Incomplete Factorial design
On Fri, 6 Feb 2004, Simon Fear wrote:
One could also fit fit <- lm(y~A*B - 1, data.frame(y=..., A=..., B=..,) which will give a direct a:b term (as the negative of the intercept in Spenser's formulation). Arguably this is more natural in a setting where there is no placebo so that an intercept term has a less obvious interpretation.
I would have though the natural analysis was to compare A+B to B alone and A+B to A alone with two separate t.tests, and power the analysis for these. It's not really a factorial design at all. -thomas