Scribd Logo
Upload

Welcome to Scribd!

  • 11 views

    Regresi Panel

    Uploaded by

    M. Yusuf Dali
    The document discusses panel regression models. There are three panel regression models that can be estimated: 1) common effect model (ordinary least squares regression), 2) fixed effect model, and 3) random effect model. It explains the steps in panel regression which includes estimating these three models. It provides examples of output from estimating the three models in EViews. It also discusses the test procedures to select the appropriate model, including Chow test and Hausman test. The selected model based on the test results is the common effect model.

    Copyright:

    © All Rights Reserved
    Download as PPTX, PDF, TXT or read online from Scribd

    Regresi Panel

    Uploaded by

    M. Yusuf Dali
    11 views25 pages
    The document discusses panel regression models. There are three panel regression models that can be estimated: 1) common effect model (ordinary least squares regression), 2) fixed effect model, and 3) random effect model. It explains the steps in panel regression which includes estimating these three models. It provides examples of output from estimating the three models in EViews. It also discusses the test procedures to select the appropriate model, including Chow test and Hausman test. The selected model based on the test results is the common effect model.

    Original Description:

    eviews regresi panel

    Original Title

    REGRESI PANEL

    Copyright

    © © All Rights Reserved

    Available Formats

    PPTX, PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    The document discusses panel regression models. There are three panel regression models that can be estimated: 1) common effect model (ordinary least squares regression), 2) fixed effect model, and 3) random effect model. It explains the steps in panel regression which includes estimating these three models. It provides examples of output from estimating the three models in EViews. It also discusses the test procedures to select the appropriate model, including Chow test and Hausman test. The selected model based on the test results is the common effect model.

    Copyright:

    © All Rights Reserved
    Download as PPTX, PDF, TXT or read online from Scribd
    Download as pptx, pdf, or txt
    11 views25 pages

    Regresi Panel

    Uploaded by

    M. Yusuf Dali
    The document discusses panel regression models. There are three panel regression models that can be estimated: 1) common effect model (ordinary least squares regression), 2) fixed effect model, and 3) random effect model. It explains the steps in panel regression which includes estimating these three models. It provides examples of output from estimating the three models in EViews. It also discusses the test procedures to select the appropriate model, including Chow test and Hausman test. The selected model based on the test results is the common effect model.

    Copyright:

    © All Rights Reserved
    Download as PPTX, PDF, TXT or read online from Scribd
    Download as pptx, pdf, or txt
    of 25

    REGRESI PANEL

    STRUKTUR DATA
    GABUNGAN DATA TIME SERIES DAN CROSS SECTION
    TAHAPAN REGRESI PANEL

    MENGESTIMASI 3 MODEL REGRESI PANEL


    1. COMMON EFFECT MODEL (REGRESI OLS)
    2. FIXED EFFECT MODEL
    3. RANDOM EFFECT MODEL
    TAHAPAN REGRESI PANEL

    MENGESTIMASI 3 MODEL REGRESI PANEL


    1. COMMON EFFECT MODEL (REGRESI OLS)
    2. FIXED EFFECT MODEL
    3. RANDOM EFFECT MODEL
    Dependent Variable: FERC
    Dependent Variable: FERC Method: Panel Least Squares
    Method: Least Squares Date: 06/23/23 Time: 17:07
    Date: 06/23/23 Time: 16:54 Sample: 2018 2021
    Sample: 1 164 Periods included: 4
    Included observations: 164 Cross-sections included: 41
    Total panel (balanced) observations: 164
    Variable Coefficient Std. Error t-Statistic Prob.
    Variable Coefficient Std. Error t-Statistic Prob.
    C -70.70941 134.2794 -0.526584 0.5992
    EM 58.52391 83.02564 0.704890 0.4819 C -70.70941 134.2794 -0.526584 0.5992
    KA -1.502657 13.38140 -0.112295 0.9107 EM 58.52391 83.02564 0.704890 0.4819
    CAR 0.084770 0.327943 0.258489 0.7964 KA -1.502657 13.38140 -0.112295 0.9107
    ROE -0.285079 0.342964 -0.831221 0.4071 ROE -0.285079 0.342964 -0.831221 0.4071
    SIZE 4.703005 9.813025 0.479262 0.6324 SIZE 4.703005 9.813025 0.479262 0.6324
    CAR 0.084770 0.327943 0.258489 0.7964
    R-squared 0.006800 Mean dependent var -3.587134
    Adjusted R-squared -0.024630 S.D. dependent var 72.86033 R-squared 0.006800 Mean dependent var -3.587134
    S.E. of regression 73.75216 Akaike info criterion 11.47520 Adjusted R-squared -0.024630 S.D. dependent var 72.86033
    Sum squared resid 859422.1 Schwarz criterion 11.58861 S.E. of regression 73.75216 Akaike info criterion 11.47520
    Log likelihood -934.9661 Hannan-Quinn criter. 11.52124 Sum squared resid 859422.1 Schwarz criterion 11.58861
    F-statistic 0.216353 Durbin-Watson stat 1.950543 Log likelihood -934.9661 Hannan-Quinn criter. 11.52124
    Prob(F-statistic) 0.955137 F-statistic 0.216353 Durbin-Watson stat 1.337375
    Prob(F-statistic) 0.955137
    Dependent Variable: FERC
    Method: Panel Least Squares
    Date: 06/23/23 Time: 17:10
    Sample: 2018 2021
    Periods included: 4
    Cross-sections included: 41
    Total panel (balanced) observations: 164

    Variable Coefficient Std. Error t-Statistic Prob.

