series. This function is identical to “TS_LACK OF FIT function [Time Series]”, except that it returns the p-value of q, rather than returning q.
TS_LACK OF FIT_P (timeseries_expression, p_value, q_value, lagmax, [tolerance])
OVER (window-spec)
timeseries_expression A numeric expression, generally a column name, containing an element in a time series.
p_value An integer containing the number of autoregressive parameters.
q_value An integer containing the number of moving average parameters.
lagmax An integer containing the maximum log of the correlation function.
tolerance (An optional parameter). A floating-point value level used to determine convergence of the nonlinear least-squares algorithm. The default value is 0.
window-spec TS_LACK_OF_FIT_P is an OLAP function requiring an OVER () clause.
This function returns a double-precision floating-point value containing the p-value of the lack-of-fit statistic (q) for the time series. TS_LACK_OF_FIT_P calls the function imsls_d_lack_of_fit in the IMSL libraries.
The arguments of TS_LACK_OF_FIT_P map to the IMSL library function imsls_d_lack_of_fit as follows:
params = imsls_d_arma(n_objs, z[], p, q, IMSLS_LEAST_SQUARES, IMSLS_CONVERGENCE_TOLERANCE, tolerance, IMSL_RESIDUAL, &residual, 0);correlations = imsls_d_autocorrelation(n_objs-p+lagmax, residuals, lagmax, 0);result = imsls_d_lack_of_fit(n_objs, correlations, lagmax, npfree, 0);
n_objs Contains the number of rows in the current window frame.
z[] Contains the value of timeseries_expression for the current window frame.
p Maps to the p_value argument defined in TS_LACK_OF_FIT_P.
q Maps to the q_value argument defined in TS_LACK_OF_FIT_P.
lagmax Maps to the lagmax argument defined in TS_LACK_OF_FIT_P.
tolerance An optional argument using IMSLS_CONVERGENCE_TOLERANCE. If null, the IMSL library applies a default value and does not use IMSLS_CONVERGENCE_TOLERANCE.
For detailed information on how the IMSL function imsls_d_lack_of_fit performs 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_LACK_OF_FIT_P 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:
rownum |
data |
|---|---|
1 |
0.315523 |
2 |
0.485859 |
3 |
0.676886 |
4 |
1.97381 |
5 |
2.77555 |
6 |
2.73657 |
7 |
2.64233 |
8 |
4.26118 |
9 |
3.13641 |
10 |
4.16566 |
11 |
2.95952 |
12 |
2.14504 |
13 |
1.98799 |
14 |
0.805859 |
15 |
0.833405 |
16 |
2.29075 |
17 |
1.30045 |
18 |
0.467122 |
19 |
-0.170107 |
20 |
-0.256657 |
21 |
-0.382597 |
22 |
-0.505511 |
23 |
-1.90147 |
24 |
-0.981688 |
25 |
-1.43116 |
26 |
-1.39389 |
27 |
-2.34823 |
28 |
-2.91122 |
29 |
-0.927423 |
30 |
-0.044383 |
31 |
-0.389648 |
32 |
0.545008 |
33 |
0.614096 |
34 |
0.364668 |
35 |
1.16043 |
36 |
-0.654063 |
37 |
0.616094 |
38 |
2.00875 |
39 |
1.86696 |
40 |
2.80171 |
41 |
3.78422 |
42 |
4.11499 |
43 |
2.77188 |
44 |
4.00312 |
45 |
4.21298 |
46 |
5.00413 |
47 |
4.74498 |
48 |
4.89621 |
49 |
3.93273 |
50 |
4.31592 |
The following SQL statement returns the p value of the lack of fit statistic on data from the data column:
select ts_lack_of_fit_p(data,1,1,5,0.225) 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:
res |
|---|
0.735006 |
0.735006 |
0.735006 |
0.735006 |
0.735006 |
0.735006 |
0.735006 |
0.735006 |
0.735006 |
0.735006 |
... |
0.735006 |
Chapter 2, “Using OLAP” in the System Administration Guide: Volume 2
IMSL Numerical Library User’s Guide: Volume 2 of 2 C Stat Library
