Doug's modification

From InterSciWiki

summary(col.lm)

Call:lagsarlm(formula = femsubs ~ fishimp + huntimp + pathstress + rainfall + polygamy + eboysxp + fixres + landtrans + polinteg + socstrat, data = ffd, listw = wmat, quiet = FALSE)

Residuals:

     Min        1Q    Median        3Q       Max 

-31.12551 -9.83855 0.10200 8.82163 41.25362

Type: lag Coefficients: (asymptotic standard errors)

            Estimate Std. Error z value  Pr(>|z|)

(Intercept) 54.219673 9.625468 5.6329 1.772e-08 fishimp -0.166648 0.064963 -2.5653 0.0103092 huntimp -0.375657 0.079325 -4.7357 2.183e-06 pathstress -1.531668 0.404876 -3.7831 0.0001549 rainfall -2.118356 0.660463 -3.2074 0.0013395 polygamy 1.405035 0.684845 2.0516 0.0402076 eboysxp 4.195995 1.962018 2.1386 0.0324671 fixres -1.391853 0.879172 -1.5831 0.1133896 landtrans -2.110776 1.155823 -1.8262 0.0678186 polinteg 2.097514 1.317630 1.5919 0.1114110 socstrat -2.229963 1.123288 -1.9852 0.0471212

Rho: 0.002928 LR test value: 2.7741 p-value: 0.095803 Asymptotic standard error: 0.0017225 z-value: 1.6999 p-value: 0.089158 Wald statistic: 2.8895 p-value: 0.089158

Log likelihood: -705.1941 for lag model ML residual variance (sigma squared): 185.08, (sigma: 13.604) Number of observations: 175 Number of parameters estimated: 13 AIC: 1436.4, (AIC for lm: 1437.2) LM test for residual autocorrelation test value: 0.0027596 p-value: 0.9581