stat.anova {base} | R Documentation |
This is a utility function, used in lm
and
glm
methods for anova(..., test != NULL)
and should not be used by the average user.
stat.anova(table, test = c("Chisq", "F", "Cp"), scale, df.scale, n)
table |
numeric matrix as results from
|
test |
a character string, matching one of |
scale |
a weighted residual sum of squares. |
df.scale |
degrees of freedom corresponding to scale. |
n |
number of observations. |
A matrix which is the original table
, augmented by a column
of test statistics, depending on the test
argument.
anova.lm
, anova.glm
.
##-- Continued from ``?glm'':
print(ag <- anova(glm.D93))
stat.anova(ag$table, test = "Cp",
scale = sum(resid(glm.D93, "pearson")^2)/4, df = 4, n = 9)