Seed germination data
A classic toy data set, “from research conducted by microbiologist Dr P. Whitney of Surrey University. A batch of tiny seeds is brushed onto a plate covered with a certain extract at a given dilution. The numbers of germinated and ungerminated seeds are subsequently counted” (Crowder, 1978). Two seed types and two extracts are here considered in a 2x2 factorial design.
data("seeds")The data frame includes 21 observations on the following variables:
Factor for replication;
Seed type, a factor with two levels O73 and O75;
Root extract, a factor with two levels Bean and Cucumber;
Number of seeds that germinated;
Total number of seeds tested
Crowder (1978), Table 3.
Crowder, M.J., 1978. Beta-binomial anova for proportions. Appl. Statist., 27, 34-37.
Y. Lee and J. A. Nelder. 1996. Hierarchical generalized linear models (with discussion). J. R. Statist. Soc. B, 58: 619-678.
# An extended quasi-likelihood (EQL) fit as considered by Lee & Nelder (1996):
data("seeds")
fitme(cbind(r,n-r)~seed*extract+(1|plate),family=binomial(),
rand.family=Beta(),
method="EQL-", # see help("method") for difference with "EQL+" method
data=seeds)Please choose more modern alternatives, such as Google Chrome or Mozilla Firefox.