BATHIN VII 66 TANJUNG JABUNG TIMUR MUARA SABAK BARAT 106 BUNGO BATHIN III ULU
78 TANJUNG JABUNG BARAT PENGABUAN 118 JAMBI TELANAIPURA 79 TANJUNG JABUNG BARAT SENYERANG 119 JAMBI DANAU TELUK
80 TANJUNG JABUNG BARAT TUNGKAL ILIR 120 JAMBI PELAYANGAN
121 JAMBI JAMBI TIMUR 122 SUNGAI PENUH TANAH KAMPUNG 123 SUNGAI PENUH KUMUN DEBAI 124 SUNGAI PENUH SUNGAI PENUH 125
SUNGAI PENUH HAMPARAN RAWANG 126 SUNGAI PENUH PESISIR BUKIT 127 SUNGAI PENUH BERBAK
128 MUAROJAMBI BAHAR SELATAN 129 MUAROJAMBI TAMAN RAJO 130 MUAROJAMBI SUNGAI BAHAR 131 KERINCI DANAU KERINCI
Lampiran 7. Output Moran dan LISA Propinsi Jambi
> moran.test(Dataset$Y1,list=listwD,alternative="two.sided")
Moran's I test under randomisation
data: Dataset$Y1 weights: listwD
Moran I statistic standard deviate = 8.9522, p-value < 2.2e-16 alternative hypothesis: two.sided
sample estimates:
Moran I statistic Expectation Variance 0.457149783 -0.007692308 0.002696193
> moran.test(Dataset$X3,list=listwD,alternative="two.sided")
Moran's I test under randomisation
data: Dataset$X3 weights: listwD
Moran I statistic standard deviate = 6.4789, p-value = 9.238e-11 alternative hypothesis: two.sided
sample estimates:
Moran I statistic Expectation Variance 0.332192398 -0.007692308 0.002752061
> moran.test(Dataset$Y2,list=listwD,alternative="two.sided")
Moran's I test under randomisation
data: Dataset$Y2 weights: listwD
Moran I statistic standard deviate = 5.9791, p-value = 2.244e-09 alternative hypothesis: two.sided
sample estimates:
Moran I statistic Expectation Variance 0.305071830 -0.007692308 0.002736284
> moran.test(Dataset$X4,list=listwD,alternative="two.sided")
Moran's I test under randomisation
data: Dataset$X4 weights: listwD
Moran I statistic standard deviate = 6.8985, p-value = 5.255e-12 alternative hypothesis: two.sided
sample estimates:
Moran I statistic Expectation Variance 0.356379099 -0.007692308 0.002785229
> moran.test(Dataset$X5,list=listwD,alternative="two.sided")
Moran's I test under randomisation
data: Dataset$X5 weights: listwD
Moran I statistic standard deviate = 2.1643, p-value = 0.03044 alternative hypothesis: two.sided
sample estimates:
Moran I statistic Expectation Variance 0.104669819 -0.007692308 0.002695208
> moran.test(Dataset$X6,list=listwD,alternative="two.sided")
Moran's I test under randomisation
data: Dataset$X6 weights: listwD
Moran I statistic standard deviate = 1.9694, p-value = 0.04891 alternative hypothesis: two.sided
sample estimates:
Moran I statistic Expectation Variance 0.097461688 -0.007692308 0.002851001
> moran.test(Dataset$X7,list=listwD,alternative="two.sided")
Moran's I test under randomisation
data: Dataset$X7 weights: listwD
Moran I statistic standard deviate = 4.6807, p-value = 2.859e-06 alternative hypothesis: two.sided
sample estimates:
Moran I statistic Expectation Variance 0.242297492 -0.007692308 0.002852511
> moran.test(Dataset$X11,list=listwD,alternative="two.sided")
Moran's I test under randomisation
data: Dataset$X11 weights: listwD
Moran I statistic standard deviate = 2.3326, p-value = 0.01967 alternative hypothesis: two.sided
sample estimates:
Moran I statistic Expectation Variance 0.045107937 -0.007692308 0.000512366
> moran.test(Dataset$X13,list=listwD,alternative="two.sided")
Moran's I test under randomisation
data: Dataset$X13 weights: listwD
Moran I statistic standard deviate = 17.81, p-value < 2.2e-16 alternative hypothesis: two.sided
sample estimates:
Moran I statistic Expectation Variance 0.943327258 -0.007692308 0.002851355
Moran's I test under randomisation
data: Dataset$X15 weights: listwD
Moran I statistic standard deviate = 8.4076, p-value < 2.2e-16 alternative hypothesis: two.sided
sample estimates:
Moran I statistic Expectation Variance 0.439901150 -0.007692308 0.002834152
> moran.test(Dataset$X8_proporsi,list=listwD,alternative="two.sided")
Moran's I test under randomisation
data: Dataset$X8_proporsi weights: listwD
Moran I statistic standard deviate = 1.6799, p-value = 0.09298 alternative hypothesis: two.sided
sample estimates:
Moran I statistic Expectation Variance 0.080976420 -0.007692308 0.002786078
> moran.test(Dataset$X9_proporsi,list=listwD,alternative="two.sided")
Moran's I test under randomisation
data: Dataset$X9_proporsi weights: listwD
Moran I statistic standard deviate = 6.0639, p-value = 1.328e-09 alternative hypothesis: two.sided
sample estimates:
Moran I statistic Expectation Variance 0.313358799 -0.007692308 0.002803103
> localmoran.test(Dataset$Y1,list=listwD,alternative="two.sided")
> localmoran(Dataset$Y1,list=listwD,alternative="two.sided") Ii E.Ii Var.Ii Z.Ii Pr(z != 0) 1 16.11184811 -0.05384615 6.609689 6.287874453 3.218420e-10 2 -1.28590815 -0.03076923 3.774784 -0.646019636 5.182666e-01 3 9.06291911 -0.03076923 3.774784 4.680518750 2.861499e-06 4 27.72614699 -0.03846154 4.719871 12.779871834 2.124193e-37 5 15.43059706 -0.04615385 5.664839 6.502584611 7.895159e-11 6 23.29017657 -0.03846154 4.719871 10.738023004 6.747378e-27 7 9.49944604 -0.04615385 5.664839 4.010600888 6.056441e-05 ... 127 -1.89967934 -0.03846154 4.719871 -0.856706659 3.916070e-01 128 0.60525609 -0.01538462 1.884257 0.452137192 6.511702e-01 129 -0.16263458 -0.05384615 6.609689 -0.042314792 9.662478e-01 130 1.28040131 -0.03076923 3.774784 0.674859099 4.997653e-01 131 8.89304291 -0.04615385 5.664839 3.755819526 1.727752e-04 attr(,"call")
localmoran(x = Dataset$Y1, listw = listwD, alternative = "two.sided") attr(,"class")
[1] "localmoran" "matrix"
> localmoran(Dataset$Y2,list=listwD,alternative="two.sided") Ii E.Ii Var.Ii Z.Ii Pr(z != 0) 1 1.179717e-05 -0.05384615 6.708021 0.020794698 9.834094e-01
2 -4.020969e-01 -0.03076923 3.830882 -0.189717718 8.495303e-01 3 3.738862e-01 -0.03076923 3.830882 0.206745463 8.362086e-01 4 -3.259011e-01 -0.03846154 4.790047 -0.131333835 8.955112e-01 5 -1.661324e+00 -0.04615385 5.749093 -0.673625732 5.005493e-01 6 4.384836e-01 -0.03846154 4.790047 0.217920731 8.274909e-01 7 -6.748528e-01 -0.04615385 5.749093 -0.262206253 7.931624e-01 8 1.366941e-01 -0.01538462 1.912198 0.109977023 9.124276e-01 ... 123 2.873734e+00 -0.02307692 2.871599 1.709456901 8.736635e-02 124 4.695021e+00 -0.04615385 5.749093 1.977362353 4.800069e-02 125 2.253403e+00 -0.04615385 5.749093 0.959057224 3.375299e-01 126 1.404353e+00 -0.02307692 2.871599 0.842350798 3.995916e-01 127 5.335904e+00 -0.03846154 4.790047 2.455598419 1.406502e-02 128 1.867315e+00 -0.01538462 1.912198 1.361490749 1.733587e-01 129 9.425229e-01 -0.05384615 6.708021 0.384700742 7.004591e-01 130 5.248995e+00 -0.03076923 3.830882 2.697522827 6.985750e-03 131 -4.133148e-01 -0.04615385 5.749093 -0.153128785 8.782967e-01 attr(,"call")
localmoran(x = Dataset$Y2, listw = listwD, alternative = "two.sided") attr(,"class")
Lampiran 8. Output Moran dan LISA Propinsi Jawa Barat > moran.test(Dataset$Y1,list=listwD,alternative="two.sided")
