*****************************************************************************

* Semiparametric Geographically Weighted Regression *

* Release 1.0.90 (GWR 4.0.90) *
* 12 May 2015 *
* (Originally coded by T. Nakaya: 1 Nov 2009) *
* *
* Tomoki Nakaya(1), Martin Charlton(2), Chris Brunsdon (2) *
* Paul Lewis (2), Jing Yao (3), A Stewart Fotheringham (4) *
* (c) GWR4 development team *
* (1) Ritsumeikan University, (2) National University of Ireland, Maynooth, *
* (3) University of Glasgow, (4) Arizona State University *
*****************************************************************************

Program began at 2019/12/5 �U�� 01:46:25

*****************************************************************************
Session: Male_COPD
Session control file: D:\�����2019�ҵ{\data\EX8\male_copd.ctl
*****************************************************************************
Data filename: D:\�����2019�ҵ{\data\EX8\Male_exercise.csv
Number of areas/points: 358

Model settings---------------------------------
Model type: Gaussian
Geographic kernel: adaptive bi-square
Method for optimal bandwidth search: Golden section search
Criterion for optimal bandwidth: AICc
Number of varying coefficients: 11
Number of fixed coefficients: 0

Modelling options---------------------------------
Standardisation of independent variables: OFF
Testing geographical variability of local coefficients: On
Local to Global Variable selection: OFF
Global to Local Variable selection: OFF
Prediction at non-regression points: OFF

Variable settings---------------------------------
Area key: field2: TOWNCODE
Easting (x-coord): field19 : X
Northing (y-coord): field20: Y
Cartesian coordinates: Euclidean distance
Dependent variable: field7: copd_Male
Offset variable is not specified
Intercept: varying (Local) intercept
Independent variable with varying (Local) coefficient: field8: Smoking
Independent variable with varying (Local) coefficient: field9: ADI
Independent variable with varying (Local) coefficient: field10: TB_M
Independent variable with varying (Local) coefficient: field11: aborigines
Independent variable with varying (Local) coefficient: field12: Hospitals
Independent variable with varying (Local) coefficient: field13: CO_MEAN
Independent variable with varying (Local) coefficient: field14: NO2_MEAN
Independent variable with varying (Local) coefficient: field15: SO2_MEAN
Independent variable with varying (Local) coefficient: field16: PM10_MEAN
Independent variable with varying (Local) coefficient: field17: elevation_mean
*****************************************************************************

*****************************************************************************
Global regression result
*****************************************************************************
< Diagnostic information >
Residual sum of squares: 35504.543330
Number of parameters: 11
(Note: this num does not include an error variance term for a Gaussian model)
ML based global sigma estimate: 9.958650
Unbiased global sigma estimate: 10.115264
-2 log-likelihood: 2661.644090
Classic AIC: 2685.644090
AICc: 2686.548438
BIC/MDL: 2732.210486
CV: 111.057446
R square: 0.508657
Adjusted R square: 0.493036

Variable Estimate Standard Error t(Est/SE)

-------------------- --------------- --------------- ---------------
Intercept -10.669729 9.449453 -1.129137
Smoking 40.546219 15.291304 2.651587
ADI 0.918983 0.465329 1.974911
TB_M -0.113543 0.038135 -2.977378
aborigines 51.464216 4.491253 11.458765
Hospitals -0.101661 0.041056 -2.476181
CO_MEAN 3.126405 1.363784 2.292448
NO2_MEAN -0.562558 0.242694 -2.317970
SO2_MEAN 0.339483 0.287495 1.180831
PM10_MEAN 0.437593 0.061094 7.162627
elevation_mean -0.011241 0.002688 -4.181345

*****************************************************************************
GWR (Geographically weighted regression) bandwidth selection
*****************************************************************************

Bandwidth search <golden section search>

Limits: 62, 358
Golden section search begins...
Initial values
pL Bandwidth: 62.000 Criterion: 2576.078
p1 Bandwidth: 175.062 Criterion: 2558.664
p2 Bandwidth: 244.938 Criterion: 2586.056
pU Bandwidth: 358.000 Criterion: 2629.257
iter 1 (p1) Bandwidth: 175.062 Criterion: 2558.664 Diff: 69.876
iter 2 (p1) Bandwidth: 131.876 Criterion: 2545.541 Diff: 43.186
iter 3 (p1) Bandwidth: 105.186 Criterion: 2536.139 Diff: 26.690
iter 4 (p2) Bandwidth: 105.186 Criterion: 2536.139 Diff: 16.496
iter 5 (p1) Bandwidth: 105.186 Criterion: 2536.139 Diff: 10.195
iter 6 (p1) Bandwidth: 98.885 Criterion: 2534.917 Diff: 6.301
iter 7 (p2) Bandwidth: 98.885 Criterion: 2534.917 Diff: 3.894
iter 8 (p1) Bandwidth: 98.885 Criterion: 2534.917 Diff: 2.407
iter 9 (p1) Bandwidth: 97.398 Criterion: 2534.888 Diff: 1.487
iter 10 (p2) Bandwidth: 97.398 Criterion: 2534.888 Diff: 0.919
Best bandwidth size 97.000
Minimum AICc 2534.888

