PSPP Regression with /noorigin

[Hulliger Beat]

 

Last week a student asked me whether he should eliminate the intercept in a simple linear regression when it is not significantly different from 0. Yes, I said: It is very simple to remove it in PSPP. How wrong was I! There is no option /NOORIGIN in the PSPP Regression procedure.

 

I have seen the discussions about this issue and the corresponding proposals. I tried GLM but no coefficients are output. I tried with dummies but a bit of algebra convinced me that this does not work.  I thought the simplest thing is to delete the column of ones in the design matrix. I have downloaded the code and looked into linreg.c. Of course, things are a bit more complicated than it seems at first. Say, my knowledge of C is not enough to venture into the code.   

 

So back to crude SPSS-Syntax for simple linear regression (say a ratio model): See the code below.

 

It would be nice to have a /noorigin option in the Regression procedure!

 

Beat

 

-------------

* Regression through the origin: Ratio model with PSPP.

* Assign y and x.

compute y = Balance.

compute x = ATM.

 

* Regression y=beta*x.

COMPUTE xx = x * x.

COMPUTE yx = y * x.

COMPUTE >

EXECUTE.

 

AGGREGATE OUTFILE=* MODE=ADDVARIABLES

               /PRESORTED

               /BREAK= one

               /sumyx = SUM (yx)

               /sumxx = SUM (xx)

               /nsamp = sum(one).

 

COMPUTE beta = sumyx/sumxx.

COMPUTE resid = y - beta * x.

COMPUTE resid2 = resid * resid.

 

AGGREGATE OUTFILE=* MODE=ADDVARIABLES

               /PRESORTED

               /BREAK= one

               /SSE = SUM (resid2).

 

COMPUTE SER = sqrt(SSE/(nsamp-1)).

EXECUTE.

 

LIST

      /Variables beta SER

      /cases = from 1 to 1.

 

delete variables y x one yx xx sumyx sumxx nsamp beta resid2 SSE SER.