Moran's I test under randomisation data: Dataset$Y1
weights: listwD
Moran I statistic standard deviate = 20.133, p-value < 2.2e-16 alternative hypothesis: two.sided
sample estimates:
Moran I statistic Expectation Variance 0.4727051994 -0.0016000000 0.0005550175
> moran.test(Dataset$Y2,list=listwD,alternative="two.sided") Moran's I test under randomisation
data: Dataset$Y2 weights: listwD
Moran I statistic standard deviate = 20.269, p-value < 2.2e-16 alternative hypothesis: two.sided
sample estimates:
Moran I statistic Expectation Variance 0.475432178 -0.001600000 0.000553909
> moran.test(Dataset$X1,list=listwD,alternative="two.sided") Moran's I test under randomisation
data: Dataset$X1 weights: listwD
Moran I statistic standard deviate = 28.168, p-value < 2.2e-16 alternative hypothesis: two.sided
sample estimates:
Moran I statistic Expectation Variance 0.6614861936 -0.0016000000 0.0005541688
> moran.test(Dataset$X3,list=listwD,alternative="two.sided") Moran's I test under randomisation
data: Dataset$X3 weights: listwD
Moran I statistic standard deviate = 16.609, p-value < 2.2e-16 alternative hypothesis: two.sided
sample estimates:
Moran I statistic Expectation Variance 0.3886053864 -0.0016000000 0.0005519244
> moran.test(Dataset$X4,list=listwD,alternative="two.sided") Moran's I test under randomisation
data: Dataset$X4 weights: listwD
Moran I statistic standard deviate = 31.233, p-value < 2.2e-16 alternative hypothesis: two.sided
sample estimates:
Moran I statistic Expectation Variance 0.7318917601 -0.0016000000 0.0005515075
Moran's I test under randomisation data: Dataset$X5
weights: listwD
Moran I statistic standard deviate = 6.5873, p-value = 4.48e-11 alternative hypothesis: two.sided
sample estimates:
Moran I statistic Expectation Variance 0.1534827274 -0.0016000000 0.0005542637
> moran.test(Dataset$X6,list=listwD,alternative="two.sided")
Moran's I test under randomisation data: Dataset$X6
weights: listwD
Moran I statistic standard deviate = 4.3948, p-value = 1.109e-05 alternative hypothesis: two.sided
sample estimates:
Moran I statistic Expectation Variance 0.1017656753 -0.0016000000 0.0005531835
> moran.test(Dataset$X7,list=listwD,alternative="two.sided") Moran's I test under randomisation
data: Dataset$X7 weights: listwD
Moran I statistic standard deviate = 7.336, p-value = 2.201e-13 alternative hypothesis: two.sided
sample estimates:
Moran I statistic Expectation Variance 0.1710673807 -0.0016000000 0.0005539941
> moran.test(Dataset$X8_proporsi,list=listwD,alternative="two.sided") Moran's I test under randomisation
data: Dataset$X8_proporsi weights: listwD
Moran I statistic standard deviate = 6.3703, p-value = 1.887e-10 alternative hypothesis: two.sided
sample estimates:
Moran I statistic Expectation Variance 0.1420247673 -0.0016000000 0.0005083235
> moran.test(Dataset$X9_proporsi,list=listwD,alternative="two.sided")
Moran's I test under randomisation data: Dataset$X9_proporsi
weights: listwD
Moran I statistic standard deviate = 9.8463, p-value < 2.2e-16 alternative hypothesis: two.sided
sample estimates:
Moran I statistic Expectation Variance 0.1987858424 -0.0016000000 0.0004141768
> moran.test(Dataset$X11,list=listwD,alternative="two.sided") Moran's I test under randomisation
weights: listwD
Moran I statistic standard deviate = 26.999, p-value < 2.2e-16 alternative hypothesis: two.sided
sample estimates:
Moran I statistic Expectation Variance 0.6330204280 -0.0016000000 0.0005524969
> moran.test(Dataset$X13,list=listwD,alternative="two.sided") Moran's I test under randomisation
data: Dataset$X13 weights: listwD
Moran I statistic standard deviate = 40.48, p-value < 2.2e-16 alternative hypothesis: two.sided
sample estimates:
Moran I statistic Expectation Variance 0.9525021268 -0.0016000000 0.0005555343
> localmoran(Dataset$Y1,list=listwD,alternative="two.sided") Ii E.Ii Var.Ii Z.Ii Pr(z != 0) 1 2.0966771925 -0.0080 4.9906891 0.9421178602 3.461323e-01 2 -0.3462339699 -0.0096 5.9891296 -0.1375549061 8.905922e-01 3 0.0276276121 -0.0064 3.9922435 0.0170303260 9.864124e-01 4 0.4298516341 -0.0128 7.9859951 0.1566381524 8.755300e-01 5 -0.0434393679 -0.0080 4.9906891 -0.0158637446 9.873431e-01 ... 624 0.2050918348 -0.0096 5.9891296 0.0877270799 9.300936e-01 625 -0.2854342776 -0.0032 1.9953370 -0.1998028276 8.416348e-01 626 0.3082931670 -0.0096 5.9891296 0.1298970652 8.966479e-01 attr(,"call")
localmoran(x = Dataset$Y1, listw = listwD, alternative = "two.sided") attr(,"class")
[1] "localmoran" "matrix"
> localmoran(Dataset$Y2,list=listwD,alternative="two.sided") Ii E.Ii Var.Ii Z.Ii Pr(z != 0) 1 20.073723970 -0.0080 4.9807267 8.998179201 2.294920e-19 2 12.225843449 -0.0096 5.9771734 5.004627836 5.597006e-07 3 10.901376534 -0.0064 3.9842749 5.464640373 4.638462e-08 4 4.838053728 -0.0128 7.9700514 1.718255004 8.575011e-02 5 1.205948803 -0.0080 4.9807267 0.543943781 5.864802e-01 6 -2.076292154 -0.0080 4.9807267 -0.926756262 3.540531e-01 7 -0.904790376 -0.0064 3.9842749 -0.450080757 6.526522e-01 8 1.142642272 -0.0112 6.9736150 0.436935632 6.621580e-01 9 2.190492710 -0.0064 3.9842749 1.100611895 2.710656e-01 10 0.381088696 -0.0112 6.9736150 0.148551421 8.819076e-01 11 -0.385441930 -0.0064 3.9842749 -0.189894597 8.493917e-01 12 -0.535408712 -0.0080 4.9807267 -0.236320254 8.131842e-01 ... 623 3.216661112 -0.0048 2.9878179 1.863699245 6.236395e-02 624 2.316513059 -0.0096 5.9771734 0.951443257 3.413794e-01 625 0.441308311 -0.0032 1.9913559 0.314996296 7.527645e-01 626 -10.689084852 -0.0096 5.9771734 -4.368198617 1.252755e-05 attr(,"call")
localmoran(x = Dataset$Y2, listw = listwD, alternative = "two.sided") attr(,"class")
Lampiran 9. Output OLS dan GWR Y1 di Kabupaten/Kota Propinsi Jambi
Output OLS
> LinearModel.1 <- lm(Y1 ~ X3+X4+X5+X6+X7+X8_proporsi+X9_proporsi+X11+X13, + data=Dataset)
> summary(LinearModel.1) Call:
lm(formula = Y1 ~ X3 + X4 + X5 + X6 + X7 + X8_proporsi + X9_proporsi + X11 + X13, data = Dataset) Residuals: 1 2 3 4 5 6 7 0.0571927 -2.6918741 1.0512834 0.8762732 2.2637297 -1.4072695 1.0436348 8 9 10 11 -0.7449573 0.0002295 -1.0073077 0.5590652 Coefficients:
Estimate Std. Error t value Pr(>|t|) (Intercept) 3.625e+01 1.810e+01 2.003 0.2948 X3 2.563e+00 2.419e-01 10.595 0.0599 . X4 1.289e-01 2.309e-02 5.583 0.1128 X5 -3.313e+00 1.067e+00 -3.105 0.1984 X6 6.050e-01 2.853e-01 2.121 0.2805 X7 -9.039e-01 1.740e-01 -5.194 0.1211 X8_proporsi 1.772e+05 4.558e+04 3.887 0.1603 X9_proporsi -4.380e+02 1.146e+02 -3.823 0.1629 X11 -1.557e+02 1.502e+02 -1.037 0.4884 X13 -1.631e+01 4.559e+00 -3.578 0.1735 ---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1 Residual standard error: 4.382 on 1 degrees of freedom
Multiple R-squared: 0.9979, Adjusted R-squared: 0.9787 F-statistic: 52.12 on 9 and 1 DF, p-value: 0.1071
> AIC(LinearModel.1) [1] 59.34309
> dwtest(Y1 ~ X3 + X4 + X5 + X6 + X7 + X8_proporsi + X9_proporsi + X11 + X13, + alternative="two.sided", data=Dataset)
