Knowledge that Transforms

We analyze the impact of increased immigration on employment outcomes of natives in Germany using a data set of county-level variables for the late 1980s. In order to construct more unified labor market regions, we aggregate the 328 counties to 167 larger regions. We study two measures of immigration, the change in the share of foreigners between 1985 and 1989 as well as one-year gross and net flows of immigrants to an area. In order to address the potential problem of immigrant selection into local labor markets, we condition on previous labor market outcomes, which may serve as the basis of immigrant selection. This specification allows for mean reversion in the unemployment rate, which is strong in our data set and period of study. We show that this rules out some other approaches of identifying the impact of immigration. Our results indicate no detrimental effect of immigration. We find no support for the hypothesis that the absence of displacement effects is due to a response of native migration patterns.

We take a model selection approach to the question of whether a class of adaptive prediction models (artificial neural networks) is useful for predicting future values of nine macroeconomic variables. We use a variety of out-of-sample forecast-based model selection criteria, including forecast error measures and forecast direction accuracy. Ex ante or real-time forecasting results based on rolling window prediction methods indicate that multivariate adaptive linear vector autoregression models often outperform a variety of (1) adaptive and nonadaptive univariate models, (2) nonadaptive multivariate models, (3) adaptive nonlinear models, and (4) professionally available survey predictions. Further, model selection based on the in-sample Schwarz information criterion apparently fails to offer a convenient shortcut to true out-of-sample performance measures.

As with most analyses involving microdata, applications of count data models must somehow account for unobserved heterogeneity. The count model literature has generally assumed that unobservables and observed covariates are statistically independent. Yet for many applications this independence assumption is clearly tenuous. When the unobservables are omitted variables correlated with included regressors, standard estimation methods will generally be inconsistent. Though alternative consistent estimators may exist in special circumstances, it is suggested here that a nonlinear instrumental-variable strategy offers a reasonably general solution to such estimation problems. This approach is applied in two examples that focus on cigarette smoking behavior.

This paper studies the least squares estimation of a change point in multiple regressions. Consistency, rate of convergence, and asymptotic distributions are obtained. The model allows for lagged dependent variables and trending regressors. The error process can be dependent and heteroskedastic. For nonstationary regressors or disturbances, the asymptotic distribution is shown to be skewed. The analytical density function and the cumulative distribution function for the general skewed distribution are derived. The analysis applies to both pure and partial changes. The method is used to analyze the response of market interest rates to discount rate changes.

Ever since Nelson and Plosser (1982) found evidence in favor of the unit-root hypothesis for 13 long-term annual macro series, observed unit - root behavior has been equated with persistence in the economy. Perron (1989) questioned this interpretation, arguing instead that the "observed" behavior may indicate failure to account for structural change. Zivot and Andrews (1992) restored confidence in the unit-root hypothesis by incorporating an endogenous break point into the specification. By allowing for the possibility of two endogenous break points, we find more evidence against the unit-root hypothesis than Zivot and Andrews, but less than Perron.

This paper presents a model of consumer demand that is consistent with the observed expenditure patterns of individual consumers in a long time series of expenditure surveys and is also able to provide a detailed welfare analysis of shifts in relative prices. A nonparametric analysis of consumer expenditure patterns suggests that Engel curves require quadratic terms in the logarithm of expenditure. While popular models of demand such as the Translog or the Almost Ideal Demand Systems do allow flexible price responses within a theoretically coherent structure, they have expenditure share Engel curves that are linear in the logarithm of total expenditure. We derive the complete class of integrable quadratic logarithmic expenditure share systems. A specification from this class is estimated on a large pooled data set of U.K. households. Models that fail to account for Engel curvature are found to generate important distortions in the patterns of welfare losses associated with a tax increase.

In a 1991 essay in Scientific American, Michael Porter suggested that environmental regulation may have a positive effect on the performance of domestic firms relative to their foreign competitors by stimulating domestic innovation. We examine the stylized facts regarding environmental expenditures and innovation in a panel of manufacturing industries. We find that lagged environmental compliance expenditures have a significant positive effect on R&D expenditures when we control for unobserved industry-specific effects. We find little evidence, however, that industries' inventive output (as measured by successful patent applications) is related to compliance costs.