    C 786.3030 868.0913 0.905784 0.3669


    EM 17.94941 166.2360 0.107975 0.9142
    KA 19.27229 31.51794 0.611470 0.5421
    ROE -0.206015 0.462427 -0.445508 0.6568
    SIZE -59.62766 64.62606 -0.922656 0.3581
    CAR 0.362425 0.514566 0.704331 0.4826

    Effects Specification

    Cross-section fixed (dummy variables)

    R-squared 0.281904 Mean dependent var -3.587134


    Adjusted R-squared 0.008054 S.D. dependent var 72.86033
    S.E. of regression 72.56632 Akaike info criterion 11.63867
    Sum squared resid 621372.7 Schwarz criterion 12.50815
    Log likelihood -908.3712 Hannan-Quinn criter. 11.99165
    F-statistic 1.029411 Durbin-Watson stat 1.838430
    Prob(F-statistic) 0.438841
    Dependent Variable: FERC
    Method: Panel EGLS (Cross-section random effects)
    Date: 06/23/23 Time: 17:12
    Sample: 2018 2021
    Periods included: 4
    Cross-sections included: 41
    Total panel (balanced) observations: 164
    Swamy and Arora estimator of component variances

    Variable Coefficient Std. Error t-Statistic Prob.

    C -63.96676 143.3947 -0.446089 0.6561


    EM 55.90362 88.30594 0.633068 0.5276
    KA -0.652844 14.39251 -0.045360 0.9639
    ROE -0.286565 0.353420 -0.810834 0.4187
    SIZE 4.187120 10.51029 0.398383 0.6909
    CAR 0.082117 0.336974 0.243690 0.8078

    Effects Specification
    S.D. Rho

    Cross-section random 18.18656 0.0591


    Idiosyncratic random 72.56632 0.9409

    Weighted Statistics

    R-squared 0.006366 Mean dependent var -3.206839


    Adjusted R-squared -0.025078 S.D. dependent var 70.84769
    S.E. of regression 71.73056 Sum squared resid 812953.1
    F-statistic 0.202447 Durbin-Watson stat 1.412984
    Prob(F-statistic) 0.961056

    Unweighted Statistics

    R-squared 0.006765 Mean dependent var -3.587134


    Sum squared resid 859452.1 Durbin-Watson stat 1.336537
    Pemilihan model
    • PENGUJIAN CHOW
    • Digunakan untuk memilih model yang tepat adalah CEM of FEM
    Hipotesis
    Ho : CEM
    Ha : FEM
    Keputusan
    Jika p-Value dari cross section chisquare ≤ 0,05 maka Ho ditolak
    Jika p-Value dari cross section chisquare > 0,05 maka Ho diterima
    Posisi eviews : dalam bentuk FIXED
    PENGUJIAN CHOW
    Redundant Fixed Effects Tests
    Equation: MODEL_PANEL
    Test cross-section fixed effects

    Effects Test Statistic d.f. Prob.

    Cross-section F 1.130152 (40,118) 0.3021


    Cross-section Chi-square 53.189983 40 0.0792 HASIL OLAHAN DIPEROLEH NILAI CROSS
    SECTION CHISQUARE SEBESAR 0,0792 >
    Cross-section fixed effects test equation:
    Dependent Variable: FERC
    0,05 MAKA HO DITEIRMA
    Method: Panel Least Squares
    Date: 06/23/23 Time: 17:21
    Sample: 2018 2021 KESIMPUJLAN :
    Periods included: 4
    Cross-sections included: 41
    MODEL YANG TERPILIH CEM
    Total panel (balanced) observations: 164

    Variable Coefficient Std. Error t-Statistic Prob.

