Trang chủ / Nợ Xấu

Kiểm Định Hiện Tượng Phương Sai Thay Đổi Breusch-Pagan / Cook-Weisberg Test For Heteroskedasticity



Var sd = sqrt(Var)

NPL

e u

4.035716 2.008909


3.122708 1.767118


0 0

Có thể bạn quan tâm!

Xem toàn bộ 133 trang tài liệu này.

Các yếu tố tác động đến nợ xấu tại các ngân hàng thương mại Việt Nam - Phùng Thùy Dung - 13

Test: Var(u) = 0


chibar2(01) = 0.00 Prob > chibar2 = 1.0000


Kiểm định FEM với REM


---- Coefficients ----



(b)

(B)

(b-B)

sqrt(diag(V_b-V_B))


fe

re

Difference

S.E.

Nplt1

.0640367

.1755874

-.1115507

.0165025

llp

3.7199140

2.1245520

1.5953630

.3760353

lev

.0039862

.0015412

.0024450

.0113639

size

.0014794

-.0058818

.0073612

.0050616

Roat1

-.1965281

-.1814664

-.0150617

.0947685

lg

.0000419

-.0007528

.0007947

.0005325

inf

.0288595

.0049421

.0239174

.0116679

gdp

-.3592396

-.4873099

.1280703

.0231310

b = consistent under Ho and Ha; obtained from xtreg

B = inconsistent under Ha, efficient under Ho; obtained from xtreg Test: Ho: difference in coefficients not systematic


chi2(8) = (b-B)'[(V_b-V_B)^(-1)](b-B)

= 57.51

Prob>chi2 = 0.0000

(V_b-V_B is not positive definite)


Phụ lục 6: Kiểm định hiện tượng phương sai thay đổi Breusch-Pagan / Cook-Weisberg test for heteroskedasticity

Ho: Constant variance

Variables: fitted values of NPL chi2(1) = 85.16

Prob > chi2 = 0.0000


Phụ lục 7: Kiểm định hiện tượng tự tương quan Wooldridge test for autocorrelation in panel data H0: no first-order autocorrelation

F( 1, 24) = 13.299 Prob > F = 0.0013


Phụ lục 8: Kết quả mô hình hồi quy


Mô hình Pooled OLS

asdoc reg NPLt NPLt1 LLP LEV SIZE ROAt1 LG INF GDP USA

(File Myfile.doc already exists, option append was assumed) Source | SS df MS Number of obs = 272


-------------+---------------------------------- F(9, 262) = 9.49

Model | .026892488 9 .002988054 Prob > F = 0.0000

Residual | .082453475 262 .000314708 R-squared = 0.2459

-------------+---------------------------------- Adj R-squared = 0.2200 Total | .109345963 271 .000403491 Root MSE = .01774

------------------------------------------------------------------------------

NPLt | Coef. Std. Err. t P>|t| [95% Conf. Interval]

-------------+----------------------------------------------------------------


NPLt1 |

.1861826

.0561799

3.31

0.001

. 075561

.2968042

LLP |

1.98893

.3795311

5.24

0.000

1.24161

2.736249

LEV |

.0005384

.0187919

0.03

0.977

-.0364639

.0375408

SIZE |

-.007072

.003

-2.36

0.019

-.0129793

-.0011648

ROAt1|

-.115392

.1629087

-0.71

0.479

-.436169

.205385

LG |

-.0001136

.0010989

-0.10

0.918

-.0022774

.0020503

INF |

.0351753

.0229357

1.53

0.126

-.0099865

.080337

GDP |

-.5684979

.190393

-2.99

0.003

-.9433931

-.1936027

USA |

1.58e-06

7.68e-07

2.06

0.041

6.69e-08

3.09e-06

_cons |

.0615492

.0225281

2.73

0.007

.01719

.1059084

Mô hình FEM

xtreg NPLt NPLt1 LLP LEV SIZE ROAt1 LG INF GDP USA, fe

Fixed-effects (within) regression Number of obs = 272

Group variable: id Number of groups = 25

R-sq: Obs per group:

within = 0.2595 min = 9


between = 0.2110

avg =

10.9

overall = 0.2302

max =

11


F(9,238) = 9.27

corr(u_i, Xb) = -0.3209 Prob > F = 0.0000


------------------------------------------------------------------------------

NPLt | Coef. Std. Err. t P>|t| [95% Conf. Interval]