Durbin-Watson test
data: Y1 ~ X3 + X4 + X5 + X6 + X7 + X8_proporsi + X9_proporsi + X11 + X13 DW = 2.6163, p-value < 2.2e-16
alternative hypothesis: true autocorrelation is not 0
> vif(LinearModel.1) X3 X4 X5 X6 X7 X8_proporsi 2.835297 11.022727 26.040721 9.278523 4.322990 6.416150 X9_proporsi X11 X13 19.018265 11.915317 6.492696 > with(Dataset, shapiro.test(residuals.LinearModel.1)) Shapiro-Wilk normality test
data: residuals.LinearModel.1 W = 0.97436, p-value = 0.9268
> bptest(Y1 ~ X3 + X4 + X5 + X6 + X7 + X8_proporsi + X9_proporsi + X11 + X13, + varformula = ~ fitted.values(LinearModel.1), studentize=FALSE, data=Dataset)
Breusch-Pagan test
data: Y1 ~ X3 + X4 + X5 + X6 + X7 + X8_proporsi + X9_proporsi + X11 + X13 BP = 0.64055, df = 1, p-value = 0.4235
Output GWR
> col.bw <- gwr.sel (Y ~ X3 + X4 + X5 + X6 + X7 + X8_proporsi + X9_proporsi + X11 + X13, coords=cbind(Dataset$X_cord,Dataset$Y_cord), data=Dataset, adapt=TRUE, gweight=gwr.Gauss) Adaptive q: 0.381966 CV score: 5054182354 Adaptive q: 0.618034 CV score: 5054182355 Adaptive q: 0.236068 CV score: 5054182355 Adaptive q: 0.4560356 CV score: 5054182354 Adaptive q: 0.4406655 CV score: 5054182354 Adaptive q: 0.4198349 CV score: 5054182355 Adaptive q: 0.4327089 CV score: 5054182355 Adaptive q: 0.4465363 CV score: 5054182354 Adaptive q: 0.4376263 CV score: 5054182354 Adaptive q: 0.442908 CV score: 5054182354 Adaptive q: 0.4395046 CV score: 5054182354 Adaptive q: 0.441522 CV score: 5054182354 Adaptive q: 0.4402221 CV score: 5054182354 Adaptive q: 0.4409927 CV score: 5054182354 Adaptive q: 0.4404961 CV score: 5054182355 Adaptive q: 0.4407905 CV score: 5054182354 Adaptive q: 0.4406008 CV score: 5054182354 Adaptive q: 0.4405601 CV score: 5054182355 Adaptive q: 0.4406008 CV score: 5054182354
>gwr<- gwr(Y ~ X3 + X4 + X5 + X6 + X7 + X8_proporsi + X9_proporsi + X11 + X13,
data=Dataset, adapt=col.bw, coords=cbind(Dataset$X_cord,Dataset$Y_cord),
hatmatrix=TRUE, gweight = gwr.Gauss) >gwr
Call:
gwr(formula = Y ~ X3 + X4 + X5 + X6 + X7 + X8_proporsi + X9_proporsi + X11 + X13, data = Dataset, coords = cbind(Dataset$X_cord,
Dataset$Y_cord), gweight = gwr.Gauss, adapt = col.bw, hatmatrix = TRUE) Kernel function: gwr.Gauss
Adaptive quantile: 0.4406008 (about 4 of 11 data points) Summary of GWR coefficient estimates at data points:
Min. 1st Qu. Median 3rd Qu. Max. X.Intercept. 3.431e+01 3.452e+01 3.537e+01 3.725e+01 3.781e+01 X3 2.480e+00 2.516e+00 2.565e+00 2.602e+00 2.625e+00 X4 1.262e-01 1.268e-01 1.301e-01 1.322e-01 1.340e-01 X5 -3.500e+00 -3.412e+00 -3.379e+00 -3.314e+00 -3.248e+00 X6 6.000e-01 6.134e-01 6.337e-01 6.406e-01 6.645e-01 X7 -9.088e-01 -9.014e-01 -8.906e-01 -8.863e-01 -8.826e-01 X8_proporsi 1.678e+05 1.695e+05 1.725e+05 1.764e+05 1.794e+05 X9_proporsi -4.407e+02 -4.391e+02 -4.360e+02 -4.337e+02 -4.328e+02 X11 -1.997e+02 -1.864e+02 -1.696e+02 -1.371e+02 -1.358e+02 X13 -1.713e+01 -1.696e+01 -1.633e+01 -1.583e+01 -1.566e+01 Global X.Intercept. 36.2465 X3 2.5631 X4 0.1289 X5 -3.3135 X6 0.6050 X7 -0.9039 X8_proporsi 177224.2163 X9_proporsi -437.9583 X11 -155.7337 X13 -16.3122 Number of data points: 11
Effective number of parameters (residual: 2traceS - traceS'S): 10.64481 Effective degrees of freedom (residual: 2traceS - traceS'S): 0.3551945 Sigma (residual: 2traceS - traceS'S): 4.378917
Effective number of parameters (model: traceS): 10.41525 Effective degrees of freedom (model: traceS): 0.5847522 Sigma (model: traceS): 3.412824
Sigma (ML): 0.786871
AICc (GWR p. 61, eq 2.33; p. 96, eq. 4.21): -151.5064 AIC (GWR p. 96, eq. 4.22): 36.35869
Residual sum of squares: 6.810825 Quasi-global R2: 0.9992453
>anova(gwr)
Analysis of Variance Table Df Sum Sq Mean Sq F value
OLS Residuals 10.00000 19.1749 GWR Improvement 0.64481 12.3641 19.175 GWR Residuals 0.35519 6.8108 19.175 1 > LMZ.F1GWR.test(gwr)
Leung et al. (2000) F(1) test data: gwr
F = 1, df1 = 1, df2 = 1, p-value = 0.5 alternative hypothesis: less
sample estimates:
SS OLS residuals SS GWR residuals 19.174915 6.810825
Tabel GWR
No
Estimasi
X.Intercept. X3 X4 X5 X6 X7 X8_proporsi X9_proporsi X11 X13
1 34.396376 2.6073994 0.1324925 -3.41958 0.646051 -0.88384 168655.98 -433.815 -189.51 -15.7156 2 35.135281 2.5996019 0.1300583 -3.41405 0.633705 -0.89626 175795.32 -436.023 -170.634 -16.3281 3 34.307099 2.6253107 0.134027 -3.50044 0.664458 -0.88761 169832.43 -433.397 -199.658 -16.0974 4 37.090441 2.5191689 0.1274419 -3.38156 0.634281 -0.89059 172499.74 -439.134 -151.677 -16.8669 5 37.321994 2.5123532 0.126362 -3.31035 0.610748 -0.90429 178626.88 -440.399 -136.663 -17.081 6 37.168102 2.5191039 0.1269344 -3.27596 0.60005 -0.90885 179438.72 -439.156 -137.446 -16.9398 7 37.808111 2.480269 0.1267429 -3.24753 0.604603 -0.90173 173506.04 -437.263 -135.765 -16.9797 8 35.368081 2.5647057 0.1304834 -3.3175 0.619479 -0.89058 170677.63 -433.572 -169.578 -15.944 9 34.531515 2.5915682 0.1321804 -3.37947 0.63845 -0.88261 167824.42 -432.839 -185.794 -15.6647 10 37.538829 2.5028627 0.1261799 -3.32112 0.616103 -0.90104 177034.32 -440.738 -136.735 -17.1254 11 34.503502 2.6052202 0.1321835 -3.41085 0.642797 -0.88494 169148 -434.155 -187.074 -15.7245 Se_Estimasi
X.Intercept._se X3_se X4_se X5_se X6_se X7_se X8_proporsi_se X9_proporsi_se X11_se X13_se
14.16825 0.191562 0.0182 0.835312 0.224501 0.136438 36127.28 89.2825 119.8702 3.581094 14.12126 0.190562 0.018005 0.834897 0.223334 0.135669 35522.19 89.23684 117.5191 3.550801 14.1755 0.194561 0.018423 0.843886 0.226988 0.136133 35969.08 89.29487 121.8517 3.554724 14.11002 0.191524 0.018018 0.832901 0.22338 0.135935 35695.16 89.22879 116.9866 3.576996 14.11959 0.192545 0.01809 0.831211 0.222259 0.135538 35521.56 89.24436 117.8847 3.600975 14.11297 0.191533 0.018047 0.831721 0.222249 0.135592 35546.66 89.22897 117.8093 3.584311 14.14713 0.199195 0.01806 0.832794 0.222215 0.135549 35622.8 89.22573 117.975 3.588687
14.1113 0.188436 0.018025 0.831214 0.222499 0.135936 35869.47 89.28956 117.4406 3.56236 14.15792 0.189729 0.018164 0.832798 0.223734 0.136551 36252.67 89.31323 119.2676 3.586467 14.13063 0.194201 0.018106 0.831229 0.222382 0.135556 35505.04 89.25038 117.8776 3.606903 14.15999 0.191264 0.018165 0.834667 0.224154 0.136343 36058.36 89.27332 119.4676 3.580202
t hitung
X.Intercept. X3 X4 X5 X6 X7 X8_proporsi X9_proporsi X11 X13
2.427709 13.61124 7.279735 -4.09377 2.877723 -6.47796 4.668383 -4.8589 -1.58096 -4.3885 2.488112 13.64177 7.223325 -4.08919 2.837475 -6.60617 4.948887 -4.88613 -1.45197 -4.59843 2.420169 13.49352 7.275129 -4.148 2.927287 -6.52015 4.721623 -4.85355 -1.63854 -4.52846 2.628659 13.15331 7.073174 -4.05998 2.839477 -6.55157 4.832581 -4.92144 -1.29654 -4.71537 2.643278 13.04813 6.985244 -3.98257 2.747913 -6.67184 5.028689 -4.93475 -1.15929 -4.74343 2.633612 13.15235 7.033656 -3.93878 2.699904 -6.70278 5.047977 -4.92168 -1.16668 -4.7261 2.672493 12.45146 7.017903 -3.89955 2.720803 -6.65242 4.870646 -4.90064 -1.1508 -4.73145 2.506366 13.61051 7.238978 -3.99116 2.784189 -6.55151 4.758298 -4.85579 -1.44394 -4.47567 2.439025 13.65929 7.276956 -4.05796 2.853607 -6.46359 4.629298 -4.84631 -1.55779 -4.36771 2.656558 12.88802 6.969012 -3.99544 2.770478 -6.64695 4.986174 -4.93822 -1.15997 -4.74796 2.436689 13.62109 7.276989 -4.08648 2.86766 -6.49057 4.690951 -4.86321 -1.5659 -4.39207
