Dennis W. Jansen

A Primer on Cointegration with an Application to Money and Income

For some time now, macroeconomists have been aware that many macroeconomic time-series are not stationary in their levels and that many time-series are most adequately represented by first differences.1 In the parlance of time-series analysis, such variables are said to be integrated of order one and are denoted I(1). The level of such variables can become arbitrarily large or small so there is no tendency for them to revert to their mean level. Indeed, neither the mean nor the variance is a meaningful concept for such variables.

Safety First Portfolio Selection, Extreme Value Theory and Long Run Asset Risks

The paper motivates the use of the statistical extreme value theory for the problem of portfolio selection in economics, both theoretically and empirically. It is shown that the conventional safety first criterion developed by Roy can be successfully improved upon by exploiting the fat tail property of asset returns. Extreme value theory is seen to provide a better bound than the Chebyshev bound. In the empirical application we calculate minimum threshold return levels given very low exceedance probabilities for bond and equity investors. A proof of a new quantile estimator is obtained in the appendix. The data cover at least a half-century of returns and allow for evaluation of investment risks in the long run.

Portfolio selection with limited downside risk

A safety-first investor maximizes expected return subject to a downside risk constraint. Arzac and Bawa [Arzac, E.R., Bawa, V.S., 1977. Portfolio choice and equilibrium in capital markets with safety-first investors. Journal of Financial Economics 4, 277–288.] use the Value at Risk as the downside risk measure. The paper by Gourieroux, Laurent and Scaillet estimates the optimal safety-first portfolio by a kernel-based method, we exploit the fact that returns are fat-tailed, and propose a semi-parametric method for modeling tail events. We also analyze a portfolio containing the two stocks used by Gourieroux et al. and discuss the merits of the safety-first approach.

The method of moments ratio estimator for the tail shape parameter

The so-called Hill estimator for the shape parameter of the tail distribution is known to be downwardly biased. The Hill estimator is a moment estimator, based on the first conditional moment of the highest logarithmically transformed data. We propose a new estimator for the tail index based on the ratio of the second to the first conditional moment. This estimator has a smaller bias than the Hill estimator. We provide simulation results that demonstrate a sizable reduction in bias when a is large, while the MSE is moderated as well. The new estimator is applied to stock return data in order to resolve a long standing issue in economics.

Unit Roots and Infrequent Large Shocks: New International Evidence on Output Growth

The authors examine output growth for the G-7 countries. They use Nathan S. Balke and Thomas Fombys procedure to identify the date and type of trend breaks, and note that these occur in clusters. The authors estimate country-specific intervention models and test the unit root hypothesis. Their critical values explicitly take account of the prior outliner search procedure. For Italy, Japan, and the United Kingdom, the unit root null hypothesis can be rejected. This suggests that the variance of output growth in these countries is generated by low-frequency, high-magnitude shocks rather than high-frequency, low-magnitude shocks. Copyright 1995 by Ohio State University Press.

The geographic distribution of unemployment rates in the U.S. : A spatial-time series analysis

Abstract This paper presents estimates of the time series and spatial pattern of unemployment rate fluctuations in the U.S. over the period 1977.I–1983.IV. Spatial and time series autocorrelations over a regular lattice are estimated using both simultaneous (SAR) and conditional (CAR) autoregressive models of spatial series. The empirical results indicate that a temporary unemployment rate shock has a significant effect on unemployment rates in adjacent areas contemporaneously, but virtually no impact on neighboring unemployment rates after six quarters. A permanent change in an areas unemployment rate has a strong and persistent impact on unemployment rates in labor markets within 250 miles of the initial shock.

Advertising effects in complete demand systems

A rationale for including advertising in complete demand systems is presented. An advertising analogue of the Slutsky equation is derived, and properties of the expenditure and indirect utility functions characterized. Empirical estimates of a complete demand system incorporating dynamic advertising effects support neoclassical restrictions; we do not reject homogeneity, or symmetry at the 1% level. This represents surprisingly strong support for neoclassical theory relative to prior parametric studies.

The Adequacy of Educational Cost Functions: Lessons From Texas

Adequacy studies based on cost functions have come under attack. A recent Texas court battle featured two cost function studies that reached markedly different conclusions about the additional funding needed to meet designated performance goals. Some critics see such disparities as indicators of a general futility in the whole education cost function enterprise. We argue that the more appropriate conclusion is that it is critically important to demand best-practice techniques from any analyst of educational costs. This article uses the Texas litigation studies as a lens through which to explore best practices in the estimation of educational cost functions. The analysis highlights five key decisions that researchers must make when using the cost function methodology in an educational setting and explores the implications of the various possible choices using recent data on public schools in Texas. As the analysis demonstrates, some common practices in cost function analyses of education are not best practices, and these deviations from best practice can have a significant impact on the estimated cost of an adequate education.

Variance of Agricultural Prices, Industrial Prices, and Money

The relative uncertainty of agricultural prices and industrial prices with respect to the uncertainty of growth in the money supply are investigated utilizing multivariate ARCH and GARCH analysis. The conditional variances of agricultural prices were shown to dwarf the variances of industrial prices and the money supply. The relatively greater sensitivity of the conditional variance of agricultural prices to changes in the variance of the money supply than industrial prices found in this analysis provides a further perspective on the uncertainty confronting farmers, including the impacts of the monetary policy shock that precipitated the farm financial crisis in the early 1980s.

An evaluation of federal reserve forecasting

Abstract This paper examines the accuracy, reliability and efficiency of U.S. Federal Reserve System green book forecasts, which form the basis for policy discussions at the Feeral Open Market Committee meetings. Poor forecasting combined with activist policy making could well result in poor policy performance. We find evidence that some of the Feds forecasts can be improved, and we investigate some explicit modifications intended to improve on the Fed forecasts.