Summarize an Analysis of Variance Model
Summarize an analysis of variance model.
"summary"(object, intercept = FALSE, split, expand.split = TRUE, keep.zero.df = TRUE, ...)"summary"(object, ...)
- An object of class
- logical: should intercept terms be included?
- an optional named list, with names corresponding to terms in the model. Each component is itself a list with integer components giving contrasts whose contributions are to be summed.
- logical: should the split apply also to interactions involving the factor?
- logical: should terms with no degrees of freedom be included?
- Arguments to be passed to or from other methods,
summary.aovlistincluding those for
An object of class
"summary.aovlist"respectively.For fits with a single stratum the result will be a list of ANOVA tables, one for each response (even if there is only one response): the tables are of class
"anova"inheriting from class
"data.frame". They have columns
"Mean Sq", as well as
"Pr(>F)"if there are non-zero residual degrees of freedom. There is a row for each term in the model, plus one for
"Residuals"if there are any.For multistratum fits the return value is a list of such summaries, one for each stratum.
The use of
expand.split = TRUE is little tested: it is always
possible to set it to
FALSE and specify exactly all
the splits required.
## For a simple example see example(aov) # Cochran and Cox (1957, p.164) # 3x3 factorial with ordered factors, each is average of 12. CC <- data.frame( y = c(449, 413, 326, 409, 358, 291, 341, 278, 312)/12, P = ordered(gl(3, 3)), N = ordered(gl(3, 1, 9)) ) CC.aov <- aov(y ~ N * P, data = CC , weights = rep(12, 9)) summary(CC.aov) # Split both main effects into linear and quadratic parts. summary(CC.aov, split = list(N = list(L = 1, Q = 2), P = list(L = 1, Q = 2))) # Split only the interaction summary(CC.aov, split = list("N:P" = list(L.L = 1, Q = 2:4))) # split on just one var summary(CC.aov, split = list(P = list(lin = 1, quad = 2))) summary(CC.aov, split = list(P = list(lin = 1, quad = 2)), expand.split = FALSE)
Looks like there are no examples yet.