[Farid Osmanov]

Thank you!
Carlo Lazzaro is there a suitable command in Stata to run Ramsey's RESET test after using xtreg, fe/re cluster() ?

[Carlo Lazzaro]

Farid:
see: https://www.statalist.org/forums/for...ition-test-vat, #2

[Farid Osmanov]

Dear Carlo Lazzaro


In order to get the regression results in a table in Word document, i have used a "prefix" asdoc*

And i got the following result:

sqrtEPS	Coef.		St.Err.	t-value		p-value	[95% Conf		Interval]		Sig
sqrtSTD	-.717		.264	-2.71		.008	-1.24		-.194		***
sqrtLTD	-.709		.268	-2.64		.009	-1.24		-.178		***
SIZE	.395		.08	4.96		0	.238		.553		***
GROWTH	.071		.116	0.62		.539	-.158		.301
Constant	-1.49		.644	-2.31		.022	-2.765		-.215		**
Mean dependent var		1.534			SD dependent var			0.650
R-squared		0.131			Number of obs			711
F-test		7.057			Prob > F			0.000
Akaike crit. (AIC)		355.230			Bayesian crit. (BIC)			373.497
*** p<.01, ** p<.05, * p<.1

this is the result of the command

. asdoc xtreg sqrtEPS sqrtSTD sqrtLTD SIZE GROWTH, fe cluster( companyID)

my question:

1)What does AIC and BIC results mean/imply?

2) SD dependent var means standard deviation of the dependent variable?

3) are the R-squared and F-stat result correct? I am asking because FE doesnt return the correct R-squared and F-stat value am i right? if yes, which commands are responsible for getting the correct values?

Many thanks!

[Carlo Lazzaro]

Farid:
1) see -help BIC note- and related entries in Stata .pdf manual;
2) yes.
3) I'm not familiar with the community-contributed module -asdoc-. However, please note that the R-sq to be considered for -xtreg,fe- is the within one.

[Farid Osmanov]

Carlo Lazzaro Thanks!

However returning to my question regarding F-stat and corresponding p-value: are they correctly depicted after the command xtreg , fe cluster( companyID) ? I want to describe the goodness-of-fit with those values

[Carlo Lazzaro]

Farid:
yes, they are.
However, please note that a statistically significant F-statistic does not prove the goodness of it of your model, but that the predictors are jointly statistically significant (ie, more informative) vs the simple mean of the regressand:

. use "https://www.stata-press.com/data/r16/nlswork.dta"
(National Longitudinal Survey.  Young Women 14-26 years of age in 1968)

. xtreg ln_wage, fe

Fixed-effects (within) regression               Number of obs     =     28,534
Group variable: idcode                          Number of groups  =      4,711

R-sq:                                           Obs per group:
     within  = 0.0000                                         min =          1
     between = 0.0050                                         avg =        6.1
     overall =      .                                         max =         15

                                                F(0,23823)        =       0.00
corr(u_i, Xb)  =      .                         Prob > F          =          .

------------------------------------------------------------------------------
     ln_wage |      Coef.   Std. Err.      t    P>|t|     [95% Conf. Interval]
-------------+----------------------------------------------------------------
       _cons |   1.674907   .0018961   883.35   0.000     1.671191    1.678624
-------------+----------------------------------------------------------------
     sigma_u |  .42456905
     sigma_e |  .32028665
         rho |  .63731204   (fraction of variance due to u_i)
------------------------------------------------------------------------------
F test that all u_i=0: F(4710, 23823) = 8.44                 Prob > F = 0.0000

. xtreg ln_wage c.age##c.age, fe

Fixed-effects (within) regression               Number of obs     =     28,510
Group variable: idcode                          Number of groups  =      4,710

R-sq:                                           Obs per group:
     within  = 0.1087                                         min =          1
     between = 0.1006                                         avg =        6.1
     overall = 0.0865                                         max =         15

                                                F(2,23798)        =    1451.88
corr(u_i, Xb)  = 0.0440                         Prob > F          =     0.0000

------------------------------------------------------------------------------
     ln_wage |      Coef.   Std. Err.      t    P>|t|     [95% Conf. Interval]
-------------+----------------------------------------------------------------
         age |   .0539076   .0028078    19.20   0.000     .0484041    .0594112
             |
 c.age#c.age |  -.0005973   .0000465   -12.84   0.000    -.0006885   -.0005061
             |
       _cons |    .639913   .0408906    15.65   0.000     .5597649    .7200611
-------------+----------------------------------------------------------------
     sigma_u |   .4039153
     sigma_e |  .30245467
         rho |  .64073314   (fraction of variance due to u_i)
------------------------------------------------------------------------------
F test that all u_i=0: F(4709, 23798) = 8.74                 Prob > F = 0.0000

.