[Rd] Orthogonal polynomial ANOVA or polynomial regression?
pdalgd at gmail.com
Thu Mar 24 17:09:45 CET 2011
On Mar 24, 2011, at 16:53 , Dominick Samperi wrote:
> I have not been able to find R tools that permit an orthogonal polynomial
> ANOVA analysis: single degree of freedom F-test comparisons including
> L, Q, C, etc. terms. Do such tools exist?
> I guess you can accomplish something similar by doing straightforward
> polynomial regression and removing powers manually, combined with
> ANOVA model comparisons.
(Why R-devel? This is a plain R-help thing.)
Look up contr.poly(), and poly().
Notice that for unbalanced designs, you still need to remove terms one at a time.
Center for Statistics, Copenhagen Business School
Solbjerg Plads 3, 2000 Frederiksberg, Denmark
Email: pd.mes at cbs.dk Priv: PDalgd at gmail.com
More information about the R-devel