Scribd
Upload
56 views6 pages

Hasil Eview

The document contains the results of panel data analysis using fixed effects and random effects models. [1] It shows the coefficients, standard errors, t-statistics and probabilities for each independent variable in the fixed effects and random effects models. [2] It also reports the results of Chow test, Hausman test and residual diagnostic tests for multicollinearity, heteroskedasticity and normality. [3] The Chow test and Hausman test indicate that the fixed effects model is preferred over the random effects model.

Uploaded by

Meismifty Anisa
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
56 views6 pages

Hasil Eview

The document contains the results of panel data analysis using fixed effects and random effects models. [1] It shows the coefficients, standard errors, t-statistics and probabilities for each independent variable in the fixed effects and random effects models. [2] It also reports the results of Chow test, Hausman test and residual diagnostic tests for multicollinearity, heteroskedasticity and normality. [3] The Chow test and Hausman test indicate that the fixed effects model is preferred over the random effects model.

Uploaded by

Meismifty Anisa
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 6

COMMON EFFECT/PLS

Dependent Variable: Y
Method: Panel Least Squares
Date: 05/21/19 Time: 10:51
Sample: 2003 2017
Periods included: 15
Cross-sections included: 5
Total panel (balanced) observations: 75

Variable Coefficient Std. Error t-Statistic Prob.

C -36070.65 2611.522 -13.81212 0.0000


X1 58481.83 4012.167 14.57612 0.0000
X2 5.77E-08 1.76E-08 3.272426 0.0017
X3 -1.02E-08 1.85E-09 -5.507622 0.0000
X4 -1247.216 453.3864 -2.750890 0.0076

R-squared 0.940059 Mean dependent var 3741.867


Adjusted R-squared 0.936633 S.D. dependent var 2745.436
S.E. of regression 691.1013 Akaike info criterion 15.97879
Sum squared resid 33433474 Schwarz criterion 16.13329
Log likelihood -594.2046 Hannan-Quinn criter. 16.04048
F-statistic 274.4517 Durbin-Watson stat 0.495753
Prob(F-statistic) 0.000000

CHOW TEST

Redundant Fixed Effects Tests


Equation: FIXED
Test cross-section fixed effects

Effects Test Statistic d.f. Prob.

Cross-section F 6.818905 (4,66) 0.0001


Cross-section Chi-square 25.942802 4 0.0000

Cross-section fixed effects test equation:


Dependent Variable: Y
Method: Panel Least Squares
Date: 05/21/19 Time: 11:00
Sample: 2003 2017
Periods included: 15
Cross-sections included: 5
Total panel (balanced) observations: 75

Variable Coefficient Std. Error t-Statistic Prob.

C -36070.65 2611.522 -13.81212 0.0000


X1 58481.83 4012.167 14.57612 0.0000
X2 5.77E-08 1.76E-08 3.272426 0.0017
X3 -1.02E-08 1.85E-09 -5.507622 0.0000
X4 -1247.216 453.3864 -2.750890 0.0076

R-squared 0.940059 Mean dependent var 3741.867


Adjusted R-squared 0.936633 S.D. dependent var 2745.436
S.E. of regression 691.1013 Akaike info criterion 15.97879
Sum squared resid 33433474 Schwarz criterion 16.13329
Log likelihood -594.2046 Hannan-Quinn criter. 16.04048
F-statistic 274.4517 Durbin-Watson stat 0.495753
Prob(F-statistic) 0.000000

Berdasarkan gambar di atas, maka dalam tutorial ini nilai prob sebesar 0,000
< 0,05 maka chow test memilih fixed effect.

RANDOM EFFECT

Dependent Variable: Y
Method: Panel EGLS (Cross-section random effects)
Date: 05/21/19 Time: 11:07
Sample: 2003 2017
Periods included: 15
Cross-sections included: 5
Total panel (balanced) observations: 75
Swamy and Arora estimator of component variances

Variable Coefficient Std. Error t-Statistic Prob.

