Utility Package
CLIMITS Methods
CLIMITS.Compute Method
rc=obj.Compute (Actual, Predicted,<Alpha>);
Computes the prediction standard errors and confidence limits for specified actual and predicted time series. Both input series are validated by ascertaining the presence of nonmissing observation values under at least one matching index. Also, the predicted series is checked for the presence of extreme values. The computed forecast series are stored in the object’s internal memory and can be individually queried via the GetForecast method into a numeric array defined in the user program. A negative return code indicates that the validation of an input series failed (for example, the predicted series has extreme values or all missing values), you specified an out-of-range Alpha argument value, or a computational failure occurred (for example, out-of-memory error).
Input Arguments
You must specify the following input arguments:
- Actual
specifies a numeric array that corresponds to the actual time series.
- Predicted
specifies a numeric array that corresponds to the predicted time series.
You can also specify the following input argument:
- Alpha
takes a numeric value between 0 and 1, exclusive, that specifies the significance level for forecast confidence bands. The default value is 0.05.
CLIMITS.GetForecast Method
rc=obj.GetForecast (Which,Result));
Places the specified forecast series (Which) from the CLIMITS object into the specified numeric array (Result). Forecast series have the same length as the predicted series that is supplied to the Compute method via its Predicted argument. The GetForecast method returns a negative status code if the Compute method returned a non zero value or if it was not yet executed (that is, no results exist to be queried).
Input Arguments
You must specify the following input argument:
- Which
is a case-insensitive character string that specifies the type of forecast series to return. You can specify one of the following values:
- LOWER
returns a lower confidence limit series.
- STDERR
returns a prediction standard error series.
- UPPER
returns an upper confidence limit series.
Output Arguments
You must specify the following output argument:
- Result
specifies a numeric array to receive the forecast series. If the array length is longer than the requested series, it is padded with missing values.