*****************************************************************************
GWR (Geographically weighted regression) result
*****************************************************************************
Bandwidth and geographic ranges
Bandwidth size: 97.397692
Coordinate Min Max Range
--------------- --------------- --------------- ---------------
X-coord 88044.944990 341842.834400 253797.889410
Y-coord 2432172.408000 2795490.113000 363317.705000

Diagnostic information
Residual sum of squares: 15472.407266
Effective number of parameters (model: trace(S)): 67.694021
Effective number of parameters (variance: trace(S'S)): 53.348140
Degree of freedom (model: n - trace(S)): 290.305979
Degree of freedom (residual: n - 2trace(S) + trace(S'S)): 275.960098
ML based sigma estimate: 6.574117
Unbiased sigma estimate: 7.487827
-2 log-likelihood: 2364.288428
Classic AIC: 2501.676470
AICc: 2534.888147
BIC/MDL: 2768.245884
CV: 90.489963
R square: 0.785879
Adjusted R square: 0.721992

***********************************************************
<< Geographically varying (Local) coefficients >>
***********************************************************
Estimates of varying coefficients have been saved in the following file.
Listwise output file: D:\�����2019�ҵ{\data\EX8\male_copd_listwise.csv

Summary statistics for varying (Local) coefficients

Variable Mean STD
-------------------- --------------- ---------------
Intercept 2.384599 43.094295
Smoking 16.981980 58.088323
ADI 0.905479 1.497188
TB_M 0.112372 0.251882
aborigines -8.263633 98.324581
Hospitals -0.152638 0.146703
CO_MEAN 8.094892 23.391055
NO2_MEAN 0.340342 1.198675
SO2_MEAN -1.536714 3.878153
PM10_MEAN 0.155062 0.362735
elevation_mean 0.000046 0.016629

Variable Min Max Range

-------------------- --------------- --------------- ---------------
Intercept -58.961153 128.052670 187.013823
Smoking -173.204217 137.664222 310.868439
ADI -2.090485 3.786175 5.876659
TB_M -0.303997 0.693077 0.997074
aborigines -519.804370 288.168772 807.973142
Hospitals -1.310079 0.058099 1.368178
CO_MEAN -51.375511 88.698791 140.074302
NO2_MEAN -5.402598 4.481249 9.883847
SO2_MEAN -15.862512 3.423150 19.285661
PM10_MEAN -1.058290 1.083988 2.142278
elevation_mean -0.056594 0.086138 0.142732

Variable Lwr Quartile Median Upr Quartile

-------------------- --------------- --------------- ---------------
Intercept -24.431332 -14.317681 28.228535
Smoking -11.878444 33.128130 60.729081
ADI -0.161002 0.728930 2.064338
TB_M -0.067023 0.008471 0.284393
aborigines -20.984102 9.834961 33.950836
Hospitals -0.166633 -0.125570 -0.074224
CO_MEAN -0.407626 3.294808 19.853213
NO2_MEAN -0.384225 0.401368 1.279479
SO2_MEAN -2.021572 -0.085201 0.863450
PM10_MEAN -0.094212 0.190567 0.402249
elevation_mean -0.006305 0.000779 0.006033

Variable Interquartile R Robust STD

-------------------- --------------- ---------------
Intercept 52.659867 39.036225
Smoking 72.607526 53.823221
ADI 2.225340 1.649622
TB_M 0.351417 0.260502
aborigines 54.934938 40.722712
Hospitals 0.092409 0.068502
CO_MEAN 20.260839 15.019154
NO2_MEAN 1.663704 1.233287
SO2_MEAN 2.885021 2.138637
PM10_MEAN 0.496461 0.368021
elevation_mean 0.012338 0.009146
(Note: Robust STD is given by (interquartile range / 1.349) )

*****************************************************************************
GWR ANOVA Table
*****************************************************************************
Source SS DF MS F
----------------- ------------------- ---------- --------------- ----------
Global Residuals 35504.543 347.000
GWR Improvement 20032.136 71.040 281.984
GWR Residuals 15472.407 275.960 56.068 5.029367

*************************************************************************
Geographical variability tests of local coefficients
*************************************************************************
Variable F DOF for F test DIFF of Criterion
-------------------- ------------------ ---------------- -----------------
Intercept 41.738704 5.010 290.306 -179.068348
Smoking 24.610077 5.631 290.306 -122.731229
ADI 2.390093 7.237 290.306 0.991056
TB_M 4.277813 6.865 290.306 -13.877566
aborigines 16.637790 5.246 290.306 -78.262181
Hospitals 0.453886 3.475 290.306 8.619077
CO_MEAN 2.546534 3.917 290.306 -0.210010
NO2_MEAN 201.366969 4.889 290.306 -514.895765
SO2_MEAN 1.557026 4.445 290.306 5.026929
PM10_MEAN 97.830832 4.977 290.306 -337.513722
elevation_mean 4.718325 5.497 290.306 -14.047453
-------------------- ------------------ ---------------- -----------------
Note: positive value of diff-Criterion (AICc, AIC, BIC/MDL or CV) suggests no
spatial variability in terms of model selection criteria.
F test: in case of no spatial variability, the F statistics follows the F
distribution of DOF for F test.

*****************************************************************************
Program terminated at 2019/12/5 �U�� 01:47:03