Transformation of Variables - x=f(x) Tab

Select the x=f(x) tab of the Transformations of Variables dialog box to access the options described here.

Element Name Description
OK (Transform selected series) Click the OK (Transform selected series) button to transform the selected variable (series) and display a plot of the analysis. Transformed variables are appended to the active work area. If a transformation produces an invalid value (e.g., square root of a negative value, division by zero, etc.), Statistica assigns a missing data value; then, in a second pass, those missing data are replaced according to your selection on the Time Series Analysis Startup Panel - Missing Data tab.
Transformation Use the options in the Transformation group box to select the desired type of transformation.
Add a constant (x=x+C) If you select the Add a constant (x=x+C) option button, a constant C (where C is the value you enter in the adjacent C= box) is added to all values in the Transform variable. By default, this constant is equal to minus the smallest value in the series, so that after the transformation the minimum value of the series is equal to 0 (zero).
Power (x=x**C) If you select the Power (x=x**C) option button, each value in the series is transformed as: x=xC.
Inverse power (x=x**1/C) If you select the Inverse power (x=x**1/C) option button, each value in the series is transformed as: x=x(1/C).
Natural log (x=ln(x)) If you select the Natural log (x=ln(x)) option button, each value in the series is transformed as: x=natural log(X).
Exponent (x=exp(x)) If you select the Exponent (x=exp(x)) option button, each value in the series is transformed as: x=eX [where e is the base of the natural logarithm, sometimes called Euler's e (2.71...)].
Mean subtract (x=x-M) If you select the Mean subtract (x=x-M) option button, each value in the series is transformed as x=x-M; where M is either (1) the overall mean for the untransformed series, or (2) the value specified in the adjacent M= box, depending on the setting of the Estimate mean & std. dev. from data check box (see below).
Standardize (x=(x-M)/SD) If you select the Standardize (x=(x-M)/SD) option button, each value in the series is standardized: x=(x-M)/SD; where M and SD are either (1) the overall mean and standard deviation for the untransformed series, or (2) the values specified in the adjacent M= and S= boxes, depending on the setting of the Estimate mean & std. dev. from data check box (see below).
Estimate mean & std. dev. from data. If you select the Estimate mean & std. dev. from data check box, the mean and/or standard deviation is computed from the data for the two transformations described in the previous two paragraphs. If the check box is cleared, the values you enter in the M= and S= boxes are used.
Trend subtract (x=x-(a+b*t)). If you select the Trend subtract (x=x-(a+b*t)) option button, the values in the series are transformed to remove the trend over time: x=x-(a+b*t). In this formula, t refers to the case number and a and b are constants that are either user-defined (the values specified in the adjacent a= and b= boxes) or computed from the data, depending on the setting of the Estimate a/b from data check box (see below).
Autocorr. (x=x-(a+b*x(lag))). If you select the Autocorr. (x=x-(a+b*x(lag))) option button, the values in the series are transformed to remove an autocorrelation of a particular lag: x=x-(a+b*X(lag)). In this formula, a and b are constants that are either user-defined (the values specified in the adjacent a= and b= boxes) or computed from the data (via least squares regression), depending on the setting of the Estimate a/b from data check box (see below). The lag in the computations is determined by the value entered in the Lag box (see below).
Estimate a/b from data If you select the Estimate a/b from data check box, the intercept (a) and slope (b) are computed from the data (via least squares regression) for the two transformations described in the previous two paragraphs. If the check box is cleared, the values you enter in the a= and b= boxes are used.
Lag Enter a value in the Lag box (or adjust the value with the microscrolls) to specify the lag value to be used in the Autocorrelation computation (see above).