Scribd Logo
Upload

Welcome to Scribd!

  • 18 views

    Auto Correlation

    Uploaded by

    Renild Muriansyah Putra Tj
    The document describes a regression model with the dependent variable Y and independent variables X2 through X6. Estimating the model shows autocorrelation based on the Durbin-Watson statistic being below 2. Additional tests, including the Breusch-Godfrey test and estimating the model with Newey-West standard errors, confirm the presence of autocorrelation. The document demonstrates different methods for detecting and addressing autocorrelation in a regression model.

    Copyright:

    Attribution Non-Commercial (BY-NC)
    Download as DOC, PDF, TXT or read online from Scribd

    Auto Correlation

    Uploaded by

    Renild Muriansyah Putra Tj
    18 views2 pages
    The document describes a regression model with the dependent variable Y and independent variables X2 through X6. Estimating the model shows autocorrelation based on the Durbin-Watson statistic being below 2. Additional tests, including the Breusch-Godfrey test and estimating the model with Newey-West standard errors, confirm the presence of autocorrelation. The document demonstrates different methods for detecting and addressing autocorrelation in a regression model.

    Copyright

    © Attribution Non-Commercial (BY-NC)

    Available Formats

    DOC, PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    The document describes a regression model with the dependent variable Y and independent variables X2 through X6. Estimating the model shows autocorrelation based on the Durbin-Watson statistic being below 2. Additional tests, including the Breusch-Godfrey test and estimating the model with Newey-West standard errors, confirm the presence of autocorrelation. The document demonstrates different methods for detecting and addressing autocorrelation in a regression model.

    Copyright:

    Attribution Non-Commercial (BY-NC)
    Download as DOC, PDF, TXT or read online from Scribd
    Download as doc, pdf, or txt
    18 views2 pages

    Auto Correlation

    Uploaded by

    Renild Muriansyah Putra Tj
    The document describes a regression model with the dependent variable Y and independent variables X2 through X6. Estimating the model shows autocorrelation based on the Durbin-Watson statistic being below 2. Additional tests, including the Breusch-Godfrey test and estimating the model with Newey-West standard errors, confirm the presence of autocorrelation. The document demonstrates different methods for detecting and addressing autocorrelation in a regression model.

    Copyright:

    Attribution Non-Commercial (BY-NC)
    Download as DOC, PDF, TXT or read online from Scribd
    Download as doc, pdf, or txt
    of 2

    ECONOMETRIC: AUTOCORRELATION

    Oleh: Tri Widodo, Ph.D.


    1. Saudara memiliki model regresi

    Yt = 1 + 2 X 2 t + 3X 3 t + 4 X 4 t + 5 X 5 t + 6 X 6 t + u t . Dengan menggunakan data

    autocorrelation.sav estimasilah model tersebut!


    Dependent Variable: Y
    Method: Least Squares
    Sample: 1971 2000
    Included observations: 30
    Variable
    Coefficient
    C
    15.38369
    X2
    0.020752
    X3
    -0.002178
    X4
    0.034338
    X5
    -0.003790
    X6
    0.011774
    R-squared
    0.949200
    Adjusted R-squared
    0.938616
    S.E. of regression
    5.387113
    Sum squared resid
    696.5037
    Log likelihood
    -89.74129
    Durbin-Watson stat
    0.983723

    2.

    Std. Error
    t-Statistic
    14.01730
    1.097479
    0.012865
    1.613110
    0.133207
    -0.016349
    0.013535
    2.537008
    0.004617
    -0.820953
    0.398255
    0.029565
    Mean dependent var
    S.D. dependent var
    Akaike info criterion
    Schwarz criterion
    F-statistic
    Prob(F-statistic)

    Prob.
    0.2833
    0.1198
    0.9871
    0.0181
    0.4198
    0.9767
    45.63967
    21.74352
    6.382753
    6.662992
    89.68776
    0.000000

    Dengan menggunakan Durbin-Watson d, ujilah apakah terdapat autocorrelation!


    3. Dengan menggunakan BG test (LM), ujilah apakah terdapat autocorrelation!
    Breusch-Godfrey Serial Correlation LM Test:
    F-statistic
    5.518993 Probability
    Obs*R-squared
    10.02299 Probability

    0.011416
    0.006661

    Test Equation:
    Dependent Variable: RESID
    Method: Least Squares
    Presample missing value lagged residuals set to zero.
    Variable
    Coefficient
    Std. Error
    t-Statistic
    C
    0.896038
    11.96251
    0.074904
    X2
    0.001118
    0.010970
    0.101961
    X3
    -0.068564
    0.115852
    -0.591820
    X4
    0.010620
    0.012010
    0.884223
    X5
    0.001042
    0.003980
    0.261903
    X6
    -0.068785
    0.340994
    -0.201719
    RESID(-1)
    0.698812
    0.211001
    3.311894
    RESID(-2)
    -0.286898
    0.214899
    -1.335038
    R-squared
    0.334100 Mean dependent var
    Adjusted R-squared
    0.122223 S.D. dependent var
    S.E. of regression
    4.591504 Akaike info criterion
    Sum squared resid
    463.8020 Schwarz criterion
    Log likelihood
    -83.64206 F-statistic
    Durbin-Watson stat
    2.058460 Prob(F-statistic)

    Prob.
    0.9410
    0.9197
    0.5600
    0.3861
    0.7958
    0.8420
    0.0032
    0.1955
    -3.35E-15
    4.900752
    6.109471
    6.483123
    1.576855
    0.194514

    4. Dengan menggunakan HAC (Heteroscedastitcity and autocorrelation-consistent0


    standard errors / Newey-West standard errors, estimasilah model tersebut!
    Dependent Variable: Y

    Method: Least Squares


    Sample: 1971 2000
    Included observations: 30
    Newey-West HAC Standard Errors & Covariance (lag truncation=3)
    Variable
    Coefficient
    Std. Error
    t-Statistic
    C
    15.38369
    21.19480
    0.725824
    X2
    0.020752
    0.016461
    1.260662
    X3
    -0.002178
    0.164053
    -0.013275
    X4
    0.034338
    0.009462
    3.629040
    X5
    -0.003790
    0.006268
    -0.604687
    X6
    0.011774
    0.548649
    0.021460
    R-squared
    0.949200 Mean dependent var
    Adjusted R-squared
    0.938616 S.D. dependent var
    S.E. of regression
    5.387113 Akaike info criterion
    Sum squared resid
    696.5037 Schwarz criterion
    Log likelihood
    -89.74129 F-statistic
    Durbin-Watson stat
    0.983723 Prob(F-statistic)

    ----ooooo----

    Prob.
    0.4750
    0.2195
    0.9895
    0.0013
    0.5511
    0.9831
    45.63967
    21.74352
    6.382753
    6.662992
    89.68776
    0.000000

    You might also like