Calculate Predicted Means for Linear Models

This package provides functions to diagnose and make inferences from various linear models, such as those obtained from 'aov', 'lm', 'glm', 'gls', 'lme', and 'lmer'. Inferences include predicted means and standard errors, contrasts, multiple comparisons, permutation tests and graphs.


Changelog for 'predictmeans' package

0.98 Corrected colour setting for 'PMplot' function Added an option 'bkplot' to control output of back transformed means plot in 'predictmeans' function Added Letter-based representation of pairwise comparisons

0.99 Updated code in 'Kmatrix' function to handle the situation such as log(x), sin(pi*x) Added an option 'trillis' to control output plot in 'covariatemeans' function

Reference manual

It appears you don't have a PDF plugin for this browser. You can click here to download the reference manual.


0.99 by Dongwen Luo, 3 years ago

Browse source code at

Authors: Dongwen Luo, Siva Ganesh and John Koolaard

Documentation:   PDF Manual  

GPL (>= 2) license

Imports ggplot2, lattice, pbkrtest, plyr

Depends on lme4, nlme

See at CRAN