ResultsEff0001
From InterSciWiki
- Wald, Abraham. 1943. Tests of Statistical Hypotheses Concerning Several Parameters When the Number of Observations is Large. Transactions of the American Mathematical Society 54: 426-482.
- #Read in the dbf format weight matrices-the dbf file is 186x186 (no row names)
- #Comment the matrix you do NOT want to use
- lds<-read.dbf("langmat.dbf") #language phylogeny
- #lds<-read.dbf("distmat.dbf") #great circle distance
- #convert to matrix
- lds<-as.matrix(lds)
- #take a quick look at the upper left hand corner to see that it is OK
- lds[1:5,1:5]
X1 X2 X3 X4 X5 1 0 3 1 1 1 2 3 0 1 1 1 3 1 1 0 3 3 4 1 1 3 0 3 5 1 1 3 3 0
- #read in SCCS data. It is in STATA format, since this is numeric--there are problems with the SPSS version,
- #since R imports the value labels from SPSS and the variables become non-numeric
- gg<-read.dta("SCCS_stata.dta")
- length(gg[,1]) #the number of observations
[1] 186
- length(gg[1,]) #the number of variables
[1] 1849
- #create a data frame containing our variables, also give the variables names
- df<-data.frame(femsubs=gg$v826,fishimp=gg$v816,huntimp=gg$v817,pathstress=gg$v1260,rainfall=gg$v855,polygamy=gg$v79,eboysxp=gg$v353,fixres=gg$v150,landtrans=gg$v154,polinteg=gg$v157,socstrat=gg$v158)
- #since the estimation doesn't work with missing values, here we identify all observations with non-missing values
- kk<-as.matrix(df)
- oo<-matrix(1,length(kk[1,]),1)
- tm<-kk%*%oo
- rr<-which(tm[,1]!="NA")
- #here we restrict the weight matrix and data to include only non-missing values
- wmat<-mat2listw(lds[rr,rr])
- ffd<-df[rr,]
- length(df[,1]) #number of observations before dropping those with missing values
[1] 186
- length(ffd[,1]) #number of observations after dropping those with missing values
[1] 180
- summary(ffd)
femsubs fishimp huntimp pathstress Min. : 0.00 Min. : 0.00 Min. : 0.00 Min. : 7.00 1st Qu.:21.00 1st Qu.: 5.00 1st Qu.: 5.00 1st Qu.: 9.00 Median :32.50 Median : 5.00 Median : 5.00 Median :12.00 Mean :32.74 Mean :15.89 Mean :15.28 Mean :12.55 3rd Qu.:42.25 3rd Qu.:25.00 3rd Qu.:25.00 3rd Qu.:15.25 Max. :79.00 Max. :90.00 Max. :80.00 Max. :21.00 rainfall polygamy eboysxp fixres Min. :1.000 Min. :1.000 Min. :2.000 Min. :1.000 1st Qu.:1.750 1st Qu.:3.000 1st Qu.:3.000 1st Qu.:2.000 Median :3.000 Median :3.000 Median :3.000 Median :5.000 Mean :3.278 Mean :3.128 Mean :3.367 Mean :3.722 3rd Qu.:5.000 3rd Qu.:4.000 3rd Qu.:3.250 3rd Qu.:5.000 Max. :7.000 Max. :4.000 Max. :5.000 Max. :5.000 landtrans polinteg socstrat Min. :1.000 Min. :1.000 Min. :1.000 1st Qu.:1.000 1st Qu.:2.000 1st Qu.:1.000 Median :1.000 Median :3.000 Median :2.000 Mean :1.783 Mean :2.944 Mean :2.439 3rd Qu.:2.000 3rd Qu.:4.000 3rd Qu.:4.000 Max. :5.000 Max. :5.000 Max. :5.000
- #We estimate a spatial lag model
- col.lm<-lagsarlm(femsubs~fishimp+huntimp+pathstress+rainfall+polygamy+eboysxp+fixres+landtrans+polinteg+socstrat,
- + data=ffd,wmat,quiet=FALSE)
Spatial lag model Jacobian calculated using neighbourhood matrix eigenvalues Computing eigenvalues ... (eigen) rho: -0.2003254 function value: -1196.641 (eigen) rho: -0.1181220 function value: -1063.774 (eigen) rho: -0.06731753 function value: -955.0824 (eigen) rho: -0.03591862 function value: -858.619 (eigen) rho: -0.01651303 function value: -780.7875 (eigen) rho: -0.004519716 function value: -736.6456 (eigen) rho: 0.002892561 function value: -724.8947 (eigen) rho: 0.006528 function value: -726.4253 (eigen) rho: 0.003551092 function value: -724.7921 (eigen) rho: 0.00362369 function value: -724.791 (eigen) rho: 0.003625334 function value: -724.791 (eigen) rho: 0.003625231 function value: -724.791 (eigen) rho: 0.003625226 function value: -724.791 (eigen) rho: 0.003625236 function value: -724.791 (eigen) rho: 0.003625231 function value: -724.791
- #this next displays parameter estimates and diagnostics for the spatial lag model
- 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
-31.0141 -9.7284 -1.0099 9.3039 41.2642
Type: lag
Coefficients: (asymptotic standard errors)
Estimate Std. Error z value Pr(*|z|)
(Intercept) 42.629091 9.235650 4.6157 3.918e-06
fishimp -0.178894 0.064200 -2.7865 0.0053277
huntimp -0.390293 0.079525 -4.9078 9.209e-07
pathstress -1.359711 0.382740 -3.5526 0.0003815
rainfall -1.970160 0.640417 -3.0764 0.0020954
polygamy 2.557231 1.682321 1.5201 0.1284956
eboysxp 4.902086 1.706921 2.8719 0.0040803
fixres -1.348417 0.876313 -1.5387 0.1238681
landtrans -1.720732 1.153186 -1.4922 0.1356585
polinteg 2.203866 1.305567 1.6881 0.0914011
socstrat -2.667423 1.103580 -2.4171 0.0156463
Rho: 0.0036252 LR test value: 4.9754 p-value: 0.02571
Asymptotic standard error: 0.0015828 z-value: 2.2904 p-value: 0.021995
Wald statistic: 5.2462 p-value: 0.021995
Log likelihood: -724.791 for lag model ML residual variance (sigma squared): 183.87, (sigma: 13.56) Number of observations: 180 Number of parameters estimated: 13 AIC: 1475.6, (AIC for lm: 1478.6) LM test for residual autocorrelation test value: 0.14304 p-value: 0.70528
The model evaluated regression coefficients predicting female contribution to subsistence
- femsubs~fishimp+huntimp+pathstress+rainfall+polygamy+eboysxp+fixres+landtrans+polinteg+socstrat
- variables having .15 > p > .10: polygamy fixres landtrans
- variables having .10 > p > .05: polinteg (+)
- variables having .05 > p > .01: socstrat (-)
- variables having .01 > p >.001: rainfall eboysxp (+) fishimp (-)
- variables having .001>p: hunting path(ogen)stress (-)
Residual autocorrelation is nonsignificant
