| ACF1 {DAAG} | R Documentation |
Numbers of aberrant crypt foci (ACF) in the section 1 of the colons of 22 rats subjected to a single dose of the carcinogen azoxymethane (AOM), sacrificed at 3 different times.
ACF1
This data frame contains the following columns:
Ranjana P. Bird, Faculty of Human Ecology, University of Manitoba, Winnipeg, Canada.
E.A. McLellan, A. Medline and R.P. Bird. Dose response and proliferative characteristics of aberrant crypt foci: putative preneoplastic lesions in rat colon. Carcinogenesis, 12(11): 2093-2098, 1991.
sapply(split(ACF1$count,ACF1$endtime),var)
plot(count ~ endtime, data=ACF1, pch=16)
pause()
print("Poisson Regression - Example 8.3")
ACF.glm0 <- glm(formula = count ~ endtime, family = poisson, data = ACF1)
summary(ACF.glm0)
# Is there a quadratic effect?
pause()
ACF.glm <- glm(formula = count ~ endtime + I(endtime^2),
family = poisson, data = ACF1)
summary(ACF.glm)
# But is the data really Poisson? If not, try quasipoisson:
pause()
ACF.glm <- glm(formula = count ~ endtime + I(endtime^2),
family = quasipoisson, data = ACF1)
summary(ACF.glm)