Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Rép. : Re: st: Estout and Stata 11


From   "Herve STOLOWY" <[email protected]>
To   <[email protected]>
Subject   Rép. : Re: st: Estout and Stata 11
Date   Mon, 02 Nov 2009 22:15:32 +0100

Dear Sergiy:

The output was much nicer and simpler:

Predicted signs	Logit on the universe		
		Coefficients	z	p
Sales	+	0.531	30.869	0.000
Return	-	-0.731	-4.702	0.000
Growth opportunities	+	0.159	7.920	0.000
Leverage	-	-1.227	-11.176	0.000
Cross listing	+	1.138	10.862	0.000
Industry effects 		Included		
Year effects 		Included		
Country effects 		Included		
Constant		-0.674	-0.980	0.327
Number of observations		12900		
Chi square		2175.230		
p(chi2)		0		
Pseudo R-square		0.238		
Nagelkerke R-square		0.374		
Pct classified in sample		74.512		

I cannot use the new output.

Best regards

Herve

>>> Sergiy Radyakin <[email protected]> 02/11/09 20:35 >>>
Dear Herve,

If I understand correctly, there should be no dots (missings?). Note
they are all in the places where rownames contain a dot. Otherwise,
what was the corresponding output in Stata 10?

I guess it would be right to blame the new feature of Stata 11 called
"Factor variables" that causes some confusion in the older
user-written commands.
See: [U] 11.4.3 Factor variables
The correction is needed in estout, though.

Best regards, Sergiy Radyakin


On Mon, Nov 2, 2009 at 2:17 PM, Herve STOLOWY <[email protected]> wrote:
> Dear Statalisters:
>
> I have the following syntax created with Stata 10 and using -estout- (downloadable from SSC).
>
> xi:logit english  ln_sales  roa_w  growth_op2_w leverage_w listing i.sic2 i.year i.country if sample_universe==1, robust nolog
>
> estimates store m1, title(Logit on the universe)
>
> estadd estatclass: m1
> estadd nagelkerke: m1
> estadd scalar cons = _b[_cons]: m1
> estadd scalar cons_t = _b[_cons]/_se[_cons]: m1
> estadd scalar cons_p = (1-normal(abs(_b[_cons]/_se[_cons]))) * 2: m1
>
> estout m1 using Table4, replace  cells ("b(fmt(%9.3f) label(Coefficients)) t(fmt(%9.3f) label(z)) p(fmt(%9.3f))") stats (cons cons_t cons_p N chi2 p  r2_p nagelkerke p_corr, layout("@ @ @") fmt(3 3 3 0 3 0 3 3 3) labels("Constant" "Number of observations" "Chi square" "p(chi2)" "Pseudo R-square" "Nagelkerke R-square" "Pct classified in sample")) label labcol2( + - + - +, title(Predicted signs)) indicate("Industry effects = _Isic2*" "Year effects = _Iyear*" "Country effects = _Icountry*" , labels("Included" "Not included" ))  drop(_cons) type
>
> It used to work perfectly.
>
> I have installed Stata 11 today and I now get very strange results (sorry to copy them):
>
> Predicted signs Logit on the universe
>                Coefficients    z       p
> english
> ln_sales        +       0.531   30.813  0.000
> roa_w   -       -0.722  -4.639  0.000
> growth_op2_w    +       0.161   7.981   0.000
> leverage_w      -       -1.222  -11.122 0.000
> English cross listing   +       1.128   10.733  0.000
> o.sic2==12              0.000   .       .
> o.sic2==41              0.000   .       .
> o.sic2==74              0.000   .       .
> o.sic2==81              0.000   .       .
> o.sic2==83              0.000   .       .
> o.sic2==84              0.000   .       .
> o.sic2==85              0.000   .       .
> o.sic2==91              0.000   .       .
> o.sic2==92              0.000   .       .
> o.sic2==94              0.000   .       .
> o.sic2==97              0.000   .       .
> o.country==BRA          0.000   .       .
> o.country==CAN          0.000   .       .
> o.country==CHL          0.000   .       .
> o.country==CIV          0.000   .       .
> o.country==CYM          0.000   .       .
> o.country==CYP          0.000   .       .
> o.country==CZE          0.000   .       .
> o.country==HRV          0.000   .       .
> o.country==ISR          0.000   .       .
> o.country==JOR          0.000   .       .
> o.country==LBR          0.000   .       .
> o.country==LTU          0.000   .       .
> o.country==MHL          0.000   .       .
> o.country==MYS          0.000   .       .
> o.country==PER          0.000   .       .
> o.country==REU          0.000   .       .
> o.country==ROM          0.000   .       .
> o.country==ROU          0.000   .       .
> o.country==SAU          0.000   .       .
> o.country==SRB          0.000   .       .
> o.country==SVK          0.000   .       .
> o.country==THA          0.000   .       .
> o.country==TUN          0.000   .       .
> o.country==TWN          0.000   .       .
> o.country==VGB          0.000   .       .
> o.country==VIR          0.000   .       .
> o.country==VNM          0.000   .       .
> o.country==ZAF          0.000   .       .
> Industry effects                Included
> Year effects            Included
> Country effects                 Included
> Constant                -0.763  -1.071  0.284
> Number of observations          12871
> Chi square              2171.490
> p(chi2)         0
> Pseudo R-square         0.238
> Nagelkerke R-square             0.374
> Pct classified in sample                74.540
> (output written to Table4)
>
> I did not have time to investigate all the changes in Stata 11.
>
> Would you have any idea?
>
> Best regards
>
> Herve Stolowy
>
>
>
>
> *
> *   For searches and help try:
> *   http://www.stata.com/help.cgi?search
> *   http://www.stata.com/support/statalist/faq
> *   http://www.ats.ucla.edu/stat/stata/
>

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/


*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/



© Copyright 1996–2024 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index