The fact that weak instruments lead to spurious inference is now widely recognized. In this paper we ask whether spurious inference occurs more generally in weakly identified models. To distinguish between models where spurious inference will occur from those where it does not, we introduce the...

This paper examines whether permanent earnings growth, crucial to stock valuation, increased during the last decade as suggested by proponents of the 'New Economy.' Using S\&P 500 earnings for 1951-2000, we do not find strong evidence of either a one-time structural break or gradual change....