Content Review 4

library(tidyverse)

Registered S3 methods overwritten by 'dbplyr':
  method         from
  print.tbl_lazy     
  print.tbl_sql      
-- Attaching packages --------------------------------------- tidyverse 1.3.0 --
v ggplot2 3.3.2     v dplyr   1.0.2
v tibble  3.0.3     v stringr 1.4.0
v tidyr   1.1.1     v forcats 0.5.0
v purrr   0.3.4     
-- Conflicts ------------------------------------------ tidyverse_conflicts() --
x tidyr::expand() masks Matrix::expand()
x dplyr::filter() masks stats::filter()
x dplyr::lag()    masks stats::lag()
x tidyr::pack()   masks Matrix::pack()
x tidyr::unpack() masks Matrix::unpack()

library(psych)

Attaching package: 㤼㸱psych㤼㸲

The following objects are masked from 㤼㸱package:ggplot2㤼㸲:

    %+%, alpha

library(lme4)

peer_scale <- schoolsmoke %>%
  select(., d,
         d2,
         d3,
         d4,
         d5)
alpha(peer_scale)

Some items were negatively correlated with the total scale and probably 
should be reversed.  
To do this, run the function again with the 'check.keys=TRUE' option

Some items ( d3 d4 ) were negatively correlated with the total scale and 
probably should be reversed.  
To do this, run the function again with the 'check.keys=TRUE' option

NaNs produced

Reliability analysis   
Call: alpha(x = peer_scale)

 

 lower alpha upper     95% confidence boundaries
-0.15 -0.07 0.01 

 Reliability if an item is dropped:

 Item statistics 

Non missing response frequency for each item
      0    1    2    3    4 miss
d  0.10 0.22 0.38 0.20 0.10    0
d2 0.11 0.18 0.43 0.18 0.09    0
d3 0.10 0.23 0.38 0.18 0.10    0
d4 0.10 0.20 0.40 0.20 0.10    0
d5 0.10 0.20 0.40 0.20 0.10    0

model.null <- lmer(thk ~ (1|school), REML=FALSE, data=schoolsmoke)
summary(model.null)

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

     AIC      BIC   logLik deviance df.resid 
  4833.0   4849.1  -2413.5   4827.0     1597 

Scaled residuals: 
    Min      1Q  Median      3Q     Max 
-1.9039 -0.7734  0.0693  0.9240  1.7430 

Random effects:
 Groups   Name        Variance Std.Dev.
 school   (Intercept) 0.09438  0.3072  
 Residual             1.16219  1.0780  
Number of obs: 1600, groups:  school, 28

Fixed effects:
            Estimate Std. Error       df t value Pr(>|t|)    
(Intercept)  2.60750    0.06538 25.83292   39.88   <2e-16 ***
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

lmerTest::rand(model.null)

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

Model:
thk ~ (1 | school)
             npar  logLik    AIC   LRT Df Pr(>Chisq)    
<none>          3 -2413.5 4833.0                        
(1 | school)    2 -2445.6 4895.2 64.16  1  1.147e-15 ***
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

model.1 <- lmer(thk ~ prethk + (1|school), REML = FALSE, data = schoolsmoke)
summary(model.1)

Linear mixed model fit by maximum likelihood . t-tests use
  Satterthwaite's method [lmerModLmerTest]
Formula: thk ~ prethk + (1 | school)
   Data: schoolsmoke

     AIC      BIC   logLik deviance df.resid 
  4733.5   4755.0  -2362.7   4725.5     1596 

Scaled residuals: 
     Min       1Q   Median       3Q      Max 
-2.12273 -0.82727  0.03082  0.83756  2.15165 

Random effects:
 Groups   Name        Variance Std.Dev.
 school   (Intercept) 0.07519  0.2742  
 Residual             1.09321  1.0456  
Number of obs: 1600, groups:  school, 28

Fixed effects:
             Estimate Std. Error        df t value Pr(>|t|)    
(Intercept) 2.152e+00  7.414e-02 6.142e+01   29.02   <2e-16 ***
prethk      2.175e-01  2.122e-02 1.599e+03   10.25   <2e-16 ***
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Correlation of Fixed Effects:
       (Intr)
prethk -0.598

model.2 <- lmer(thk ~ prethk + cc + gprethk + (1|school), REML = FALSE, data = schoolsmoke)
summary(model.2)

Linear mixed model fit by maximum likelihood . t-tests use
  Satterthwaite's method [lmerModLmerTest]
Formula: thk ~ prethk + cc + gprethk + (1 | school)
   Data: schoolsmoke

     AIC      BIC   logLik deviance df.resid 
  4712.6   4744.9  -2350.3   4700.6     1594 

Scaled residuals: 
     Min       1Q   Median       3Q      Max 
-2.23332 -0.79567  0.02374  0.79254  2.16704 

Random effects:
 Groups   Name        Variance Std.Dev.
 school   (Intercept) 0.01734  0.1317  
 Residual             1.09334  1.0456  
Number of obs: 1600, groups:  school, 28

Fixed effects:
             Estimate Std. Error        df t value Pr(>|t|)    
(Intercept) 1.076e+00  2.548e-01 3.024e+01   4.224 0.000203 ***
prethk      2.126e-01  2.138e-02 1.571e+03   9.944  < 2e-16 ***
cc          4.308e-01  7.554e-02 2.330e+01   5.702 7.94e-06 ***
gprethk     4.183e-01  1.193e-01 3.387e+01   3.507 0.001301 ** 
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Correlation of Fixed Effects:
        (Intr) prethk cc    
prethk   0.000              
cc      -0.288  0.000       
gprethk -0.963 -0.179  0.148