Missing Data Treatment The Missing Data Treatment Tab

Missing Data Treatment

To select a missing data treatment method that is used to calculate missing values in variables, use the Missing Data Treatment side panel tab.

Make sure that the side panel is displayed.
Select output variable or one of the equation links.
Go to the Missing Data Treatment side panel tab.

If missing data treatment is required, select the Apply checkbox and select one of the methods:

Casewise. Default. Empty values are excluded from the series. Calculations are executed without considering them.

Geometric Interpolation. Empty values of series are calculated using geometric interpolation.

Overlay. Empty values of the output series are replaced with values of the series specified in the Series with Values parameter.

Cubic Spline Interpolation. Empty values of series are calculated using cubic spline interpolation.

Linear Interpolation. Empty values of series are calculated using linear interpolation by two neighbor points.

Linear Trend. Empty values of series are calculated using linear trend.

Pattern. Empty values of series are calculated using pattern interpolation. Select the variable representing the template data series in the Pattern Series parameter.

Previous Value. Empty values of series are replaced with the previous non-empty value.

Random Value. Empty values of series are replaced with a random number that belongs to the interval [minimum series value; maximum series value].

Succeeding Value. Empty values of series are replaced with the succeeding non-empty value.

Average. Empty values of series are calculated as average.

N-Point Average. Empty values of series are calculated as N-point average. Select the number of neighbor points (N) in the Parameter box.

Previous Growth Rate. Empty values of series are calculated based on growth rate of existing values in comparison with the previous period. Select the number of periods in the Parameter box.

Succeeding Growth Rate. Empty values of series are calculated based on growth rate of the existing values for the succeeding period. Select the number of periods in the Parameter box.

Value. Empty values of series are replaced with the value selected in the Parameter box.

To set the series, select it in the Pattern Series/Series with Values drop-down list or:

Select the variable in the data view area (the Scheme view).
Hold down the main button mouse button and drag the variable to the Pattern Series box.
Release the mouse button. Values of the variable are used to substitute the missing data.

To remove the pattern series, click the button.

NOTE. If a variable used as a pattern series or a series with values is removed from the model, specify a variable that will be used instead of the removed one in the missing data treatment method.