C -36070.65 2262.344 -15.94393 0.0000


X1 58481.83 3475.713 16.82585 0.0000
X2 5.77E-08 1.53E-08 3.777503 0.0003
X3 -1.02E-08 1.60E-09 -6.357688 0.0000
X4 -1247.216 392.7656 -3.175472 0.0022

Effects Specification
S.D. Rho

Cross-section random 0.017003 0.0000


Idiosyncratic random 598.6964 1.0000

Weighted Statistics

R-squared 0.940059 Mean dependent var 3741.867


Adjusted R-squared 0.936633 S.D. dependent var 2745.436
S.E. of regression 691.1013 Sum squared resid 33433474
F-statistic 274.4517 Durbin-Watson stat 0.495753
Prob(F-statistic) 0.000000

Unweighted Statistics

R-squared 0.940059 Mean dependent var 3741.867


Sum squared resid 33433474 Durbin-Watson stat 0.495753

Hausman Test
Correlated Random Effects - Hausman Test
Equation: RANDOM
Test cross-section random effects

Chi-Sq.
Test Summary Statistic Chi-Sq. d.f. Prob.

Cross-section random 27.275620 4 0.0000


Cross-section random effects test comparisons:

Variable Fixed Random Var(Diff.) Prob.

55209.98984 11449921.843
X1 0 58481.833140 369 0.3336
X2 0.000000 0.000000 0.000000 0.0166
X3 -0.000000 -0.000000 0.000000 0.1590
- 254336.09018
X4 2133.371919 -1247.216221 0 0.0789

Cross-section random effects test equation:


Dependent Variable: Y
Method: Panel Least Squares
Date: 05/21/19 Time: 11:12
Sample: 2003 2017
Periods included: 15
Cross-sections included: 5
Total panel (balanced) observations: 75

Variable Coefficient Std. Error t-Statistic Prob.

C -33785.45 3158.103 -10.69802 0.0000


X1 55209.99 4850.825 11.38157 0.0000
X2 3.51E-08 1.80E-08 1.951980 0.0552
X3 -6.87E-09 2.86E-09 -2.406372 0.0189
X4 -2133.372 639.2190 -3.337467 0.0014

Effects Specification

Cross-section fixed (dummy variables)

R-squared 0.957587 Mean dependent var 3741.867


Adjusted R-squared 0.952446 S.D. dependent var 2745.436
S.E. of regression 598.6964 Akaike info criterion 15.73955
Sum squared resid 23656870 Schwarz criterion 16.01765
Log likelihood -581.2332 Hannan-Quinn criter. 15.85059
F-statistic 186.2641 Durbin-Watson stat 0.702502
Prob(F-statistic) 0.000000

Nilai tersebut adalah nilai p value dari uji hausman test, dimana
dalam tutorial ini nilainya sebesar 0,0000. Nilai P Value 0,000 kurang
dari 0,05 maka terima H1 yang berarti metode terbaik yang harus
digunakan adalah fixed effect dari pada random effect

UJI ASUMSI KLASIK:

1. UJI MULTIKOLINEARITAS

X1 X2 X3 X4
X1 1.000000 0.263882 -0.175360 0.867152
X2 0.263882 1.000000 0.503122 0.034829
X3 -0.175360 0.503122 1.000000 -0.494332
X4 0.867152 0.034829 -0.494332 1.000000
 Dari hasil pengujian tersebut terlihat bahwa tidak adanya multikolinearitas dalam model
regresi. Karena koefisien korelasi antara variabel independen < 0,80.

2. UJI HETEROSKEDASTISITAS

Dependent Variable: RESABS


Method: Panel Least Squares
Date: 05/21/19 Time: 11:49
Sample: 2003 2017
Periods included: 15
Cross-sections included: 5
Total panel (balanced) observations: 75

Variable Coefficient Std. Error t-Statistic Prob.