Lampiran 10. Output OLS dan GWR Y2 di Kecamatan Propinsi Jambi
Output OLS
> LinearModel.1 <- lm(Y1 ~ X3 +X4 +X5 +X6 +X7 +X8_proporsi + X9_proporsi + + X11 +X13 +X15, data=Dataset)
>summary(LinearModel.1) Call:
lm(formula = Y1 ~ X3 + X4 + X5 + X6 + X7 + X8_proporsi + X9_proporsi + X11 + X13 + X15, data = Dataset)
Residuals:
Min 1Q Median 3Q Max -19.190 -8.619 -1.718 4.648 69.027 Coefficients:
Estimate Std. Error t value Pr(>|t|) (Intercept) 1.107e+01 5.403e+00 2.049 0.042667 * X3 -1.397e-01 1.299e-01 -1.076 0.284210 X4 1.711e-03 3.868e-04 4.423 2.15e-05 *** X5 3.052e-02 6.352e-02 0.481 0.631719 X6 -1.224e-01 3.571e-02 -3.427 0.000836 *** X7 -3.484e-02 3.654e-02 -0.953 0.342265 X8_proporsi 5.392e+03 4.994e+03 1.080 0.282489 X9_proporsi 9.191e+00 1.625e+01 0.566 0.572629 X11 2.444e+01 1.267e+01 1.929 0.056070 . X13 9.045e+00 1.894e+00 4.776 5.11e-06 *** X15 -2.557e-03 5.838e-04 -4.380 2.55e-05 *** ---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1 Residual standard error: 12.74 on 120 degrees of freedom Multiple R-squared: 0.4832, Adjusted R-squared: 0.4401 F-statistic: 11.22 on 10 and 120 DF, p-value: 2.349e-13
>AIC(LinearModel.1) [1] 1050.966 > vif(LinearModel.1) X3 X4 X5 X6 X7 X8_proporsi 1.657628 1.157008 1.183135 1.138884 1.160241 1.115253 X9_proporsi X11 X13 X15 1.367194 1.159106 1.269315 1.640377 > library(zoo, pos=14) > library(lmtest, pos=14)
> bptest(Y1 ~ X3 + X4 + X5 + X6 + X7 + X8_proporsi + X9_proporsi + X11 + X13 + + X15, varformula = ~ fitted.values(LinearModel.1), studentize=FALSE, + data=Dataset)
Breusch-Pagan test
data: Y1 ~ X3 + X4 + X5 + X6 + X7 + X8_proporsi + X9_proporsi + X11 + X13 + X15 BP = 52.067, df = 1, p-value = 5.365e-13 > Dataset<- within(Dataset, { + fitted.LinearModel.1 <- fitted(LinearModel.1) + residuals.LinearModel.1 <- residuals(LinearModel.1) + rstudent.LinearModel.1 <- rstudent(LinearModel.1) + hatvalues.LinearModel.1 <- hatvalues(LinearModel.1) + cooks.distance.LinearModel.1 <- cooks.distance(LinearModel.1) + obsNumber <- 1:nrow(Dataset) + })
> with(Dataset, shapiro.test(residuals.LinearModel.1)) Shapiro-Wilk normality test
data: residuals.LinearModel.1 W = 0.88275, p-value = 9.441e-09 > anova(LinearModel.1)
Analysis of Variance Table
Response: Y1
Df Sum Sq Mean Sq F value Pr(>F) X3 1 6.1 6.1 0.0375 0.8468066 X4 1 2983.6 2983.6 18.3864 3.666e-05 *** X5 1 313.7 313.7 1.9330 0.1670094 X6 1 1955.3 1955.3 12.0497 0.0007207 *** X7 1 1159.8 1159.8 7.1474 0.0085527 ** X8_proporsi 1 285.3 285.3 1.7583 0.1873569 X9_proporsi 1 14.9 14.9 0.0917 0.7625219 X11 1 3124.2 3124.2 19.2529 2.476e-05 *** X13 1 5248.7 5248.7 32.3452 9.263e-08 *** X15 1 3113.4 3113.4 19.1865 2.552e-05 *** Residuals 120 19472.4 162.3 --- Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
> dwtest(Y1 ~ X3 + X4 + X5 + X6 + X7 + X8_proporsi + X9_proporsi + X11 + X13 + + X15, alternative="two.sided", data=Dataset)
Durbin-Watson test
data: Y1 ~ X3 + X4 + X5 + X6 + X7 + X8_proporsi + X9_proporsi + X11 + X13 + X15
DW = 1.7868, p-value = 0.1338
alternative hypothesis: true autocorrelation is not 0
Output GWR
> col.bw <- gwr.sel (Y1 ~ X3 + X4 + X5 + X6 + X7 + X8_proporsi + X9_proporsi +X11
+ X13+X15, coords=cbind(Dataset$coord.x,Dataset$coord.y), data=Dataset, adapt=TRUE, gweight=gwr.bisquare) Adaptive q: 0.381966 CV score: 26012.84 Adaptive q: 0.618034 CV score: 22464.77 Adaptive q: 0.763932 CV score: 21669.3 Adaptive q: 0.7997023 CV score: 21718.52 Adaptive q: 0.7635137 CV score: 21666.03 Adaptive q: 0.7079454 CV score: 21721.83 Adaptive q: 0.7422885 CV score: 21706.53 Adaptive q: 0.7550248 CV score: 21679.42 Adaptive q: 0.7600172 CV score: 21669.79 Adaptive q: 0.7620019 CV score: 21666.73 Adaptive q: 0.7628117 CV score: 21665.58 Adaptive q: 0.7629258 CV score: 21665.42 Adaptive q: 0.7630689 CV score: 21665.22 Adaptive q: 0.7632388 CV score: 21664.99 Adaptive q: 0.7633438 CV score: 21664.84 Adaptive q: 0.7634087 CV score: 21665.21 Adaptive q: 0.7633031 CV score: 21664.9 Adaptive q: 0.7633438 CV score: 21664.84 > gwr9 <- gwr(Y1 ~ X3+X4+X5+X6+X7+X8_proporsi+X9_proporsi+X11+X13+X15,
data=Dataset, adapt=col.bw, coords=cbind(Dataset$coord.x,Dataset$coord.y),
hatmatrix=TRUE, gweight = gwr.bisquare) > gwr9
Call:
gwr(formula = Y1 ~ X3 + X4 + X5 + X6 + X7 + X8_proporsi + X9_proporsi + X11 + X13 + X15, data = Dataset, coords = cbind(Dataset$coord.x, Dataset$coord.y), gweight = gwr.bisquare, adapt = col.bw, hatmatrix = TRUE)
Adaptive quantile: 0.7633438 (about 99 of 131 data points) Summary of GWR coefficient estimates at data points:
Min. 1st Qu. Median 3rd Qu. Max. Global X.Intercept. 2.974e-01 2.610e+00 4.509e+00 1.130e+01 1.318e+01 11.0701 X3 -5.039e-01 -3.097e-01 -1.544e-01 -1.165e-01 -4.698e-02 -0.1397 X4 2.157e-04 9.302e-04 2.289e-03 3.095e-03 3.344e-03 0.0017 X5 -8.176e-03 7.740e-03 2.620e-02 4.761e-02 7.256e-02 0.0305 X6 -1.492e-01 -1.178e-01 -9.680e-02 -6.363e-02 -2.031e-02 -0.1224 X7 -5.847e-02 -3.870e-02 -3.106e-02 -1.335e-02 9.584e-03 -0.0348 X8_proporsi -3.777e+03 -2.594e+03 3.991e+03 6.570e+03 8.613e+03 5391.9833 X9_proporsi -2.040e+01 -7.111e+00 5.921e+00 1.032e+01 1.814e+01 9.1910 X11 -7.726e+01 1.535e+01 2.045e+01 2.345e+02 3.194e+02 24.4383 X13 -3.029e+00 -1.303e+00 6.988e+00 1.366e+01 1.585e+01 9.0453 X15 -2.916e-03 -2.554e-03 -1.610e-03 -7.422e-04 1.054e-05 -0.0026 Number of data points: 131
Effective number of parameters (residual: 2traceS - traceS'S): 32.38782 Effective degrees of freedom (residual: 2traceS - traceS'S): 98.61218 Sigma (residual: 2traceS - traceS'S): 11.88765
Effective number of parameters (model: traceS): 26.29817 Effective degrees of freedom (model: traceS): 104.7018 Sigma (model: traceS): 11.53676
Sigma (ML): 10.31396
AICc (GWR p. 61, eq 2.33; p. 96, eq. 4.21): 1052.778 AIC (GWR p. 96, eq. 4.22): 1009.437
Residual sum of squares: 13935.49 Quasi-global R2: 0.6301353 > anova(gwr9)
Analysis of Variance Table
Df Sum Sq Mean Sq F value OLS Residuals 11.000 19472.4 GWR Improvement 21.388 5536.9 258.88 GWR Residuals 98.612 13935.5 141.32 1.8319 > LMZ.F1GWR.test(gwr8)
> LMZ.F1GWR.test(gwr9)
Leung et al. (2000) F(1) test
data: gwr9
F = 0.87087, df1 = 106.71, df2 = 120.00, p-value = 0.2332 alternative hypothesis: less
sample estimates:
SS OLS residuals SS GWR residuals 19472.42 13935.49
Tabel GWR
No
Estimasi
X.Intercept. X3 X4 X5 X6 X7 X8_proporsi X9_proporsi X11 X13 X15
