BookmarkSubscribeRSS Feed
🔒 This topic is solved and locked. Need further help from the community? Please sign in and ask a new question.
nassimsa
Obsidian | Level 7

Hello

 

I am a beginner in SAS and i need to make elasticities matrices on it. I did my best to use the PDF code provided by SAS for a translog function but i have an ERROR that i am trying to solv for more than a weak and still nothing.

Please if you can hel i need to get the result ASAP.

Thanks a lot

 

376 proc iml;
NOTE: IML Ready
377 /*Read in parameter estimates*/
378 use est;
379 read all var {gcc gcg gcf gch gce gcs};
380 read all var {ggg ggf ggh gge ggs};
381 read all var {ghh ghf ghe ghs};
382 read all var {gee gef ges};
383 read all var {gss gsf};
384 close est;
385
386 /*Calculate S parameter based on homogeneity constraint*/
387 gfs=0-gcs-ggs-ghs-ges-gss;
388
389 /*Read in mean cost shares and construct vector*/
390 use meanshares;
391 read all var {sc sg sf sh se ss};
392 close meanshares;
393
394 w = sc//sg//sf//sh//se//ss;
395
396 print w;
397
398 /*Construct matrix of parameter estimates*/
399 gij = (gcc||ggc||gcf||gch||gce||gsc)//
400 (ggc||ggg||ggf||ggh||gge||ggs)//
401 (gcf||ggf||gff||gfh||gfe||gfs)//
402 (gch||ggh||gfh||ghh||ghe||ghs)//
403 (gce||gge||gfe||ghe||gee||ges)//
404 (gsc||ggs||gfs||ghs||ges||gss) ;
ERROR: (execution) Matrices do not conform to the operation.
 
operation : // at line 399 column 39
operands : _TEM1005, _TEM1010
 
_TEM1005 1 row 4 cols (numeric)
 
-0.179326 0.0149951 0.1827359 -0.001691
 
_TEM1010 1 row 5 cols (numeric)
 
-0.004915 -0.008446 0.0382183 -0.004144 -0.003238
 
statement : ASSIGN at line 399 column 3
405
406 print gij;
ERROR: Matrix gij has not been set to a value.
 
statement : PRINT at line 406 column 4
407
408 nk=ncol(gij);
409 mi = -1#I(nk);
ERROR: (execution) Invalid operand to operation.
 
operation : I at line 409 column 13
operands : nk
 
nk 1 row 1 col (numeric)
 
0
 
statement : ASSIGN at line 409 column 4
409 ! /*Initialize negative identity matrix*/
410 eos = j(nk,nk,0);
ERROR: (execution) Invalid operand to operation.
 
operation : J at line 410 column 11
operands : nk, nk, *LIT1009
 
nk 1 row 1 col (numeric)
 
0
 
nk 1 row 1 col (numeric)
 
0
 
*LIT1009 1 row 1 col (numeric)
 
0
 
statement : ASSIGN at line 410 column 4
410 ! /*Initialize Marshallian EOS Matrix*/
411 mos = j(nk,nk,0);
ERROR: (execution) Invalid operand to operation.
 
operation : J at line 411 column 11
operands : nk, nk, *LIT1010
 
nk 1 row 1 col (numeric)
 
0
 
nk 1 row 1 col (numeric)
 
0
 
*LIT1010 1 row 1 col (numeric)
 
0
 
statement : ASSIGN at line 411 column 4
411 ! /*Initialize Morishima EOS Matrix*/
412 ep = j(nk,nk,0);
ERROR: (execution) Invalid operand to operation.
 
operation : J at line 412 column 11
operands : nk, nk, *LIT1011
 
nk 1 row 1 col (numeric)
 
0
 
nk 1 row 1 col (numeric)
 
0
 
*LIT1011 1 row 1 col (numeric)
 
0
 
statement : ASSIGN at line 412 column 4
412 ! /*Initialize Price EOD Matrix*/
413
414 /*Calculate Marshallian EOS and Price EOD Matrices*/
415 i=1;
416 do i=1 to nk;
417 j=1;
418 do j=1 to nk;
419 eos[i,j] = (gij[i,j]+w[i]#w[j]+mi[i,j]#w[i])/(w[i]#w[j]);
420 ep[i,j] = w[j]#eos[i,j];
421 end;
422 end;
423
424 /*Calculate Morishima EOS Matrix*/
425 i=1;
426 do i=1 to nk;
427 j=1;
428 do j=1 to nk;
429 mos[i,j] = ep[i,j]-ep[j,j];
430 end;
431 end;
432
433 /*Print Elasticity Matrices*/
434 factors = {"Coal" "Gas" "Fuel" "Hydraulic" "Wind" "Solar"};
435 print
436 ep[label="Price Elasticities of Demand" rowname=factors colname=factors
437 format=d7.3],
438 eos[label="Hicks-Allen Elasticities of Substitution" rowname=factors colname=factors
439 format=d7.3],
440 mos[label="Morishima Elasticities of Substitution" rowname=factors colname=factors
441 format=d7.3];
ERROR: Matrix ep has not been set to a value.
 
statement : PRINT at line 435 column 4
442
443
444
445
446 OPTIONS NONOTES NOSTIMER NOSOURCE NOSYNTAXCHECK;
458
 
1 ACCEPTED SOLUTION

Accepted Solutions
PeterClemmensen
Tourmaline | Level 20

Haven't looked through all the error messages, but at line 399 you do a lot of concatenation of matrices. However, there is a mismatch between the dimensions as one of the vectors has 4 columns and another has 5.

 

Use 

 

show names;

to check the attributes of all of the matrices in your current IML session and work from there.

View solution in original post

3 REPLIES 3
PeterClemmensen
Tourmaline | Level 20

Haven't looked through all the error messages, but at line 399 you do a lot of concatenation of matrices. However, there is a mismatch between the dimensions as one of the vectors has 4 columns and another has 5.

 

Use 

 

show names;

to check the attributes of all of the matrices in your current IML session and work from there.

nassimsa
Obsidian | Level 7

Thank you very much for your prompt reply and for the help.

It was as you said a problem of dimension and i replaced this part :

 

     "read all var {gcc gcg gcf gch gce gcs};
380 read all var {ggg ggf ggh gge ggs};
381 read all var {ghh ghf ghe ghs};
382 read all var {gee gef ges};
383 read all var {gss gsf};"
 
I didn't include all the vectors so to avoid having one with 4 and another with 5 i did this :
 
      read all var {gcc gcg gcf gch gce gcs ggc ggg ggf ggh gge ggs ghc ghg ghf ghh ghe ghs gec geg gef geh gee ges gsc gsg gsf gsh gse gss};
 
 
 
PeterClemmensen
Tourmaline | Level 20

No problem 🙂 Glad you found your answer.

sas-innovate-2024.png

Don't miss out on SAS Innovate - Register now for the FREE Livestream!

Can't make it to Vegas? No problem! Watch our general sessions LIVE or on-demand starting April 17th. Hear from SAS execs, best-selling author Adam Grant, Hot Ones host Sean Evans, top tech journalist Kara Swisher, AI expert Cassie Kozyrkov, and the mind-blowing dance crew iLuminate! Plus, get access to over 20 breakout sessions.

 

Register now!

Multiple Linear Regression in SAS

Learn how to run multiple linear regression models with and without interactions, presented by SAS user Alex Chaplin.

Find more tutorials on the SAS Users YouTube channel.

From The DO Loop
Want more? Visit our blog for more articles like these.
Discussion stats
  • 3 replies
  • 1182 views
  • 4 likes
  • 2 in conversation