case1402 {Sleuth2}

Effect of Ozone, SO2 and Drought on Soybean Yield

Description

In a completely randomized design with a 2x3x5 factorial treatment structure, researchers randomly assigned one of 30 treatment combinations to open-topped growing chambers, in which two soybean cultivars were planted. The responses for each chamber were the yields of the two types of soybean.

Usage

case1402

Format

A data frame with 30 observations on the following 5 variables.

Stress

a factor indicating treatment, with two levels "Well-watered" and "Stressed"

SO2

a quantitative treatment with three levels 0, 0.02 and 0.06

O3

a quantitative treatment with five levels 0.02, 0.05, 0.07, 0.08 and 0.10

Forrest

the yield of the Forrest cultivar of soybean (in kg/ha)

William

the yield of the Williams cultivar of soybean (in kg/ha)

Source

Ramsey, F.L. and Schafer, D.W. (2002). The Statistical Sleuth: A Course in Methods of Data Analysis (2nd ed), Duxbury.

References

Heggestad, H.E. and Lesser, V.M. (1990). Effects of Chronic Doses of Sulfur Dioxide, Ozone, and Drought on Yields and Growth of Soybeans Under Field Conditions, Journal of Environmental Quality 19: 488–495.

Examples

str(case1402)

plot(Forrest ~ O3,  case1402, log="y", pch=ifelse(Stress=="Stressed",19,21))
plot(Forrest ~ SO2, case1402, log="y", pch=ifelse(Stress=="Stressed",19,21))

fitbig <- lm(log(Forrest) ~  O3*SO2*Stress, case1402)
# Residual plot does not indicate any problem.
plot(fitbig) 
# The 3-factor interaction is not statistically significant.
anova(fitbig)  
# Drop the three-factor interaction
fit2 <- update(fitbig, ~ . - O3:SO2:Stress) 
anova(fit2)

fitadditive <- lm(log(Forrest) ~ O3 + SO2 + Stress, case1402)
summary(fitadditive)