1 4.98252 -0.35545 0.003186 0.012495 -0.13068 -0.04406 6077.42 -18.2677 13.33625 15.5133 -0.00287 2 4.297693 -0.33624 0.003162 0.009668 -0.12679 -0.04345 6417.217 -17.2571 14.01187 15.34986 -0.00281 3 4.906049 -0.34693 0.003156 0.010156 -0.1366 -0.0453 6249.113 -20.2218 12.92641 15.85064 -0.00288 4 4.365559 -0.32399 0.003115 0.006782 -0.13339 -0.0447 6666.819 -19.1453 13.60649 15.62023 -0.00282 ... ... ... ... ... ... ... ... ... ... ... ... Se_Estimasi
X.Intercept._se X3_se X4_se X5_se X6_se X7_se X8_proporsi_se X9_proporsi_se X11_se X13_se X15_se
8.792043 0.174125 0.000663 0.074382 0.040146 0.048278 5774.16 23.47021 11.9298 3.744939 0.000735 8.744568 0.171842 0.000653 0.073765 0.039795 0.047734 5709.523 23.30185 11.89793 3.695918 0.00073 8.929139 0.176316 0.000661 0.074628 0.040327 0.048679 5811.386 23.84359 11.95454 3.859367 0.000739 8.855696 0.17411 0.000648 0.073948 0.039959 0.048094 5737.208 23.66625 11.92156 3.782061 0.000733 ... ... ... ... ... ... ... ... ... ... ... t hitung
X.Intercept. X3 X4 X5 X6 X7 X8_proporsi X9_proporsi X11 X13 X15
0.566708 -2.04134 4.802074 0.167987 -3.25505 -0.91265 1.05252 -0.77834 1.117894 4.142471 -3.9095 0.49147 -1.95666 4.841988 0.131072 -3.18618 -0.91023 1.12395 -0.74059 1.177674 4.153193 -3.84764 0.549443 -1.96763 4.77312 0.136094 -3.38744 -0.93056 1.075322 -0.8481 1.081297 4.107057 -3.89906 0.492966 -1.86085 4.809148 0.09171 -3.33814 -0.92938 1.162032 -0.80897 1.141335 4.130084 -3.84731
Lampiran 11. Output OLS dan GWR Y3 di Kecamatan Propinsi Jambi
Output OLS
> LinearModel.2 <- lm(y2 ~ X3 + X4 + X5 + X6 + X7 + X8_proporsi + X9_proporsi + + X11 + X13 + X15, data=Dataset)
>summary(LinearModel.2) Call:
lm(formula = Y2 ~ X3 + X4 + X5 + X6 + X7 + X8_proporsi + X9_proporsi + X11 + X13 + X15, data = Dataset)
Residuals:
Min 1Q Median 3Q Max -11.8423 -3.0607 -0.5728 2.5446 28.8591 Coefficients:
Estimate Std. Error t value Pr(>|t|) (Intercept) 5.594e+00 2.304e+00 2.428 0.01666 * X3 1.179e-01 5.539e-02 2.128 0.03538 * X4 6.157e-04 1.649e-04 3.734 0.00029 *** X5 -5.683e-03 2.708e-02 -0.210 0.83416 X6 -1.354e-02 1.523e-02 -0.889 0.37555 X7 -2.277e-02 1.558e-02 -1.462 0.14649 X8_proporsi -4.107e+03 2.129e+03 -1.929 0.05613 . X9_proporsi 1.287e+01 6.927e+00 1.858 0.06556 . X11 3.453e+00 5.401e+00 0.639 0.52379 X13 -7.681e-01 8.075e-01 -0.951 0.34343 X15 7.383e-04 2.489e-04 2.966 0.00364 ** ---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1 Residual standard error: 5.431 on 120 degrees of freedom Multiple R-squared: 0.2516, Adjusted R-squared: 0.1892 F-statistic: 4.034 on 10 and 120 DF, p-value: 8.76e-05
>AIC(LinearModel.2) [1] 827.6218 > vif(LinearModel.1) X3 X4 X5 X6 X7 X8_proporsi 1.657628 1.157008 1.183135 1.138884 1.160241 1.115253 X9_proporsi X11 X13 X15 1.367194 1.159106 1.269315 1.640377 > library(zoo, pos=14) > library(lmtest, pos=14)
> bptest(Y2 ~ X3 + X4 + X5 + X6 + X7 + X8_proporsi + X9_proporsi + X11 + X13 + + X15, varformula = ~ fitted.values(LinearModel.1), studentize=FALSE, + data=Dataset)
Breusch-Pagan test
data: Y2 ~ X3 + X4 + X5 + X6 + X7 + X8_proporsi + X9_proporsi + X11 + X13 + X15
BP = 9.3131, df = 1, p-value = 0.002275
> dwtest(Y2 ~ X3 + X4 + X5 + X6 + X7 + X8_proporsi + X9_proporsi + X11 + X13 + + X15, alternative="two.sided", data=Dataset)
Durbin-Watson test
data: Y2 ~ X3 + X4 + X5 + X6 + X7 + X8_proporsi + X9_proporsi + X11 + X13 + X15
DW = 1.8644, p-value = 0.2939
> Dataset<- within(Dataset, { + fitted.LinearModel.1 <- fitted(LinearModel.1) + residuals.LinearModel.1 <- residuals(LinearModel.1) + rstudent.LinearModel.1 <- rstudent(LinearModel.1) + hatvalues.LinearModel.1 <- hatvalues(LinearModel.1) + cooks.distance.LinearModel.1 <- cooks.distance(LinearModel.1) + obsNumber <- 1:nrow(Dataset) + }) > with(Dataset, shapiro.test(residuals.LinearModel.1)) Shapiro-Wilk normality test
data: residuals.LinearModel.1 W = 0.91099, p-value = 2.84e-07 > anova(LinearModel.1)
Analysis of Variance Table
Response: Y2
Df Sum Sq Mean Sq F value Pr(>F) X3 1 5.4 5.44 0.1845 0.6683190 X4 1 476.4 476.37 16.1488 0.0001026 *** X5 1 36.5 36.45 1.2356 0.2685337 X6 1 53.7 53.75 1.8221 0.1796077 X7 1 48.7 48.72 1.6518 0.2011950 X8_proporsi 1 73.7 73.70 2.4985 0.1165859 X9_proporsi 1 165.1 165.10 5.5968 0.0195961 * X11 1 2.0 2.03 0.0687 0.7936952 X13 1 68.9 68.88 2.3349 0.1291357 X15 1 259.6 259.57 8.7993 0.0036373 ** Residuals 120 3539.8 29.50 --- Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1 Output GWR
> col.bw <- gwr.sel (Y2 ~ X3 + X4 + X5 + X6 + X7 + X8_proporsi + X9_proporsi +X11
+ X13+X15, coords=cbind(Dataset$coord.x,Dataset$coord.y), data=Dataset, adapt=TRUE, gweight=gwr.bisquare) Adaptive q: 0.381966 CV score: 5226.613 Adaptive q: 0.618034 CV score: 4653.54 Adaptive q: 0.763932 CV score: 4472.696 Adaptive q: 0.8902392 CV score: 4337.266 Adaptive q: 0.8419941 CV score: 4394.033 Adaptive q: 0.9321641 CV score: 4309.49 Adaptive q: 0.9693037 CV score: 4261.967 Adaptive q: 0.9551176 CV score: 4279.309 Adaptive q: 0.9810287 CV score: 4246.916 Adaptive q: 0.9882751 CV score: 4243.092 Adaptive q: 0.9912728 CV score: 4244.539 Adaptive q: 0.9873268 CV score: 4242.668 Adaptive q: 0.9849211 CV score: 4241.699 Adaptive q: 0.9834343 CV score: 4243.43 Adaptive q: 0.98584 CV score: 4242.049 Adaptive q: 0.9843532 CV score: 4242.151 Adaptive q: 0.98514 CV score: 4241.78 Adaptive q: 0.9847042 CV score: 4241.67 Adaptive q: 0.9846635 CV score: 4241.725 Adaptive q: 0.9848011 CV score: 4241.655 Adaptive q: 0.984847 CV score: 4241.672 Adaptive q: 0.9847604 CV score: 4241.641 Adaptive q: 0.9847604 CV score: 4241.641 > gwr9 <- gwr(Y2 ~ X3+X4+X5+X6+X7+X8_proporsi+X9_proporsi+X11+X13+X15,
data=Dataset, adapt=col.bw, coords=cbind(Dataset$coord.x,Dataset$coord.y),
hatmatrix=TRUE, gweight = gwr.bisquare)
> gwr11 <- gwr(Y2 ~ X3+X4+X5+X6+X7+X8_proporsi+X9_proporsi+X11+X13+X15,
data=Dataset, adapt=col.bw, coords=cbind(Dataset$coord.x,Dataset$coord.y),
> gwr11 Call:
gwr(formula = Y2 ~ X3 + X4 + X5 + X6 + X7 + X8_proporsi + X9_proporsi + X11 + X13 + X15, data = Dataset, coords = cbind(Dataset$coord.x, Dataset$coord.y), gweight = gwr.bisquare, adapt = col.bw, hatmatrix = TRUE)
Kernel function: gwr.bisquare
Adaptive quantile: 0.9847604 (about 129 of 131 data points) Summary of GWR coefficient estimates at data points:
Min. 1st Qu. Median 3rd Qu. Max. Global X.Intercept. 3.079e+00 3.709e+00 5.097e+00 5.871e+00 6.604e+00 5.5941 X3 5.217e-02 7.832e-02 1.095e-01 1.826e-01 1.849e-01 0.1179 X4 5.463e-04 5.724e-04 6.115e-04 6.934e-04 7.250e-04 0.0006 X5 -2.192e-02 -1.814e-02 -3.739e-03 3.972e-03 8.079e-03 -0.0057 X6 -1.712e-02 -1.620e-02 -1.568e-02 -1.100e-02 -1.027e-02 -0.0135 X7 -2.353e-02 -2.060e-02 -1.906e-02 -1.831e-02 -1.669e-02 -0.0228 X8_proporsi -7.247e+03 -5.269e+03 -4.760e+03 -3.775e+03 -2.956e+03 -4107.1807 X9_proporsi 5.495e+00 8.930e+00 2.162e+01 2.296e+01 2.378e+01 12.8728 X11 -2.491e+01 -3.820e+00 1.343e+00 2.723e+00 3.175e+00 3.4534 X13 -1.480e+00 -1.116e+00 -3.850e-01 5.677e-01 1.615e+00 -0.7681 X15 4.346e-04 5.218e-04 5.966e-04 8.535e-04 1.069e-03 0.0007 Number of data points: 131
