Operator "D" in regression

[alimou]

A simple and quick question, hopefully easy to answer.
I have estmated the following equation in EViews 12: LS DLOG(AUME_RRR) C DLOG(AUME_RRR(-1)) D LOG(AUMEPEDY(4)) DLOG(AUSY_RRR)

The substitued coefficients of the equation is:
DLOG(AUME_RRR) = -0.0361796455841 - 0.492869649054*DLOG(AUME_RRR(-1)) + 0.00295761368427*LOG(AUMEPEDY(4)) + 0.849704965215*DLOG(AUSY_RRR) + [D=-1.04022585673,UNCOND]

My question is how do interpret the "D" in the above? What does it represent? Is that the residuals? (FYI - I came across the D in an equation accidentally)

[EViews Gareth]

Fractional integration term for ARFIMA models.

[alimou]

Thank you Gareth. The was the answer I was looking for.

I have another quick request please. I'd like to create a series that is equal to the average of another series X over a certain period of time (e.g. 2 years). My data is in quarterly frequency. I'm using the following expression:
series Y = @mean( X, "2022.3 2024.2")
I'd like to automate this in the program with parameters/variables:
!QTR_START = 2022.3
!QTR_END = 2024.2
However, the expression series Y = @mean( X, "!QTR_START !QTR_END") returns an error message.
Any suggestion to solve this?

[alimou]

Also, I'd like to use @dateadd(!QTR_END, -8, "Q") in the expression so that I will just one parameter !QTR_END to set!

[EViews Gareth]

Code: Select all

%end = "2024.2" %start = @datestr(@dateadd(@dateval(%end), -9, "Q"), "YYYY.QQ") %smpl = %start + " " + %end series y = @mean(x, %smpl)

[alimou]

Thank you Gareth. Always helpful!