    C -70.70941 134.2794 -0.526584 0.5992


    EM 58.52391 83.02564 0.704890 0.4819
    KA -1.502657 13.38140 -0.112295 0.9107
    ROE -0.285079 0.342964 -0.831221 0.4071
    SIZE 4.703005 9.813025 0.479262 0.6324
    CAR 0.084770 0.327943 0.258489 0.7964

    R-squared 0.006800 Mean dependent var -3.587134


    Adjusted R-squared -0.024630 S.D. dependent var 72.86033
    S.E. of regression 73.75216 Akaike info criterion 11.47520
    Sum squared resid 859422.1 Schwarz criterion 11.58861
    Log likelihood -934.9661 Hannan-Quinn criter. 11.52124
    F-statistic 0.216353 Durbin-Watson stat 1.337375
    PENGUJIAN HAUSMAN
    • JIKA HASIL CHOW TEST TERPILIH FEM (FIXED) MAKA DILAKUKAN
    PENGUJIAN HAUSMAN ( FEM VS REM)
    • Ho : REM
    • Ha : FEM
    • Keputusan
    • Jika p-value cross secton random ≤ 0,05 maka Ho ditolak
    • Jika p-value cross secton random > 0,05 maka Ho diterima
    PENGUJIAN HAUSMAN  (POSISI EVIEWS :
    RANDOM)
    Correlated Random Effects - Hausman Test
    Equation: MODEL_PANEL
    Test cross-section random effects

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

    Cross-section random 1.381526 5 0.9263

    Cross-section random effects test comparisons:

    Variable Fixed Random Var(Diff.) Prob.

    EM 17.949409 55.90362419836.4845... 0.7876


    KA 19.272287 -0.652844 786.236505 0.4773
    ROE
    SIZE
    -0.206015
    -59.62765...
    -0.286565 0.088933
    4.1871204066.06184...
    0.7871
    0.3169
    HASIL OLAHAN DIPEROLEH NILAI CROSS
    SECTION RANDOM SEBESAR 0,9263 > 0,05
    CAR 0.362425 0.082117 0.151227 0.4710

    Cross-section random effects test equation:


    Dependent Variable: FERC
    Method: Panel Least Squares
    MAKA HO DITERIMA
    Date: 06/23/23 Time: 17:49
    Sample: 2018 2021
    Periods included: 4
    Cross-sections included: 41
    Total panel (balanced) observations: 164 KESIMPUJLAN : MODEL TERPILIH
    Variable Coefficient Std. Error t-Statistic Prob.
    REM
    C 786.3030 868.0913 0.905784 0.3669
    EM 17.94941 166.2360 0.107975 0.9142
    KA 19.27229 31.51794 0.611470 0.5421
    ROE -0.206015 0.462427 -0.445508 0.6568
    SIZE -59.62766 64.62606 -0.922656 0.3581
    CAR 0.362425 0.514566 0.704331 0.4826

    Effects Specification

    Cross-section fixed (dummy variables)

    R-squared 0.281904 Mean dependent var -3.587134


    Adjusted R-squared 0.008054 S.D. dependent var 72.86033
    S.E. of regression 72.56632 Akaike info criterion 11.63867
    Sum squared resid 621372.7 Schwarz criterion 12.50815
    Log likelihood -908.3712 Hannan-Quinn criter. 11.99165
    F-statistic 1.029411 Durbin-Watson stat 1.838430
    Prob(F-statistic) 0.438841
    PENGUJIAN LM
    • JIKA HASIL CHOW TEST TERPILIH COMMON MAKA DILAKUKAN
    PENGUJIAN LM ( CEM VS REM)
    • Ho : CEM
    • Ha : REM
    • Keputusan
    • Jika p-value Breusch Pagan ≤ 0,05 maka Ho ditolak
    • Jika p-value Breusch Pagan > 0,05 maka Ho diterima
    PENGUIAN LM  POSISI EVIEWS CEM
    PENGUJIAN LM
    Lagrange Multiplier Tests for Random Effects
    Null hypotheses: No effects
    Alternative hypotheses: Two-sided (Breusch-Pagan) and one-sided
    (all others) alternatives

    Test Hypothesis
    Cross-sectio... Time Both

    Breusch-Pagan 0.160151 1.628625 1.788776


    (0.6890) (0.2019) (0.1811)
    HASIL OLAHAN DIPEROLEH NILAI P-VALUE
    Honda 0.400188 -1.276176 -0.619417 DARI BREUSCH PAGAN SEBESAR O,689 >
    (0.3445) -- --
    0,05 MAKA HO DITERIOMA
    King-Wu 0.400188 -1.276176 -1.125150 JADI KESIMPULAN NYA MODEL YANG
    (0.3445) -- --
    COCOK ADALAH CEM
    Standardized Honda 0.810706 -1.061139 -5.425152
    (0.2088) -- --
    Standardized King-Wu 0.810706 -1.061139 -4.043014
    (0.2088) -- --
    Gourierioux, et al.* -- -- 0.160151
    (>= 0.10)

    *Mixed chi-square asymptotic critical values:


    1% 7.289
    5% 4.321
    10% 2.952

    You might also like

    pFad - Phonifier reborn

    Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

    Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


    Alternative Proxies:

    Alternative Proxy

    pFad Proxy

    pFad v3 Proxy

    pFad v4 Proxy