Dear Statalisters:
Some time ago, Ben Jann, the author of -estout- (downloadable from ssc-) help me to create a column with predicted signs in a regression output. It works perfectly. I display below my command lines.
xi: tobit competence11 age1 conseil2 concent3_0 instit concent3_0_instit size auditor_d i.for_list2 leverage leverage2 roa_adj growth_op2 i.bis_gics , ul
tempname b
matrix `b' = e(b)
matrix `b'[1,1] = +999 //pos. sign for age
matrix `b'[1,2] = -999 //neg. sign for board type
matrix `b'[1,3] = 998 //? sign for ownership concentration
matrix `b'[1,4] = +999 //pos. sign for institutional ownership
matrix `b'[1,5] = -999 //neg. for ownership concentration * institutional ownership
matrix `b'[1,6] = +999 //pos. sign for size
matrix `b'[1,7] = +999 //pos. sign for for auditor type
matrix `b'[1,8] = +999 //pos. sign for foreign listing
matrix `b'[1,9] = +999 //pos. sign for foreign listing
matrix `b'[1,10] = 998 //? for leverage
matrix `b'[1,11] = 998 //? for leverage2
matrix `b'[1,12] = 998 //? for roa
matrix `b'[1,13] = -999 //neg. sign for growth opportunities
matrix `b'[1,14] = .z //no sign
matrix `b'[1,15] = .z //no sign
matrix `b'[1,16] = .z //no sign
matrix `b'[1,17] = .z //no sign
matrix `b'[1,18] = .z //no sign
matrix `b'[1,19] = 998 //? for _cons
eret2 matrix signs = `b'
local e_scalars: e(scalars) //get the names of the scalars in e()
foreach e of local e_scalars {
eret2 local `e' , replace //replace the scalars by empty macros
//or: eret2 scalar `e' = .z , replace //set the scalars to missing
}
estimates store pred
xi: tobit competence11 age1 conseil2 concent3_0 instit concent3_0_instit size auditor_d i.for_list2 leverage leverage2 roa_adj growth_op2 i.bis_gics , ul
label var _Ifor_list2_1 "Foreign listing NYSE"
label var _Ifor_list2_2 "Foreign listing NASDAQ"
*label var _Ibis_gics_20 "Industrial"
label var _Ibis_gics_25 "Consumer discretionary"
label var _Ibis_gics_30 "Consumer staples"
label var _Ibis_gics_35 "Health care"
label var _Ibis_gics_50 "High tech"
label var _Ibis_gics_55 "Energy/Utilities"
estimates store tobit1, title(Financial expertise - Basic measure)
estadd nagelkerke: tobit1
estout pred tobit1 using table6_tobit, replace substitute(-999.000 - 999.000 + 998.000 ?) cells ("signs(pat (1 0)) b(fmt(%9.3f) label(coef.) pat(0)) p(fmt(%9.3f) pattern(0))") stats (chi2 p r2_p nagelkerke N, fmt(%9.3f %9.3f %9.3f %9.3f %9.0f) labels("Chi square" "p(chi2)" "Pseudo R-square" "Nagelkerke" "Number of observations")) label drop(sigma:) varlabels(_cons Constant, elist(growth_op2 "`=char(13)'Control variables"))
I would like to add a column, before the predicted signs, with the following text which corresponds to the hypotheses' number: H1 on line 1, H2 on line 2, ..., H13 on line 13. I don't have hypotheses for the lines between 14 and 19 and the column should remain empty.
It is possible with estout?
To be honest, I tried something by duplicating the command lines corresponding to the predicted signs and adapting them to my problem. But it does not work. My programming level is surely too low. And I also realize that adding a text, H1, for example, is not the same as adding a sign (+ or -).
Best regards
Herv� Stolowy
***********************************************************
Professeur/Professor
HEC Paris
D�partement Comptabilit� Contr�le de gestion / Dept of Accounting and Management Control
1, rue de la Liberation
78351 - Jouy-en-Josas
France
Tel: +33 1 39 67 94 42 - Fax: +33 1 39 67 70 86
mail: stolowy at hec dot fr
web: http://studies.hec.fr/web/stolowy
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