Effective number of parameters (residual: 2traceS - traceS'S): 21.64834 Effective degrees of freedom (residual: 2traceS - traceS'S): 109.3517 Sigma (residual: 2traceS - traceS'S): 5.352324
Effective number of parameters (model: traceS): 17.81929 Effective degrees of freedom (model: traceS): 113.1807 Sigma (model: traceS): 5.261007
Sigma (ML): 4.890119
AICc (GWR p. 61, eq 2.33; p. 96, eq. 4.21): 831.9608 AIC (GWR p. 96, eq. 4.22): 805.432
Residual sum of squares: 3132.638 Quasi-global R2: 0.3376878
> anova(gwr9)
Analysis of Variance Table
Df Sum Sq Mean Sq F value OLS Residuals 11.000 3539.8 GWR Improvement 10.648 407.2 38.241 GWR Residuals 109.352 3132.6 28.647 1.3349 > All11=data.frame(gwr11$SDF)
> LMZ.F1GWR.test(gwr11)
Leung et al. (2000) F(1) test data: gwr11
F = 0.97114, df1 = 114.57, df2 = 120.00, p-value = 0.4377 alternative hypothesis: less
sample estimates:
SS OLS residuals SS GWR residuals 3539.845 3132.638
Tabel GWR
No
Estimasi
X.Intercept. X3 X4 X5 X6 X7 X8_proporsi X9_proporsi X11 X13 X15
1 6.50575 0.055641 0.000559 0.006254 -0.01569 -0.01918 -3992.86 23.55626 2.726442 -1.24353 0.000498 2 6.389127 0.059902 0.000563 0.005786 -0.01591 -0.01898 -3960.75 23.4409 2.742101 -1.22004 0.000509 3 6.589241 0.052624 0.000558 0.007091 -0.01571 -0.01902 -3818.74 23.70496 2.831632 -1.33464 0.000497 4 6.495196 0.056061 0.000562 0.006842 -0.01593 -0.01882 -3748.97 23.61915 2.873995 -1.33218 0.000509 ... ... ... ... ... ... ... ... ... ... ... ... Se_Estimasi
X.Intercept._se X3_se X4_se X5_se X6_se X7_se X8_proporsi_se X9_proporsi_se X11_se X13_se X15_se
2.707632 0.063805 0.000223 0.029232 0.016474 0.018009 2316.564 8.777405 5.316907 0.925321 0.000285 2.68045 0.063076 0.000219 0.028978 0.016372 0.017813 2294.7 8.686009 5.30936 0.913379 0.000282 2.733809 0.064473 0.000223 0.029303 0.016514 0.018122 2327.559 8.846264 5.320497 0.935488 0.000286 2.713598 0.063902 0.00022 0.029079 0.016429 0.017957 2308.533 8.771917 5.313788 0.925826 0.000283 2.708887 0.063739 0.000217 0.028962 0.016395 0.017885 2299.614 8.744669 5.31076 0.922678 0.000282 t hitung
X.Intercept. X3 X4 X5 X6 X7 X8_proporsi X9_proporsi X11 X13 X15
2.402745 0.872051 2.503809 0.213936 -0.95229 -1.06482 -1.72361 2.683739 0.512787 -1.3439 1.747177 2.383602 0.949676 2.569783 0.199659 -0.97179 -1.06574 -1.72604 2.698697 0.516466 -1.33574 1.80461 2.410278 0.816216 2.50015 0.242001 -0.95115 -1.04976 -1.64066 2.679657 0.532212 -1.42668 1.741671 2.393574 0.877298 2.560628 0.235298 -0.96947 -1.04801 -1.62396 2.692587 0.540856 -1.43891 1.796092
Lampiran 12. Output OLS dan GWR di Kabupaten/Kota (Y1) Propinsi Jawa Barat
Output OLS
> Dataset <- readXL("D:/PROYEK/bupertiwi 09 08/data.xlsx", + rownames=FALSE, header=TRUE, na="", sheet="Sheet2", + stringsAsFactors=TRUE)
> LinearModel.1 <- lm(Y1 ~ X3 +X4 +X5 +X6 +X7 +X8_proporsi + +X9_proporsi +X11 +X13, data=Dataset)
>summary(LinearModel.1) Call:
lm(formula = Y1 ~ X3 + X4 + X5 + X6 + X7 + X8_proporsi + X9_proporsi + X11 + X13, data = Dataset)
Residuals:
Min 1Q Median 3Q Max -32.636 -10.434 -1.099 7.225 44.559 Coefficients:
Estimate Std. Error t value Pr(>|t|) (Intercept) 7.019e+00 7.607e+01 0.092 0.92763 X3 -1.015e+00 8.125e-01 -1.249 0.22946 X4 1.713e-03 1.524e-03 1.124 0.27762 X5 -8.304e-01 4.187e-01 -1.983 0.06477 . X6 1.668e+00 5.626e-01 2.965 0.00911 ** X7 -2.972e-01 4.072e-01 -0.730 0.47607 X8_proporsi 9.497e+04 1.450e+05 0.655 0.52185 X9_proporsi 1.506e-06 6.007e-06 0.251 0.80522 X11 6.073e+02 6.784e+02 0.895 0.38394 X13 4.527e+01 1.721e+01 2.630 0.01818 * ---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1 Residual standard error: 22.74 on 16 degrees of freedom
Multiple R-squared: 0.7065, Adjusted R-squared: 0.5414 F-statistic: 4.279 on 9 and 16 DF, p-value: 0.00562
> AIC(LinearModel.1) [1] 245.6169 > vif(LinearModel.1) X3 X4 X5 X6 X7 X8_proporsi 3.147042 2.469048 2.794852 2.215982 2.258081 3.694279 X9_proporsi X11 X13 2.153758 5.236166 1.387445
> bptest(Y1 ~ X3 + X4 + X5 + X6 + X7 + X8_proporsi + X9_proporsi + X11 + X13, + varformula = ~ fitted.values(LinearModel.1), studentize=FALSE, data=Dataset)
Breusch-Pagan test
data: Y1 ~ X3 + X4 + X5 + X6 + X7 + X8_proporsi + X9_proporsi + X11 + X13 BP = 13.119, df = 1, p-value = 0.0002923
> Dataset<- within(Dataset, {
+ residuals.LinearModel.1 <- residuals(LinearModel.1) + })
> with(Dataset, shapiro.test(residuals.LinearModel.1)) Shapiro-Wilk normality test
data: residuals.LinearModel.1 W = 0.96279, p-value = 0.4493
+ alternative="two.sided", data=Dataset) Durbin-Watson test
data: Y1 ~ X3 + X4 + X5 + X6 + X7 + X8_proporsi + X9_proporsi + X11 + X13 DW = 1.5637, p-value = 0.07887
alternative hypothesis: true autocorrelation is not 0 > anova(LinearModel.1)
Analysis of Variance Table Response: Y1
Df Sum Sq Mean Sq F value Pr(>F) X3 1 755.2 755.2 1.4604 0.2444297 X4 1 1170.9 1170.9 2.2643 0.1518717 X5 1 1070.3 1070.3 2.0697 0.1695264 X6 1 12880.4 12880.4 24.9078 0.0001333 *** X7 1 7.7 7.7 0.0149 0.9044211 X8_proporsi 1 221.0 221.0 0.4274 0.5225692 X9_proporsi 1 213.2 213.2 0.4122 0.5299289 X11 1 17.0 17.0 0.0329 0.8582870 X13 1 3577.6 3577.6 6.9182 0.0181867 * Residuals 16 8274.0 517.1 --- Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1 Output GWR
> col.bw <- gwr.sel (Y ~ X3 + X4 + X5 + X6 + X7 + X8_proporsi + X9_proporsi + X11 + X13, coords=cbind(Dataset$X_cord,Dataset$Y_cord), data=Dataset, adapt=TRUE, gweight=gwr.Gauss) Adaptive q: 0.381966 CV score: 49962.69 Adaptive q: 0.618034 CV score: 39506.28 Adaptive q: 0.763932 CV score: 36207.49 Adaptive q: 0.8901259 CV score: 34857.51 Adaptive q: 0.9492 CV score: 34711.26 Adaptive q: 0.9475556 CV score: 34717.44 Adaptive q: 0.9686039 CV score: 34568.91 Adaptive q: 0.9805961 CV score: 34414.81 Adaptive q: 0.9880078 CV score: 34325.37 Adaptive q: 0.9925884 CV score: 34272.16 Adaptive q: 0.9954194 CV score: 34240.02 Adaptive q: 0.997169 CV score: 34220.44 Adaptive q: 0.9982504 CV score: 34208.45 Adaptive q: 0.9989187 CV score: 34201.07 Adaptive q: 0.9993317 CV score: 34196.53 Adaptive q: 0.999587 CV score: 34193.73 Adaptive q: 0.9997447 CV score: 34192 Adaptive q: 0.9998422 CV score: 34190.93 Adaptive q: 0.9999025 CV score: 34190.27 Adaptive q: 0.9999432 CV score: 34189.83 Adaptive q: 0.9999432 CV score: 34189.83
> gwr <- gwr(Y ~ X3 + X4 + X5 + X6 + X7 + X8_proporsi + X9_proporsi + X11 + X13,
data=Dataset, adapt=col.bw, coords=cbind(Dataset$X_cord,Dataset$Y_cord),
hatmatrix=TRUE, gweight = gwr.Gauss) > gwr
Call:
gwr(formula = Y ~ X3 + X4 + X5 + X6 + X7 + X8_proporsi + X9_proporsi + X11 + X13, data = Dataset, coords = cbind(Dataset$X_cord,
Dataset$Y_cord), gweight = gwr.Gauss, adapt = col.bw, hatmatrix = TRUE) Kernel function: gwr.Gauss
Adaptive quantile: 0.9999432 (about 25 of 26 data points) Summary of GWR coefficient estimates at data points:
