NPM : 10060119052
KELAS :B
No Xt Yt
1 1.77 55.265
2 2.08 64.36
3 1.94 61.042
4 1.73 56.315
5 1.99 62.234
6 1.65 52.825
7 1.78 55.966
8 2.05 62.363
9 2.47 72.724
10 1.66 51.327
11 2.09 61.871
12 1.53 46.69
13 2.26 64.964
14 2.17 63.263
15 1.7 49.881
16 2.46 69.09
17 1.87 53.418
Prosedur Hidert Lu
Coefficientsa
Unstandardized Standardized
Coefficients Coefficients
Model B Std. Error Beta t Sig.
1 (Constant) 11.677 3.631 3.216 .006
Xt 24.250 1.841 .959 13.169 .000
a. Dependent Variable: Yt
Diperoleh model regresi yaitu : Yt = b0 + b1 Xt
Yt = 11.677 + 24.250 Xt
Model Summaryb
Adjusted R Std. Error of Durbin-
Model R R Square Square the Estimate Watson
a
1 .959 .920 .915 2.060532 .264
a. Predictors: (Constant), Xt
b. Dependent Variable: Yt
Hipotesis
H1 : ρ ≠ 0 ; Terdapat autokorelasi
Taraf arti : α = 5%
Statistik uji
Kriteria uji
Kesimpulan
Karena 1.1330 > 0.264 < 2.6188 maka H0 ditolak yang artinya terdapat autokorelasi.
𝜌̂ = 1 – (DW/2)
𝜌̂ = 1 – (0.264/2)
𝜌̂ = 0.868
Akan dicoba beberapa nilai ρ, yaitu ρ = 0.75, 0.80, 0.85, 0.90, dan 0.95.
3. Buat Model regresi dengan menggunakan nilai diseputaran 𝜌̂ , hitung MSE nya, pilih
Untuk ρ = 0.75
ANOVAa
Sum of Mean
Model Squares df Square F Sig.
1 Regression 1787.451 1 1787.451 2335.735 .000b
Residual 10.714 14 .765
Total 1798.165 15
a. Dependent Variable: Yt1
b. Predictors: (Constant), Xt1
Untuk ρ = 0.80
ANOVAa
Sum of Mean
Model Squares df Square F Sig.
1 Regression 1887.184 1 1887.184 2874.455 .000b
Residual 9.192 14 .657
Total 1896.375 15
a. Dependent Variable: Yt2
b. Predictors: (Constant), Xt2
Untuk ρ = 0.85
ANOVAa
Sum of Mean
Model Squares df Square F Sig.
1 Regression 1990.476 1 1990.476 3509.036 .000b
Residual 7.941 14 .567
Total 1998.417 15
a. Dependent Variable: Yt3
b. Predictors: (Constant), Xt3
Diperoleh nilai Means Square Residual (MSE) sebesar 0.567
Untuk ρ = 0.90
ANOVAa
Sum of Mean
Model Squares df Square F Sig.
1 Regression 2097.328 1 2097.328 4216.442 .000b
Residual 6.964 14 .497
Total 2104.292 15
a. Dependent Variable: Yt4
b. Predictors: (Constant), Xt4
Untuk ρ = 0.95
ANOVAa
Sum of Mean
Model Squares df Square F Sig.
1 Regression 2207.741 1 2207.741 4938.293 .000b
Residual 6.259 14 .447
Total 2213.999 15
a. Dependent Variable: Yt5
b. Predictors: (Constant), Xt5
Diperoleh nilai Means Square Residual (MSE) sebesar 0.447 yang merupakan nilai
Coefficientsa
Unstandardized Standardized
Coefficients Coefficients
Model B Std. Error Beta t Sig.
1 (Constant) .152 .172 .884 .392
Xt5 25.944 .369 .999 70.273 .000
a. Dependent Variable: Yt5
Sehingga model regresi dengan menggunakan nilai diseputaran 𝜌̂ dan memiliki MSE
Model awal :
Unstandardized Standardized
Coefficients Coefficients
Model B Std. Error Beta t Sig.
1 (Constant) 3.04 3.44 .884 .392
Xt5 25.944 .369 .999 70.273 .000
Yt = 3.04 + 25.944 Xt
Hipotesis
Taraf arti : α = 5%
Statistik uji
P-value = 0.392
Kriteria uji
Karena 0.392 > 0.05 maka H0 diterima yang artinya koefisien regresi tidak
berarti
Hipotesis
Taraf arti : α = 5%
Statistik uji
P-value = 0.000
Kriteria uji
Kesimpulan
Karena 0.000 < 0.05 maka H0 ditolak yang artinya koefisien regresi berarti
Coefficientsa
Unstandardized Standardized
Coefficients Coefficients
Model B Std. Error Beta t Sig.
1 (Constant) 11.677 3.631 3.216 .006
Xt 24.250 1.841 .959 13.169 .000
a. Dependent Variable: Yt
Diperoleh model regresi yaitu : Yt = b0 + b1 Xt
Yt = 11.677 + 24.250 Xt
Coefficientsa
Unstandardized Standardized
Coefficients Coefficients
Model B Std. Error Beta t Sig.
1 (Constant) -.278 .161 -1.721 .107
Xt_1 25.939 .347 .999 74.690 .000
a. Dependent Variable: Yt_1
Coefficientsa,b
Unstandardized Standardized
Coefficients Coefficients
Model B Std. Error Beta t Sig.
1 Xt_1 25.931 .369 .998 70.224 .000
a. Dependent Variable: Yt_1
b. Linear Regression through the Origin
Diketahui :
33.2
𝑋̅ = = 1.95
17
1003.598
𝑌̅ = = 59.04
17
Maka diperoleh :
𝑏0 = 𝑌̅ − [𝑏1 𝑋̅] = 59.04 − [25.931 × 1.95] = 8.40
Yt = 8.40 + 25.931 Xt
Hipotesis
Taraf arti : α = 5%
Statistik uji
P-value = 0.000
Kriteria uji
Kesimpulan
Karena 0.000 < 0.05 maka H0 ditolak yang artinya koefisien regresi berarti