For technical questions regarding estimation of single equations, systems, VARs, Factor analysis and State Space Models in EViews. General econometric questions and advice should go in the Econometric Discussions forum.
What do you mean by "estimation". There is no estimation there. You're just creating (presumably) a series that is equal to the 4 period difference in the other series.
If that's what you are doing, you can just do a unit root test, or whatever other test you would use for stationarity, on that new series.
Hello : Should one always difference before log transforming variables for stationarity? My >5000 obs dataset of stock index variables are non-stationary but show stationarity when logged to obtain return variables. Do I still need to difference?