> ## sec 2.6 Wear Exp't
> #
> data<-read.table("wear.dat", h=T, skip=2)  
> data[2,3] <- "D"   # fix a typo: lower case d shound be upper case D
> data
   row col material wear
1    1   1        C  235
2    1   2        D  236
3    1   3        B  218
4    1   4        A  268
5    2   1        A  251
6    2   2        B  241
7    2   3        D  227
8    2   4        C  229
9    3   1        D  234
10   3   2        C  273
11   3   3        A  274
12   3   4        B  226
13   4   1        B  195
14   4   2        A  270
15   4   3        C  230
16   4   4        D  225
> g<- lm(wear ~ as.factor(row) + as.factor(col) + material, data = data)
> anova(g)  # table 2.20
Analysis of Variance Table

Response: wear
               Df Sum Sq Mean Sq F value    Pr(>F)    
as.factor(row)  3  986.5   328.8  5.3687 0.0390130 *  
as.factor(col)  3 1468.5   489.5  7.9918 0.0161685 *  
material        3 4621.5  1540.5 25.1510 0.0008498 ***
Residuals       6  367.5    61.3                      
---
Signif. codes:  0 `***' 0.001 `**' 0.01 `*' 0.05 `.' 0.1 ` ' 1 
> summary(g) # part of table 2.21

Call:
lm(formula = wear ~ as.factor(row) + as.factor(col) + material, 
    data = data)

Residuals:
   Min     1Q Median     3Q    Max 
-9.750 -2.250  0.250  3.687  8.000 

Coefficients:
                Estimate Std. Error t value Pr(>|t|)    
(Intercept)      254.750      6.187  41.174 1.37e-08 ***
as.factor(row)2   -2.250      5.534  -0.407 0.698423    
as.factor(row)3   12.500      5.534   2.259 0.064657 .  
as.factor(row)4   -9.250      5.534  -1.671 0.145658    
as.factor(col)2   26.250      5.534   4.743 0.003180 ** 
as.factor(col)3    8.500      5.534   1.536 0.175454    
as.factor(col)4    8.250      5.534   1.491 0.186608    
materialB        -45.750      5.534  -8.267 0.000169 ***
materialC        -24.000      5.534  -4.337 0.004892 ** 
materialD        -35.250      5.534  -6.370 0.000703 ***
---
Signif. codes:  0 `***' 0.001 `**' 0.01 `*' 0.05 `.' 0.1 ` ' 1 

Residual standard error: 7.826 on 6 degrees of freedom
Multiple R-Squared: 0.9506,	Adjusted R-squared: 0.8766 
F-statistic: 12.84 on 9 and 6 DF,  p-value: 0.002828 

> 
> g<- lm(wear ~ material, data = data)
> anova(g)  # table 2.22
Analysis of Variance Table

Response: wear
          Df Sum Sq Mean Sq F value   Pr(>F)   
material   3 4621.5  1540.5  6.5495 0.007155 **
Residuals 12 2822.5   235.2                    
---
Signif. codes:  0 `***' 0.001 `**' 0.01 `*' 0.05 `.' 0.1 ` ' 1