Comparative case studies often rely on the analysis of a few cases sel
ected on the dependent variable. This approach has been criticized in
the methodological literature. I offer a qualified defense of the meth
od. Selecting on the dependent variable is appropriate when necessary
conditions are being evaluated. Works that have been criticized for se
lecting on the dependent variable make appropriate claims about necess
ary conditions. Evaluation of the inferential problems suggest guideli
nes for case selection and analysis. In particular, a simple Bayesian
model can question whether comparative case studies necessarily suffer
from a ''small n'' problem. Necessary conditions are an important, if
undervalued, tool of political analysis.