NBER Publications by James Powell

In this paper we study identification and estimation of the causal effect of a small change in an endogenous regressor on a continuously-valued outcome of interest using panel data. We focus on the average partial effect (APE) over the full population distribution of unobserved heterogeneity (e.g., Chamberlain, 1984; Blundell and Powell, 2003; Wooldridge, 2005a). In our basic model the outcome of interest varies linearly with a (scalar) regressor, but with an intercept and slope coefficient that may vary across units and over time in a way which depends on the regressor. This model is a special case of Chamberlain's (1980b, 1982, 1992a) correlated random coefficients (CRC) model, but not does not satisfy the regularity conditions he imposes. Irregularity, while precluding estimation at par...

This paper studies the cyclical behavior of a number of industrial labor markets of the pre-war (1923-1939) and post-war (1954-1982) eras. In the spirit of Burns and Mitchell we do not test a specific structural model of the labor market but instead concentrate on describing the qualitative features of the (monthly, industry-level) data.The two principal questions we ask are: First, how is labor input (as measured by the number of workers, the hours of work, and the intensity of utilization) varied over the cycle ? Second, what is the cyclical behaviorof labor compensation (as measured by real wages, product wages, and real weekly earnings) ? We study these questions in both the frequency domain and the time domain. Many of our findings simply reinforce, or perhaps refine, existing percept...