OK, great work, maybe, but where are the error terms? Large states, like California, Texas, Florida and New York are most self correlated. The response of these large states gives us the greatest accuracy. Illinois, the fifth largest state is the exception because they are a traffic hub for the transport of goods across the economy. Illinois unemployment dropped mostly with the drop in oil costs. Florida is a retirement state, but also self correlated, as long as entitlements are stable. So this research would show a small, but accurate effect in Florida. How about Nevada? That state is almost entirely correlated with what happens in California, it will have a high error term. Montana will be in the noise with less than a million people.NBR: We measure the effect of unemployment benefit duration on employment. We exploit the variation induced by the decision of Congress in December 2013 not to reauthorize the unprecedented benefit extensions introduced during the Great Recession. Federal benefit extensions that ranged from 0 to 47 weeks across U.S. states at the beginning of December 2013 were abruptly cut to zero. To achieve identification we use the fact that this policy change was exogenous to cross-sectional differences across U.S. states and we exploit a policy discontinuity at state borders. We find that a 1% drop in benefit duration leads to a statistically significant increase of employment by 0.0161 log points. In levels, 1.8 million additional jobs were created in 2014 due to the benefit cut. Almost 1 million of these jobs were filled by workers from out of the labor force who would not have participated in the labor market had benefit extensions been reauthorized.
State differences are OK, just watch how the error term distribute across state boundaries. In particular, block the state correlation matrix into principle components, likely three sub matrices based on correlation spreads.
No comments:
Post a Comment