Min. 1st Qu. Median 3rd Qu. Max. X.Intercept. 6.975e+00 7.662e+00 8.219e+00 9.088e+00 1.116e+01 X3 -1.052e+00 -1.045e+00 -1.028e+00 -1.010e+00 -9.885e-01 X4 1.296e-03 1.487e-03 1.561e-03 1.666e-03 1.734e-03 X5 -9.374e-01 -9.217e-01 -8.350e-01 -7.312e-01 -7.135e-01 X6 1.484e+00 1.530e+00 1.597e+00 1.714e+00 1.754e+00 X7 -2.974e-01 -2.896e-01 -2.793e-01 -2.638e-01 -2.220e-01
X8_proporsi 9.458e+04 9.598e+04 9.822e+04 9.989e+04 1.011e+05 X9_proporsi 1.228e-06 1.444e-06 2.415e-06 2.622e-06 2.961e-06 X11 5.626e+02 5.812e+02 6.761e+02 7.036e+02 7.129e+02 X13 4.508e+01 4.529e+01 4.625e+01 4.638e+01 4.671e+01 Global X.Intercept. 7.0189 X3 -1.0152 X4 0.0017 X5 -0.8304 X6 1.6683 X7 -0.2972 X8_proporsi 94965.7427 X9_proporsi 0.0000 X11 607.2883 X13 45.2722 Number of data points: 26
Effective number of parameters (residual: 2traceS - traceS'S): 11.7701 Effective degrees of freedom (residual: 2traceS - traceS'S): 14.2299 Sigma (residual: 2traceS - traceS'S): 22.64773
Effective number of parameters (model: traceS): 10.94918 Effective degrees of freedom (model: traceS): 15.05082 Sigma (model: traceS): 22.02143
Sigma (ML): 16.75479
AICc (GWR p. 61, eq 2.33; p. 96, eq. 4.21): 267.967 AIC (GWR p. 96, eq. 4.22): 231.3056
Residual sum of squares: 7298.795 Quasi-global R2: 0.7410606 > anova(gwr)
Analysis of Variance Table
Df Sum Sq Mean Sq F value OLS Residuals 10.0000 8273.8 GWR Improvement 1.7701 975.0 550.81 GWR Residuals 14.2299 7298.8 512.92 1.0739
> LMZ.F1GWR.test(gwr)
Leung et al. (2000) F(1) test data: gwr
F = 0.99189, df1 = 15.821, df2 = 16.000, p-value = 0.494 alternative hypothesis: less
sample estimates:
SS OLS residuals SS GWR residuals 8273.790 7298.795
> All=data.frame(gwr$SDF)
> write.table(All, "D:/PROYEK/bupertiwi 09 08/All1.csv", sep=" ", + col.names=TRUE, row.names=TRUE, quote=TRUE, na="NA")
Tabel GWR
No
Estimasi
X.Intercept. X3 X4 X5 X6 X7 X8_proporsi X9_proporsi X11 X13
1 8.163 -1.049 0.002 -0.937 1.749 -0.292 98543.212 0.000 562.708 45.110 2 9.091 -1.040 0.002 -0.929 1.714 -0.280 99334.635 0.000 571.692 45.084 3 10.072 -1.032 0.002 -0.901 1.652 -0.264 100538.806 0.000 609.252 45.351 4 11.165 -1.009 0.001 -0.803 1.494 -0.222 100197.135 0.000 708.149 46.328 ... ... ... ... ... ... ... ... ... ... ... Se_Estimasi
X.Intercept._se X3_se X4_se X5_se X6_se X7_se X8_proporsi_se X9_proporsi_se X11_se X13_se
74.389 0.797 0.001 0.411 0.547 0.397 141478.818 0.000 658.759 16.786 74.454 0.798 0.001 0.411 0.547 0.396 141565.488 0.000 658.701 16.794 74.623 0.798 0.001 0.411 0.547 0.396 141403.395 0.000 659.031 16.793 74.643 0.794 0.001 0.410 0.551 0.400 141675.260 0.000 664.979 16.759 ... ... ... ... ... ... ... ... ... ... t_hitung
X.Intercept. X3 X4 X5 X6 X7 X8_proporsi X9_proporsi X11 X13
0.110 -1.316 1.160 -2.278 3.197 -0.736 0.697 0.212 0.854 2.687
0.122 -1.303 1.125 -2.263 3.134 -0.707 0.702 0.231 0.868 2.685
0.135 -1.293 1.053 -2.196 3.022 -0.666 0.711 0.305 0.924 2.701
0.150 -1.271 0.868 -1.960 2.711 -0.556 0.707 0.503 1.065 2.764
Lampiran 13. Output OLS dan GWR Y2 di Kecamatan Propinsi Jawa Barat
Output OLS
> Dataset <- read.table("D:/PROYEK/bu pertiwi 08 08/DATA JABAR.txt", + header=TRUE, sep="", na.strings="NA", dec=".", strip.white=TRUE)
> LinearModel.3 <- lm(Y1 ~ X3 +X4 +X5 +X6 +X7 +X8_proporsi +X9_proporsi + X11 + +X13, data=Dataset)
>summary(LinearModel.3) Call:
lm(formula = Y1 ~ X3 + X4 + X5 + X6 + X7 + X8_proporsi + X9_proporsi + X11 + X13, data = Dataset)
Residuals:
Min 1Q Median 3Q Max -33.644 -9.281 -2.348 6.904 44.574 Coefficients:
Estimate Std. Error t value Pr(>|t|) (Intercept) 1.674e+01 2.926e+00 5.722 1.69e-08 *** X3 -1.643e-01 5.056e-02 -3.249 0.001224 ** X4 -6.610e-04 1.094e-04 -6.041 2.75e-09 *** X5 -5.108e-02 1.997e-02 -2.557 0.010802 * X6 5.737e-02 2.254e-02 2.545 0.011195 * X7 -2.171e-02 1.808e-02 -1.201 0.230309 X8_proporsi -2.076e+03 3.590e+03 -0.578 0.563377 X9_proporsi 1.915e+01 4.926e+00 3.888 0.000113 *** X11 3.873e+02 2.997e+01 12.923 < 2e-16 *** X13 6.983e-01 1.875e+00 0.372 0.709764 ---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1 Residual standard error: 13.17 on 580 degrees of freedom Multiple R-squared: 0.3846, Adjusted R-squared: 0.3751 F-statistic: 40.28 on 9 and 580 DF, p-value: < 2.2e-16
>AIC(LinearModel.3) [1] 4728.628 > vif(LinearModel.1) X3 X4 X5 X6 X7 X8_proporsi 1.388910 1.568085 1.208369 1.117943 1.085119 1.052912 X9_proporsi X11 X13 1.151576 1.739064 1.117096
> bptest(Y1 ~ X3 + X4 + X5 + X6 + X7 + X8_proporsi + X9_proporsi + X11 + X13, + varformula = ~ fitted.values(LinearModel.1), studentize=FALSE, data=Dataset)
Breusch-Pagan test
data: Y1 ~ X3 + X4 + X5 + X6 + X7 + X8_proporsi + X9_proporsi + X11 + X13 BP = 38.954, df = 1, p-value = 4.339e-10
> dwtest(Y1 ~ X3 + X4 + X5 + X6 + X7 + X8_proporsi + X9_proporsi + X11 + X13, + alternative="two.sided", data=Dataset)
Durbin-Watson test
data: Y1 ~ X3 + X4 + X5 + X6 + X7 + X8_proporsi + X9_proporsi + X11 + X13 DW = 1.3699, p-value = 5.713e-15
alternative hypothesis: true autocorrelation is not 0
> Dataset<- within(Dataset, {
+ fitted.LinearModel.1 <- fitted(LinearModel.1) + residuals.LinearModel.1 <- residuals(LinearModel.1) + rstudent.LinearModel.1 <- rstudent(LinearModel.1)
+ hatvalues.LinearModel.1 <- hatvalues(LinearModel.1)
+ cooks.distance.LinearModel.1 <- cooks.distance(LinearModel.1) + obsNumber <- 1:nrow(Dataset)
+ })
> with(Dataset, shapiro.test(residuals.LinearModel.1)) Shapiro-Wilk normality test
data: residuals.LinearModel.1 W = 0.95503, p-value = 1.961e-12
> anova(LinearModel.1) Analysis of Variance Table Response: Y1
Df Sum Sq Mean Sq F value Pr(>F) X3 1 14020 14019.5 80.7740 < 2.2e-16 *** X4 1 96 96.4 0.5555 0.4564 X5 1 3088 3088.0 17.7914 2.860e-05 *** X6 1 4382 4382.2 25.2480 6.724e-07 *** X7 1 35 34.8 0.2003 0.6546 X8_proporsi 1 277 276.6 1.5938 0.2073 X9_proporsi 1 11477 11476.7 66.1233 2.578e-15 *** X11 1 29522 29521.9 170.0914 < 2.2e-16 *** X13 1 24 24.1 0.1386 0.7098 Residuals 580 100668 173.6 --- Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1 Output GWR
> col.bw <- gwr.sel (Y1 ~ X3 + X4 + X5 + X6 + X7 + X8_proporsi + X9_proporsi + X11 + X13, coords=cbind(Dataset$X_coord,Dataset$Y_cord), data=Dataset, adapt=TRUE, gweight=gwr.bisquare) Adaptive q: 0.381966 CV score: 83215.55 Adaptive q: 0.618034 CV score: 87312.3 Adaptive q: 0.236068 CV score: 82273.21 Adaptive q: 0.1958002 CV score: 83465.03 Adaptive q: 0.2923428 CV score: 82472.22 Adaptive q: 0.2575631 CV score: 82135.19 Adaptive q: 0.2580294 CV score: 82135.92 Adaptive q: 0.25566 CV score: 82198.06 Adaptive q: 0.2577431 CV score: 82133.82 Adaptive q: 0.2577838 CV score: 82134.11 Adaptive q: 0.2577024 CV score: 82133.53 Adaptive q: 0.2576492 CV score: 82133.16 Adaptive q: 0.2576085 CV score: 82133.64 Adaptive q: 0.2576492 CV score: 82133.16
> gwr4 <- gwr(Y1 ~ X3 + X4 + X5 + X6 + X7 + X8_proporsi + X9_proporsi + X11 + X13,
data=Dataset, adapt=col.bw, coords=cbind(Dataset$X_coord,Dataset$Y_cord),
