Table 4.8 shows the number of train miles (in millions) and the number of collisions involving British Rail passenger trains between 1970 and 1984. Is it plausible that the collision counts are independent Poisson variates with constant rate over the 14-year period? Respond by testing the goodness of fit of a GLM for collision rates that contains only an intercept term.

Transcribed Image Text:

Table 4.8 Year Collisions Miles Year Collisions Miles 1970 1971 1972 1973 3647 281 1977 4 264 276 1978 1 267 268 1979 7 265 269 1980 3 267 1974 6 281 1981 5 260 1975 1976 22 2 271 1982 6 231 2 265 1983 1 249 Source: British Dept. of Transport; see also C. Chatfield, Problem Solving: A Statistician's Guide (London: Chapman and Hall, 1988), p. 86.