The impact of non-traditional income on the profitability and risk of banks in Vietnam in the period 2005-2013

Appendix 5

Source	SS	df	MS
Model	.316497733	6	.052749622
Residual	.466940033	268	.001742314
Total	.783437765	274	.002859262

Maybe you are interested!

Comparison of the Income Growth Rate of Employees and Profit Growth of 3 Joint Stock Companies.
Beliefs in Vietnamese Traditional Tet - Impact on tourism - 10
The impact of foreign culture on the business activities of Vietnamese enterprises and the direction of absorbing international cultural values combined with traditional values to enhance competitiveness in the integration period - 13
Impact of water access on income of farming households in Tan Lap commune, Cho Don district, Bac Kan - 13
Theory of Income's Impact on Spending:

Regression model by SDROE variable Pooling OLS model

Number of obs = 275

F( 6, 268) = 30.28

Prob > F = 0.0000

R-squared

=	0.4040
Adj R-squared	=	0.3906
Root MSE	=	.04174

sdroe

Coef.	Std. Err.	t	P>\|t\|	[95% Conf.	Interval]
lnsize	.003758	.0020701	1.82	0.071	-.0003179	.0078338
nim	2.007018	.192024	10.45	0.000	1.628951	2.385086
lta	1.530474	.9986223	1.53	0.127	-.4356684	3.496617
eta	8.543595	2.787823	3.06	0.002	3.054776	14.03241
circle	-.5494936	.3569046	-1.54	0.125	-1.252187	.1531999
GDP	97.00734	22.51403	4.31	0.000	52.68047	141.3342
_cons	.1139788	.046323	2.46	0.015	.0227756	.205182

REM model


Random-effects GLS regression	Number of obs	=	275
Group variable: code	Number of groups	=	40
R-sq: within = 0.3088	Obs per group: min	=	2
between = 0.4794	avg	=	6.9
overall = 0.3973	max	=	9
	Wald chi2(6)	=	139.18
corr(u_i, X) = 0 (assumed)	Prob > chi2	=	0.0000

sdroe

Coef.	Std. Err.		z P>\|z\|		[95% Conf.	Interval]
lnsize	.0013964	.002547		0.55 0.583		-.0035955	.0063884
nim	1.815699	.2028142		8.95 0.000		1.418191	2.213208
lta	2.505335	1.076542		2.33 0.020		.3953509	4.615319
eta	6.86291	2.823835		2.43 0.015		1.328295	12.39753
circle	-.2801694	.4418543		-0.63 0.526		-1.146188	.5858491
GDP	96.92326	22.6625		4.28 0.000		52.50558	141.3409
_cons	.1599452	.0558197		2.87 0.004		.0505406	.2693498
sigma_u	.02122615
sigma_e	.03700614
Rho	.24755422	(fraction	of	variance due	big	u_i)

LM Test

Breusch and Pagan Lagrangian multiplier test for random effects

sdroe[code,t] = Xb + u[code] + e[code,t]

Estimated results:

Var sd = sqrt(Var)

version .0028593 .0534721

e .0013695 .0370061

u .0004505 .0212262

Test: Var(u) = 0

chibar2(01) = 18.85

Prob > chibar2 = 0.0000

FEM model


Fixed-effects (within) regression	Number of obs =	275
Group variable: code	Number of groups =	40
R-sq: within = 0.3153	Obs per group: min =	2
between = 0.4018	avg =	6.9
overall = 0.3717	max =	9
	F(6,229) =	17.58
corr(u_i, Xb) = 0.1075	Prob > F =	0.0000

sdroe

Coef.	Std. Err.		t P>\|t\|		[95% Conf.	Interval]
lnsize	-.0009884	.0033188		-0.30 0.766		-.0075277	.0055509
nim	1.635686	.2256972		7.25 0.000		1.190977	2.080395
lta	3.532307	1.223668		2.89 0.004		1.12122	5.943393
eta	5.713021	3.015948		1.89 0.059		-.2295342	11.65558
circle	.0859825	.565351		0.15 0.879		-1.027972	1.199937
GDP	95.10219	26.27628		3.62 0.000		43,328	146.8764
_cons	.2059991	.0724786		2.84 0.005		.063189	.3488093
sigma_u	.02893278
sigma_e	.03700614
Rho	.37937139	(fraction	of	variance due	big	u_i)

F test that all u_i=0: F(39, 229) = 2.87 Prob > F = 0.0000

Hausman test

Note: the rank of the differenced variance matrix (5) does not equal the number of coefficients being tested (6); be sure this is what you expect, or there may be problems computing the test. Examine the output of your estimators for anything unexpected and possibly consider scaling your variables so that the coefficients are on a similar scale.

Coefficients

(b) fixed	(B) random	(bB) Difference	sqrt(diag(V_b-V_B)) SE
lnsize	-.0009884	.0013964	-.0023848	.0021278
nim	1.635686	1.815699	-.180013	.0990235
lta	3.532307	2.505335	1.026971	.5817379
eta	5.713021	6.86291	-1.149889	1.059196
circle	.0859825	-.2801694	.3661519	.3526847
GDP	95.10219	96.92326	-1.821073	13.29865