California PBE and Public/Private/Charter: Output

pbe_funding.txt

> joined$Funding <- as.factor(joined$Funding)
> joined$Public.Private <- as.factor(joined$Public.Private)
> 
> summary(joined$Funding)
                aPublic         Directly funded          Locally funded 
                   5153                     382                     172 
Not in CS funding model                 Private 
                      7                    1667 
> summary(joined$Public.Private)
PRIVATE  PUBLIC 
   1649    5732 
> 
> model0 <- cbind(PBE.,Enrollment-PBE.) ~ (1|County) + (1|City) + (1|School)
> model1 <- cbind(PBE.,Enrollment-PBE.) ~ (1|County) + (1|City) + (1|School) + Funding
> 
> fit0 <- glmer(model0, data=joined, family="binomial")
> fit1 <- glmer(model1, data=joined, family="binomial")
> 
> anova(fit0)
Analysis of Variance Table
     Df Sum Sq Mean Sq F value
> anova(fit1)
Analysis of Variance Table
        Df Sum Sq Mean Sq F value
Funding  4 523.87  130.97  130.97
> anova(fit0,fit1)
Data: joined
Models:
fit0: cbind(PBE., Enrollment - PBE.) ~ (1 | County) + (1 | City) + 
fit0:     (1 | School)
fit1: cbind(PBE., Enrollment - PBE.) ~ (1 | County) + (1 | City) + 
fit1:     (1 | School) + Funding
     Df   AIC   BIC logLik deviance  Chisq Chi Df Pr(>Chisq)    
fit0  4 25964 25991 -12978    25956                             
fit1  8 25515 25570 -12749    25499 456.94      4  < 2.2e-16 ***
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
> 
> summary(fit1)
Generalized linear mixed model fit by maximum likelihood (Laplace
  Approximation) [glmerMod]
 Family: binomial  ( logit )
Formula: cbind(PBE., Enrollment - PBE.) ~ (1 | County) + (1 | City) +  
    (1 | School) + Funding
   Data: joined

     AIC      BIC   logLik deviance df.resid 
 25514.8  25569.7 -12749.4  25498.8     6974 

Scaled residuals: 
    Min      1Q  Median      3Q     Max 
-1.4256 -0.6272 -0.1870  0.2439  2.0957 

Random effects:
 Groups Name        Variance Std.Dev.
 School (Intercept) 1.1152   1.0560  
 City   (Intercept) 0.8674   0.9314  
 County (Intercept) 0.8289   0.9104  
Number of obs: 6982, groups:  School, 6978; City, 919; County, 58

Fixed effects:
                               Estimate Std. Error z value Pr(>|z|)    
(Intercept)                    -3.81965    0.13730 -27.819   <2e-16 ***
FundingDirectly funded          1.34812    0.07698  17.513   <2e-16 ***
FundingLocally funded           1.04913    0.11150   9.410   <2e-16 ***
FundingNot in CS funding model  0.98645    0.61510   1.604    0.109    
FundingPrivate                  0.75254    0.04815  15.630   <2e-16 ***
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1