January, It looks like you will need an interaction effect, perhaps g <- lm( response ~ subject + group*time) Please see the ancova function in the HH package. install.packages("HH") ## if necessary library(HH) ?ancova
Rich On Wed, Aug 10, 2011 at 5:15 AM, January Weiner <january.wei...@gmail.com>wrote: > Hello, > > I have a problem with using the following design with ANCOVA in R. > > There are two groups (control + treatment), each with ten subjects. > The subjects show a response that is monitored over time (four time > points). For a single given subject, the response can be analysed with > linear regression with time as the independent variable. > > The question is, how does the response differ between the two groups. > It is to be expected that the slope of the response differs between > the two groups, while the intercept itself is of minor interest. > > I have tried a linear model as in > > g <- lm( response ~ time + subject + group) > > but somehow I think that this is not correct, as it would not show a > difference in the slope of the response. > > Any kind of help would be greatly appreciated. > > -- > January > > ______________________________________________ > R-help@r-project.org mailing list > https://stat.ethz.ch/mailman/listinfo/r-help > PLEASE do read the posting guide > http://www.R-project.org/posting-guide.html<http://www.r-project.org/posting-guide.html> > and provide commented, minimal, self-contained, reproducible code. > [[alternative HTML version deleted]] ______________________________________________ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.