plot.boxcox(x, plot.type = "both", nlabs, conf = .95,...)
"boxcox"
, typically the output
from performing a Box-Cox transformation analysis with
boxcox
.
"lambda"
asks for a plot of
t-values for all terms in the
reduced model over lambda values of Box-Cox tranformations,
"loglik"
asks for a plot of log-likelihoods over lambda values;
"both"
produces both types of plot.
The log-likelihoods of different lambda values from a Box-Cox transformation analysis are plotted, showing which value of lambda maximizes the log-likelihood. A confidence interval for lambda is also plotted. The t-values for all terms in the reduced model associated with a Box-Cox transformation are plotted against lambda values. A two-sided confidence interval for significant effects is shown as well as the choice for the best lambda value.
Box, G.E.P. and D.R. Cox (1964) An analysis of
transformations
(with discussion). J. Royal Statist. Soc. Ser. B, 26:211-246
Box, G. E. P., W. G. Hunter, and J. S. Hunter (1978)
Statistics for Experimenters,
New York: Wiley.
Haaland, P. D. (1989)
Experimental Design in Biotechnology,
New York: Marcel Dekker.
buffer.fac <- fac.aov(buffer.df) buffer.bc <- boxcox(buffer.fac, ~pH*thimer+pH*gent) plot(buffer.bc)