> triglyc.mod1 <- aov(serum ~ day*machine)
> summary(triglyc.mod1)
            Df  Sum Sq Mean Sq F value    Pr(>F)    
day          3 1334.46  444.82 24.8569 2.907e-06 ***
machine      3 1647.28  549.09 30.6836 7.192e-07 ***
day:machine  9  786.04   87.34  4.8805  0.002936 ** 
Residuals   16  286.32   17.90                      
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1 
> 
> library(lme4)
> 
> triglyc.mod2 <- lmer(serum~1 + (1|day) + (1|machine) + (1|day:machine))
> summary(triglyc.mod2)
Linear mixed model fit by REML 
Formula: serum ~ 1 + (1 | day) + (1 | machine) + (1 | day:machine) 
   AIC   BIC logLik deviance REMLdev
 225.0 232.4 -107.5    220.2   215.0
Random effects:
 Groups      Name        Variance Std.Dev.
 day:machine (Intercept) 34.721   5.8925  
 machine     (Intercept) 57.719   7.5973  
 day         (Intercept) 44.685   6.6847  
 Residual                17.895   4.2303  
Number of obs: 32, groups: day:machine, 16; machine, 4; day, 4

Fixed effects:
            Estimate Std. Error t value
(Intercept)  141.184      5.322   26.53