hatmatrix=TRUE, gweight = gwr.bisquare) > gwr4
Call:
gwr(formula = Y1 ~ X3 + X4 + X5 + X6 + X7 + X8_proporsi + X9_proporsi + X11 + X13, data = Dataset, coords = cbind(Dataset$X_coord,
Dataset$Y_cord), gweight = gwr.bisquare, adapt = col.bw, hatmatrix = TRUE)
Kernel function: gwr.bisquare
Adaptive quantile: 0.2576492 (about 152 of 590 data points) Summary of GWR coefficient estimates at data points:
Min. 1st Qu. Median 3rd Qu. Max. Global X.Intercept. -8.393e+00 5.562e+00 2.127e+01 3.288e+01 6.279e+01 16.7432 X3 -7.063e-01 -2.784e-01 -1.561e-01 -1.264e-02 1.670e-01 -0.1643 X4 -3.148e-03 -1.296e-03 -3.241e-04 -5.943e-05 1.176e-03 -0.0007 X5 -1.824e-01 -4.698e-02 -2.841e-02 -8.471e-03 3.710e-02 -0.0511 X6 -6.338e-02 -2.888e-02 -6.869e-03 3.940e-02 1.581e-01 0.0574 X7 -1.358e-01 -4.133e-02 -2.013e-02 -3.838e-04 1.397e-01 -0.0217
X8_proporsi -4.669e+04 -1.737e+04 -5.176e+03 1.755e+03 1.742e+04 -2075.6604 X9_proporsi -2.933e+01 4.858e+00 2.464e+01 4.999e+01 1.027e+02 19.1542 X11 1.148e+01 1.987e+02 4.251e+02 4.910e+02 8.723e+02 387.2866 X13 -3.326e+01 -8.471e+00 1.292e+00 1.175e+01 4.793e+01 0.6983 Number of data points: 590
Effective number of parameters (residual: 2traceS - traceS'S): 106.3821 Effective degrees of freedom (residual: 2traceS - traceS'S): 483.6179 Sigma (residual: 2traceS - traceS'S): 10.92006
Effective number of parameters (model: traceS): 82.36377 Effective degrees of freedom (model: traceS): 507.6362 Sigma (model: traceS): 10.6586
Sigma (ML): 9.886676
AICc (GWR p. 61, eq 2.33; p. 96, eq. 4.21): 4572.495 AIC (GWR p. 96, eq. 4.22): 4460.313
Residual sum of squares: 57670.35 Quasi-global R2: 0.6474658 > LMZ.F1GWR.test(gwr4)
Leung et al. (2000) F(1) test data: gwr4
F = 0.68705, df1 = 512.47, df2 = 580.00, p-value = 6.972e-06 alternative hypothesis: less
sample estimates:
SS OLS residuals SS GWR residuals 100667.74 57670.35
Tabel GWR
No
Estimasi
X.Intercept. X3 X4 X5 X6 X7 X8_proporsi X9_proporsi X11 X13
1 10.066 0.030 0.000 -0.013 0.025 -0.049 2075.485 92.724 401.286 -7.002 2 7.468 0.039 0.000 -0.015 0.030 -0.041 3390.025 85.973 477.301 -4.906 3 5.879 0.041 0.000 -0.016 0.030 -0.035 4605.767 90.191 487.155 -3.545 4 8.411 0.026 0.000 -0.018 0.036 -0.046 2775.381 77.275 481.670 -5.392 ... ... ... ... ... ... ... ... ... ... ... Se_Estimasi
X.Intercept._se X3_se X4_se X5_se X6_se X7_se X8_proporsi_se X9_proporsi_se X11_se X13_se
7.607 0.111 0.000 0.045 0.045 0.034 11725.353 23.673 88.650 6.219 7.726 0.112 0.000 0.046 0.045 0.034 11745.638 22.554 89.363 6.291 7.853 0.113 0.000 0.045 0.044 0.034 12018.386 22.567 87.342 6.510 7.428 0.109 0.000 0.045 0.044 0.033 11514.111 20.352 85.657 5.899 ... ... ... ... ... ... ... ... ... ... t hitung
X.Intercept. X3 X4 X5 X6 X7 X8_proporsi X9_proporsi X11 X13
1.323 0.272 1.144 -0.283 0.552 -1.448 0.177 3.917 4.527 -1.126
0.967 0.345 0.611 -0.336 0.663 -1.211 0.289 3.812 5.341 -0.780
0.749 0.361 -0.085 -0.342 0.688 -1.030 0.383 3.997 5.578 -0.545
1.132 0.236 0.951 -0.402 0.816 -1.387 0.241 3.797 5.623 -0.914
Lampiran 14. Output OLS dan GWR Y3 di Kecamatan Propinsi Jawa Barat
Output OLS
> LinearModel.3 <- lm(Y ~ > LinearModel.4 <- lm(Y2 ~ X3 + X4 + X5 + X6 + X7 + X8_proporsi + X9_proporsi
+ + X11 + X13 +, data=Dataset) >summary(LinearModel.4)
> LinearModel.5 <- lm(Y2 ~ X3 +X4 +X5 +X6 +X7 +X8_proporsi +X9_proporsi + X11 + +X13, data=Dataset)
>summary(LinearModel.5) Call:
lm(formula = Y2 ~ X3 + X4 + X5 + X6 + X7 + X8_proporsi + X9_proporsi + X11 + X13, data = Dataset)
Residuals:
Min 1Q Median 3Q Max -11.3745 -3.5605 -0.6888 2.8837 24.2950 Coefficients:
Estimate Std. Error t value Pr(>|t|) (Intercept) 5.464e+00 1.145e+00 4.771 2.33e-06 *** X3 3.877e-02 1.979e-02 1.959 0.05060 . X4 -2.510e-07 4.283e-05 -0.006 0.99533 X5 -2.109e-02 7.818e-03 -2.698 0.00718 ** X6 4.319e-02 8.824e-03 4.895 1.28e-06 *** X7 -7.892e-03 7.076e-03 -1.115 0.26521 X8_proporsi -1.844e+03 1.405e+03 -1.312 0.19000 X9_proporsi 5.089e+00 1.928e+00 2.640 0.00853 ** X11 6.700e+01 1.173e+01 5.712 1.79e-08 *** X13 1.337e+00 7.340e-01 1.821 0.06909 . ---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 5.156 on 580 degrees of freedom Multiple R-squared: 0.1755, Adjusted R-squared: 0.1627 F-statistic: 13.71 on 9 and 580 DF, p-value: < 2.2e-16
>AIC(LinearModel.5) [1] 3621.761
> LinearModel.1 <- lm(Y2 ~ X3 + X4 + X5 + X6 + X7 + X8_proporsi + X9_proporsi + + X11 + X13, data=Dataset)
> summary(LinearModel.1) Call:
lm(formula = Y2 ~ X3 + X4 + X5 + X6 + X7 + X8_proporsi + X9_proporsi + X11 + X13, data = Dataset)
Residuals:
Min 1Q Median 3Q Max -11.3745 -3.5605 -0.6888 2.8837 24.2950 Coefficients:
Estimate Std. Error t value Pr(>|t|) (Intercept) 5.464e+00 1.145e+00 4.771 2.33e-06 *** X3 3.877e-02 1.979e-02 1.959 0.05060 . X4 -2.510e-07 4.283e-05 -0.006 0.99533 X5 -2.109e-02 7.818e-03 -2.698 0.00718 ** X6 4.319e-02 8.824e-03 4.895 1.28e-06 *** X7 -7.892e-03 7.076e-03 -1.115 0.26521 X8_proporsi -1.844e+03 1.405e+03 -1.312 0.19000 X9_proporsi 5.089e+00 1.928e+00 2.640 0.00853 ** X11 6.700e+01 1.173e+01 5.712 1.79e-08 *** X13 1.337e+00 7.340e-01 1.821 0.06909 .
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1 Residual standard error: 5.156 on 580 degrees of freedom Multiple R-squared: 0.1755, Adjusted R-squared: 0.1627 F-statistic: 13.71 on 9 and 580 DF, p-value: < 2.2e-16
> AIC(LinearModel.1) [1] 3621.761 > vif(LinearModel.1) X3 X4 X5 X6 X7 X8_proporsi 1.388910 1.568085 1.208369 1.117943 1.085119 1.052912 X9_proporsi X11 X13 1.151576 1.739064 1.117096
> bptest(Y1 ~ X3 + X4 + X5 + X6 + X7 + X8_proporsi + X9_proporsi + X11 + X13, + varformula = ~ fitted.values(LinearModel.1), studentize=FALSE, data=Dataset)
Breusch-Pagan test
data: Y1 ~ X3 + X4 + X5 + X6 + X7 + X8_proporsi + X9_proporsi + X11 + X13 BP = 13.496, df = 1, p-value = 0.0002391
> dwtest(Y1 ~ X3 + X4 + X5 + X6 + X7 + X8_proporsi + X9_proporsi + X11 + X13, + alternative="two.sided", data=Dataset)
Durbin-Watson test
data: Y1 ~ X3 + X4 + X5 + X6 + X7 + X8_proporsi + X9_proporsi + X11 + X13 DW = 1.3699, p-value = 5.713e-15
alternative hypothesis: true autocorrelation is not 0
> with(Dataset, shapiro.test(residuals.LinearModel.1)) Shapiro-Wilk normality test
data: residuals.LinearModel.1 W = 0.96325, p-value = 5.555e-11
> anova(LinearModel.1) Analysis of Variance Table
Response: Y2
Df Sum Sq Mean Sq F value Pr(>F) X3 1 92.1 92.13 3.4648 0.063195 . X4 1 172.8 172.84 6.5004 0.011041 * X5 1 279.2 279.21 10.5009 0.001262 ** X6 1 1019.1 1019.07 38.3262 1.133e-09 *** X7 1 8.0 8.04 0.3026 0.582497 X8_proporsi 1 106.3 106.27 3.9966 0.046058 * X9_proporsi 1 575.7 575.72 21.6522 4.053e-06 *** X11 1 940.2 940.17 35.3591 4.739e-09 *** X13 1 88.2 88.19 3.3168 0.069091 . Residuals 580 15421.8 26.59 --- Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1 Output GWR
> col.bw <- gwr.sel (Y2 ~ X3 + X4 + X5 + X6 + X7 + X8_proporsi + X9_proporsi + X11