Programming the statistical procedures from SAS

Journal quaity regression output table

Accepted Solution Solved
Reply
Frequent Contributor
Posts: 107
Accepted Solution

Journal quaity regression output table

[ Edited ]

 

Hello Everyone,

 

Following on the post by zzecon

(https://communities.sas.com/t5/SAS-Procedures/Making-a-publication-quality-table-from-regression-res...)

I would also like to produce regression output like this one: regression (1).png

Using the following code, I get a slightly diffferent output.

 

/*write a dataset with standard error on the same column of coefficient*/

data parmest_;

set work.parmest;

if not missing(stderr) and variable not in ('R-Square','Root MSE','N. Obs.') then do;

value=estimate; type='coefficient'; output; end;

if not missing(stderr) then do; value=stderr; type='stderr' ;output; end;

if variable in ('R-Square','Root MSE','N. Obs.') then do; value=estimate; type=variable ;output; end;

run;

proc format;

picture stderrf (round)

low-high=' 9.9999)' (prefix='(')

.=' ';

run;

 

 

proc report data=parmest_ nowd out=table;

column numord variable type dependent, (probt value);

define numord /group order=data noprint;

define variable / group order=data ' ';

define type / group order=data noprint;

define dependent / across ' ';

define value /analysis sum;

define probt /analysis sum;

compute value;

array cc _c8_ _c6_ _c4_ ;

if type='stderr' then do;

call define(_col_,'format','stderrf.');

end;

else do;

call define(_col_,'format','8.4');

do i= 1 to 3;

if ~missing(cc(i)) then do;

if 0.05<cc(i) <= 0.1 then call define(_col_, "style", "style=[ posttext='*']" );

else if 0.01 <cc(i) <=0.05 then call define(_col_, "style", "style=[ posttext='**']" );

else if cc(i) <= 0.01 then call define(_col_, "style", "style=[ posttext='***']" );

leave; end;

end;

end;

endcomp;

run;

 

This is what my output table looks like:

 

I see two problems:

1. I have two regressions.  I would like to see the output side-by-side (as above) I only see one here.

2. the coefficients and standard error values are actually different than in my table (attached), as if I would changing it unintentionally.

 

Thanks for your help.

 

  indavgcostPr > |t| value
Intercept<.00018453.102***
 <.0001(1.3810)
tag130.7400-127.069
 0.7400(9.6254)
avgcontract<.0001-1224.34***
 <.0001(8.2317)
tag13*avgcontract1.556246.4737
 1.5562(2.5511)
ses0.0530-42.3237*
 0.0530(1.8749)
female0.0064-780.368***
 0.0064(6.3947)
age_gr<.0001-2138.21***
 <.0001(4.8519)
age_gr<.0001-1909.67***
 <.0001(4.0391)
age_gr<.0001-1802.40***
 <.0001(2.4117)
age_gr<.0001-1830.20***
 <.0001(0.5354)
age_gr<.0001-1448.62***
 <.0001(3.2364)
age_gr<.0001-1609.45***
 <.0001(1.8672)
age_gr<.0001-1557.71***
 <.0001(4.7518)
age_gr<.0001-1618.78***
 <.0001(1.6792)
age_gr<.0001-1112.25***
 <.0001(4.4247)
age_gr<.0001-1069.81***
 <.0001(3.9204)
age_gr<.0001-1245.90***
 <.0001(0.5962)
age_gr<.0001-1336.19***
 <.0001(7.3560)
age_gr<.0001-1608.00***
 <.0001(6.7212)
age_gr<.0001-1644.24***
 <.0001(7.9121)
age_gr<.0001-993.303***
 <.0001(8.1234)
age_gr<.0001-1310.02***
 <.0001(2.4610)
age_gr<.0001-1282.29***
 <.0001(9.3784)
age_gr0.5106210.1890
 0.5106(9.4449)
age_gr0.0015-1615.85***
 0.0015(0.1211)
female*age_gr0.00131127.503***
 0.0013(0.1875)
female*age_gr0.0033992.5148***
 0.0033(7.4810)
female*age_gr0.0353694.6752**
 0.0353(9.9497)
female*age_gr0.0659623.0732*
 0.0659(8.8363)
female*age_gr0.1377504.2382
 0.1377(9.6422)
female*age_gr<.00011491.246***
 <.0001(3.3474)
female*age_gr<.00011339.971***
 <.0001(8.7947)
female*age_gr0.00101102.112***
 0.0010(4.9940)
female*age_gr0.0991536.0772*
 0.0991(5.0355)
female*age_gr0.9996-0.1699
 0.9996(4.0705)
female*age_gr0.0296700.1651**
 0.0296(1.9080)
female*age_gr0.0951534.5546*
 0.0951(0.2453)
female*age_gr0.0134788.9965**
 0.0134(9.1323)
female*age_gr0.1294491.9362
 0.1294(4.3554)
female*age_gr0.0600624.4005*
 0.0600(1.9166)
female*age_gr0.00061197.305***
 0.0006(8.4239)
female*age_gr0.0184860.5910**
 0.0184(5.0921)
female*age_gr0.0267-959.616**
 0.0267(2.9871)
female*age_gr0.1352921.4893
 0.1352

(6.853)


Accepted Solutions
Solution
‎03-18-2018 03:15 AM
Frequent Contributor
Posts: 107

Re: Journal quaity regression output table

Posted in reply to PaigeMiller
Thx for your reply. I've actually found some mistakes. i will close this question and reopen another one with new dataset and code. Tx.

View solution in original post


All Replies
Respected Advisor
Posts: 3,040

Re: Journal quaity regression output table

1. Both outputs need to be somehow merged into the same data set and then run PROC REPORT to get both outputs side-by-side.

 

2. Give us a specific example, so we don't have to scroll through this mass of data and find the discrepancy on our own.

--
Paige Miller
Solution
‎03-18-2018 03:15 AM
Frequent Contributor
Posts: 107

Re: Journal quaity regression output table

Posted in reply to PaigeMiller
Thx for your reply. I've actually found some mistakes. i will close this question and reopen another one with new dataset and code. Tx.
☑ This topic is solved.

Need further help from the community? Please ask a new question.

Discussion stats
  • 2 replies
  • 167 views
  • 0 likes
  • 2 in conversation