The supply and price of skilled labor relative to unskilled labor have chan
ged dramatically over the postwar period. The relative quantity of skilled
labor has increased substantially, and the skill premium, which is the wage
of skilled labor relative to that of unskilled labor, has grown significan
tly since 1980. Many studies have found that accounting for the increase in
the skill premium on the basis of observable variables is difficult and ha
ve concluded implicitly that latent skill-biased technological change must
be the main factor responsible. This paper examines that view systematicall
y We develop a framework that provides a simple, explicit economic mechanis
m for understanding skill-biased technological change in terms of observabl
e variables, and we use the framework to evaluate the fraction of variation
in the skill premium that can be accounted for by changes in observed fact
or quantities. We find that with capital-skill complementarity, changes in
observed inputs alone can account for most of the variations in the skill p
remium over the last 30 years.