-------------+----------------------------------------------------------------


NPLt1| .1076723

.0590218

1.82

0.069

-.0085995

.2239442

LLP | 3.018031

.5079648

5.94

0.000

2.017349

4.018712

LEV | .0016099

.0222

0.07

0.942

-.0421238

.0453435

SIZE | -.0076388

.0093187

-0.82

0.413

-.0259965

.0107188

ROAt1 |-.1265315

.1916084

-0.66

0.510

-.5039965

.2509335

LG | -.0001035

.0011928

-0.09

0.931

-.0024533

.0022462

INF | .0341123

.0233107

1.46

0.145

-.0118092

.0800339

GDP | -.4963271

.1954998

-2.54

0.012

-.881458

-.1111962

USA | 1.35e-06

1.31e-06

1.04

0.301

-1.22e-06

3.93e-06

_cons | .0602793

.0480466

1.25

0.211

-.0343716

.1549303

-------------+----------------------------------------------------------------

sigma_u | .00649269

sigma_e | .0176622

rho | .11904551 (fraction of variance due to u_i)

------------------------------------------------------------------------------

F test that all u_i=0: F(24, 238) = 1.10 Prob > F = 0.3485

Mô hình REM


xtreg NPLt NPLt1 LLP LEV SIZE ROAt1 LG INF GDP USA, re

Random-effects GLS regression Number of obs = 272

Group variable: id Number of groups = 25



R-sq:

Obs per group:


within = 0.2452

min =

9

between = 0.3261

avg =

10.9

overall = 0.2459

max =

11


Wald chi2(9) = 85.45

corr(u_i, X) = 0 (assumed) Prob > chi2 = 0.0000

------------------------------------------------------------------------------

NPLt | Coef. Std. Err. z P>|z| [95% Conf. Interval]

-------------+----------------------------------------------------------------


lNPL |

.1861826

.0561799

3.31

0.001

.076072

.2962932

LLP |

1.98893

.3795311

5.24

0.000

1.245062

2.732797

LEV |

.0005384

.0187919

0.03

0.977

-.036293

.0373698

SIZE | -.007072 .003

-2.36

0.018

-.012952

-.0011921

lROA | -.115392 .1629087

-0.71

0.479

-.4346872

.2039032

LG | -.0001136 .0010989

-0.10

0.918

-.0022674

.0020403

INF | .0351753 .0229357

1.53

0.125

-.0097778

.0801284

GDP | -.5684979 .190393 -2.99 0.003 -.9416614 -.1953344 USA | 1.58e-06 7.68e-07 2.06 0.040 7.39e-08 3.08e-06

_cons | .0615492 .0225281 2.73 0.006 .0173949 .1057035


-------------+----------------------------------------------------------------

sigma_u | 0

sigma_e | .0176622

rho | 0 (fraction of variance due to u_i)

----------------------------------------------------------------------------



Phụ lục 9: Kết quả hồi quy mô hình GLS


xtabond2 NPLt NPLt1 LLP LEV SIZE ROAt1 LG INF GDP USA,gmm( L.NPLt

GDP, lag(1 1)) iv( LLP LEV SIZE INF USA) twostep


Favoring space over speed. To switch, type or click on mata: mata set matafavor speed, perm.

Warning: Number of instruments may be large relative to number of observations. Warning: Two-step estimated covariance matrix of moments is singular.

Using a generalized inverse to calculate optimal weighting matrix for two-step estimation.

Difference-in-Sargan/Hansen statistics may be negative.


Dynamic panel-data estimation, two-step system GMM


------------------------------------------------------------------------------


Group variable: id Number of obs = 272

Time variable : year Number of groups = 25

Number of instruments = 35 Obs per group: min = 9

Wald chi2(9) = 2851.34 avg = 10.88

Prob > chi2 = 0.000 max = 11


------------------------------------------------------------------------------


NPLt | Coef. Std. Err. z P>|z| [95% Conf. Interval]


-------------+----------------------------------------------------------------


lNPL | .1841593 .0146088

12.61

0.000

.1555266

.2127919

LLP | 2.204471 .1888969

11.67

0.000

1.83424

2.574702

LEV | -.0084897 .0040082

-2.12

0.034

-.0163456

-.0006337

SIZE | -.0076483 .0013626

-5.61

0.000

-.0103189

-.0049777

lROA | .229951 .100055

2.30

0.022

.0338468

.4260551

LG | -.0007796 .000464

-1.68

0.093

-.001689

.0001298

INF | .0195488 .0050399

3.88

0.000

.0096708

.0294268

GDP | -.3978581 .0424801

-9.37

0.000

-.4811175

-.3145986

USA | 1.46e-06 2.35e-07

6.20

0.000

9.95e-07

1.92e-06

_cons | .0623395 .0094716

6.58

0.000

.0437755

.0809035


------------------------------------------------------------------------------


Warning: Uncorrected two-step standard errors are unreliable.


Instruments for first differences equation Standard

D.(LLP LEV SIZE INF USA)


GMM-type (missing=0, separate instruments for each period unless collapsed) L.(L.NPLt GDP)

Instruments for levels equation Standard

LLP LEV SIZE INF USA

Xem toàn bộ nội dung bài viết ᛨ

..... Xem trang tiếp theo?
⇦ Trang trước - Trang tiếp theo ⇨

Ngày đăng: 10/12/2023