Skip to main content

Table 4 Regression Results from Three Models, n = 6455 PCSA-level observations

From: Spatial analysis of elderly access to primary care services

  OLS Model1 Spatial Lag Model2 IV Spatial Lag Model3
Variable Coeff St. Error Coeff St. Error Coeff St. Error
XMEN -198.82* 15.636 -119.50* 12.728 -142.79* 14.530
XDUAL -359.43* 18.393 -293.70* 12.131 -284.88* 15.777
XBLACK -33.69* 4.601 -22.69* 3.283 -21.65* 3.948
XOTHER -40.55 17.595 -11.49 7.397 -61.30* 12.695
XDIED 672.79* 55.498 636.97* 38.625 562.14* 47.204
XOLDER -648.11* 23.509 -482.83* 16.024 -476.86* 21.749
RISK 12.83 5.529 0.99 5.458 5.34 4.709
HIQUINT 845.10* 31.274 678.99* 20.579 661.21* 27.717
XDIAB 50.47* 9.773 43.41* 4.857 46.42* 8.126
(1) XELDERPOV 24.45 18.154 21.58 14.155 21.25 15.224
POVRATIO -2.36* 0.910 -0.64 0.834 -1.11 0.780
(2) XTRURELD -4.89* 1.972 -1.13 1.870 -0.99 1.716
RURATIO 0.09 0.076 0.14 0.087 0.04 0.068
(1)*(2) 84.67* 18.235 33.17 14.061 43.29* 15.591
XLIVALONE -3.24 10.477 -11.31 8.078 4.39 8.970
XLCOMUTE 72.25* 6.889 43.14* 5.772 56.98* 6.039
XPOORNE -90.97* 19.722 -76.49* 9.753 -29.80 14.875
PDENSITY 0.00* 0.000 0.00* 7.557 0.00* 0.000
BEDREHAB -0.08* 0.016 -0.08* 0.020 -0.08* 0.014
VISITS -0.50 0.212 -0.54* 0.128 -0.63* 0.174
TOTDOCS 1.79 0.819 0.49 0.626 0.92 0.725
ALT_DOC -87.09* 8.399 -31.05* 7.246 -38.23* 7.780
(3) IMG_RATIO 4.42* 0.993 3.68* 0.577 4.73* 0.841
(1)*(2)*(3) -23.64* 7.593 -19.33* 4.273 -22.40* 6.270
MCPENE00 -5.98 3.289 -10.28* 3.174 -7.52* 2.909
CINCREASE -0.62 0.786 -1.22 0.826 -1.09 0.690
XHMO00 -13.62* 3.147 -3.04 2.864 -4.91 2.748
XHMODIF -2.36* 0.842 -2.45* 0.666 -2.97* 0.717
XPPO00 -38.77* 5.049 -22.09* 4.714 -23.20* 4.405
XPPODIF 20.50* 3.505 14.83* 3.115 11.51* 2.998
SHRLARG3 -0.07* 0.021 -0.02 0.020 -0.06* 0.018
PRICE00A 0.02* 0.004 0.01* 0.003 0.01* 0.004
ECOV97_9 -0.32* 0.052 -0.12 0.047 -0.19* 0.048
W_ACSC    0.42* 0.012 0.33* 0.021
N 6,475 6,475 6,475
GOF measure 4 0.7743882 0.774075 0.775249
Log Likelihood    -28748.9   
  1. 1Model estimated using SYSTAT with heteroskedasticity-corrected standard errors. 2Model estimated using GeoDa. 3Model estimated using PYTHON programming in R, with heteroskedasticity-corrected standard errors. 4 To make this comparable across models, we report the correlation between observed ACSC rates and predicted values from each model. For the lag or IV model, predictions properly account for endogeneity of the lag term or for the degrees of freedom lost in instrumentation. *These coefficients are statistically significant at the 0.01 level.