To understand natural selection we need to integrate its measure across env
ironments. We present a method for measuring phenotypic selection that comb
ines the potential for both environmental variation and phenotypic plastici
ty. The method uses path analysis and a measure of selection that is analog
ous to selection on breeding values. For individuals growing in alternative
environments, paths are created that represent potential changes in the en
vironment. The probabilities for these changes are then multiplied by the p
ath coefficients to calculate selection coefficients. Selection on plastici
ty is measured as the difference in selection within each environment. We i
llustrate these methods using data on selection in an experimental populati
on of Arabidopsis thaliana. individuals from 36 families were grown in one
of four environments, a factorial combination of shaded/open and early/late
shading. For final height of the inflorescence, there was positive selecti
on in both the open and shaded environments and negative selection on plast
icity of height. For bolting time, there was also positive selection in bot
h environments, but no selection on plasticity. We show how to use this inf
ormation to examine how selection would change with changes in environmenta
l frequencies and their transition probabilities. These methods can be expa
nded to encompass continuous traits and continuous environments as well as
other complexities of natural selection.