X1 5647.063 2975.036 1.898150 0.0621


X2 5.28E-09 1.10E-08 0.478723 0.6337
X3 -2.59E-09 1.75E-09 -1.477133 0.1444
X4 -233.8250 392.0363 -0.596437 0.5529
C -3122.048 1936.881 -1.611894 0.1118

Effects Specification

Cross-section fixed (dummy variables)

R-squared 0.224615 Mean dependent var 541.0779


Adjusted R-squared 0.130629 S.D. dependent var 393.8046
S.E. of regression 367.1836 Akaike info criterion 14.76177
Sum squared resid 8898371. Schwarz criterion 15.03987
Log likelihood -544.5663 Hannan-Quinn criter. 14.87281
F-statistic 2.389880 Durbin-Watson stat 1.368097
Prob(F-statistic) 0.025058

 Kemudian, yang perlu diperhatikan dari hasil tersebut di atas adalah nilai probablitas pada
masing-masing variabel independen. Apabila nilai prob. < 0,05 maka adanya
heteroskedastisitas. Sebaliknya apabila nilai probabilitas pada setiap variabel
independen> 0,05 maka terbebas dari planggaran asumsi heteroskedastis.

3. UJI NORMALITAS
12
Series: Standardized Residuals
Sample 2003 2017
10
Observations 75

8 Mean 9.00e-15
Median -47.44241
Maximum 1115.469
6
Minimum -706.2288
Std. Dev. 346.7683
4 Skewness 0.673198
Kurtosis 3.514591
2
Jarque-Bera 6.492458
Probability 0.038921
0
-800 -600 -400 -200 0 200 400 600 800 1000 1200

HASIL JARQUE BERA > 0,05, 6,492458>0,05

ARTINYA TERDISTRIBUSI NORMAL

4. UJI AUTOKORELASI

Durbin-Watson stat 0.495753

DL = 1,5151

DU = 1,7390

4- D = 3,504247

D < DL, d< du, TERDAPAT AUTO KORELASI POSITIF

(4-D) > DU, TIDAK TERDAPAT AUTOKORELASI POSITIF

Disembuhkan, sehingga

Breusch-Godfrey Serial Correlation LM Test:

F-statistic 0.630130 Prob. F(4,65) 0.6428


Obs*R-squared 2.762397 Prob. Chi-Square(4) 0.5983

Test Equation:
Dependent Variable: RESID
Method: Least Squares
Date: 05/21/19 Time: 14:42
Sample: 2 75
Included observations: 74
Presample missing value lagged residuals set to zero.

Variable Coefficient Std. Error t-Statistic Prob.

C -0.752878 50.09041 -0.015030 0.9881


D(X1) -1879.486 3146.031 -0.597415 0.5523
D(X2) -1.51E-10 1.06E-08 -0.014279 0.9887
D(X3) 6.57E-10 1.98E-09 0.332081 0.7409
D(X4) 134.9009 328.4125 0.410767 0.6826
RESID(-1) -0.003963 0.125356 -0.031611 0.9749
RESID(-2) 0.186304 0.129209 1.441879 0.1541
RESID(-3) 0.095149 0.130280 0.730338 0.4678
RESID(-4) -0.067406 0.128583 -0.524222 0.6019

R-squared 0.037330 Mean dependent var 1.46E-14


Adjusted R-squared -0.081153 S.D. dependent var 413.3912
S.E. of regression 429.8379 Akaike info criterion 15.07826
Sum squared resid 12009442 Schwarz criterion 15.35848
Log likelihood -548.8956 Hannan-Quinn criter. 15.19004
F-statistic 0.315065 Durbin-Watson stat 1.988774
Prob(F-statistic) 0.957637

Perhatikan nilai Prob Chi Square(2) yang merupakan nilai p value


uji Breusch-Godfrey Serial Correlation LM, yaitu sebesar 0,5983 dimana >
0,05 sehingga terima H0 atau yang berarti tidak ada masalah autokorelasi
serial

You might also like