Latin square experiment for testing fungicide

data("goulden.latin")

Format

A data frame with 25 observations on the following 4 variables.

trt: treatment factor, 5 levels
yield: yield
row: row
col: column

Details

Five treatments were tested to control stem rust in wheat. Treatment codes and descriptions: A = Dusted before rains. B = Dusted after rains. C = Dusted once each week. D = Drifting, once each week. E = Not dusted.

Source

Cyrus H. Goulden (1952). Methods of Statistical Analysis, 2nd ed. Page 216.

Examples

# \dontrun{

library(agridat)
library(agridat)
data(goulden.latin)
dat <- goulden.latin


libs(desplot)
desplot(dat, yield ~ col*row,
        text=trt, cex=1, # aspect unknown
        main="goulden.latin")


# Matches Goulden.
m1 <- lm(yield~ trt + factor(row) + factor(col), data=dat)
anova(m1)
#> Analysis of Variance Table
#> 
#> Response: yield
#>             Df  Sum Sq Mean Sq F value    Pr(>F)    
#> trt          4 196.608  49.152 21.0321 2.366e-05 ***
#> factor(row)  4  46.668  11.667  4.9923   0.01328 *  
#> factor(col)  4  14.020   3.505  1.4998   0.26343    
#> Residuals   12  28.044   2.337                      
#> ---
#> Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1

# }