Module 3

plot(cars)

library(haven)
hsbmerged <- read_dta("Multilevel Modeling/hsbmerged.dta")
View(hsbmerged)

library(tidyverse)
library(lme4)
library(lmerTest)
library(Hmisc)

summary(model.null)

Linear mixed model fit by maximum likelihood . t-tests use
  Satterthwaite's method [lmerModLmerTest]
Formula: readach ~ (1 | schoolid)
   Data: hsbmerged

     AIC      BIC   logLik deviance df.resid 
 50395.7  50416.4 -25194.9  50389.7     7182 

Scaled residuals: 
    Min      1Q  Median      3Q     Max 
-4.4250 -0.5740  0.0116  0.5943  4.3166 

Random effects:
 Groups   Name        Variance Std.Dev.
 schoolid (Intercept) 22.94    4.789   
 Residual             61.06    7.814   
Number of obs: 7185, groups:  schoolid, 160

Fixed effects:
            Estimate Std. Error       df t value Pr(>|t|)    
(Intercept)  54.6081     0.3906 160.4370   139.8   <2e-16 ***
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

rand(model.null)

ANOVA-like table for random-effects: Single term deletions

Model:
readach ~ (1 | schoolid)
               npar logLik   AIC    LRT Df Pr(>Chisq)    
<none>            3 -25195 50396                         
(1 | schoolid)    2 -26126 52255 1861.8  1  < 2.2e-16 ***
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

model.null2 <- lmer(ses~(1|schoolid), REML=FALSE,data=hsbmerged)
summary(model.null2)

Linear mixed model fit by maximum likelihood . t-tests use
  Satterthwaite's method [lmerModLmerTest]
Formula: ses ~ (1 | schoolid)
   Data: hsbmerged

     AIC      BIC   logLik deviance df.resid 
 15047.0  15067.7  -7520.5  15041.0     7182 

Scaled residuals: 
    Min      1Q  Median      3Q     Max 
-5.4793 -0.6724  0.0179  0.7065  4.2632 

Random effects:
 Groups   Name        Variance Std.Dev.
 schoolid (Intercept) 0.1597   0.3997  
 Residual             0.4462   0.6680  
Number of obs: 7185, groups:  schoolid, 160

Fixed effects:
              Estimate Std. Error         df t value Pr(>|t|)
(Intercept)  -0.005674   0.032647 160.189296  -0.174    0.862

rand(model.null2)

ANOVA-like table for random-effects: Single term deletions

Model:
ses ~ (1 | schoolid)
               npar  logLik   AIC    LRT Df Pr(>Chisq)    
<none>            3 -7520.5 15047                         
(1 | schoolid)    2 -8403.4 16811 1765.9  1  < 2.2e-16 ***
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1