We are concerned with finding the orthogonal projection to the plane t
hat best displays groups. There are three situations in which this que
stion can emerge: when the groups are identified a priori; when the cl
asses result from a cluster analysis; and when the parameters of the c
lasses are estimated from a distribution mixture method. We propose a
''maximin'' projection where the minimum intermean distance is maximiz
ed over the different projections to the plane as the one that best di
splays all the groups, especially in the presence of groups with marke
dly different sizes; in the case of three groups it reduces to the pla
ne defined by the canonical variables. We illustrate the method with o
ne artificial and one real data set.