JBNST - Vol. 235/6 - 2015

The HP filter is the most popular filter for extracting the unobserved trend and cycle components from a time series. Many researchers consider the smoothing parameter ? = 1600 as something like a universal constant. It is well known that the HP filter is an optimal filter under some restrictive assumptions, especially that the “cycle” is white noise. In this paper we show that we can get a good approximation of the optimal Wiener-Kolmogorov filter for autocorrelated cycle components by using the HP filter with a much higher smoothing parameter than commonly used. In addition, a new method – based on the properties of the differences of the estimated trend – is proposed for the selection of the smoothing parameter.

The decision to revise an educational choice has hardly been analyzed in previous research. Dropping out is only one possible choice, and we distinguish between dropping out (leaving the apprenticeship system) and changing or upgrading (staying within the apprenticeship system) as three possibilities to revise an educational decision, using a dataset that consists of apprentices who have dissolved their apprenticeship contract. We analyze the determinants of leaving apprenticeship training using competing risks models. Dropout decisions seem to be driven by financial considerations such as financial distress, but local labor market conditions seem to have no effect on them. Our findings underline the importance of distinguishing between the different choices instead of focusing exclusively on dropping out.

This paper aims to find an adequate concept to evaluate the replacement rate of the latest retiree generation of 2010. Classic replacement rates fail to provide meaningful conclusions because they can only be calculated for around half the retirees. This paper proposes an alternative figure, the so-called life cycle replacement rate, which relates individuals’ pension payments to the average real income over their whole working history. In sum, work history related characteristics like marital status, income or retirement age strongly influence individuals’ replacement rates. Furthermore, women’s replacement rates particularly benefit from non-contribution based pension entitlements, e.g. for periods of child-raising.

Over the last few years, rising prices and increasing price volatility of major agricultural food commodities were observed. This caused a debate among various organizations about who is responsible for this development. While many Non-Governmental Organizations proclaim that speculations in future markets cause the rise in food prices, academic research provides ambiguous results on this topic. This controversy is the motivation for this study. In order to offer additional insights, the relationship between the price changes of corn, wheat, and soybeans and the corresponding changes in open interests are analyzed. Commitments of Traders as well as Disaggregated Commitments of Traders reports are investigated to determine whether the activities of speculators adversely affect food prices. First, Johansen cointegration tests are employed to analyze the relationship between price and position data. Second, VAR and VECM are used to analyze short- and long-term dynamics. The results of the empirical analysis demonstrate that in the short-run price changes precede changes in open interest. Additionally, soybeans show a long-run equilibrium relationship between both series, indicating that speculators influenced past prices to some extent. However, the percentage price change is rather low. Therefore, sharp rises in soybean prices cannot be explained by it.

This study aims to determine whether forward discount represents a long memory or short memory process with multiple changes in the mean. Based on the samples of six currencies from November 3, 1986, to March 6, 1998, using Baek and Pipiras’s (2012, 2014) statistical procedures, our findings suggest that forward discount is a short memory process with multiple changes in the mean rather than long memory. These changes in mean are the result of an intervention by monetary authorities in the forex market. Thus, earlier findings of long memory in forward discount, as reported in the extant literature, are questionable.

In this paper we consider frequentist model averaging for principal components augmented regressions illustrated with the Fernandez et al. (2001) data set on economic growth determinants. We compare and contrast our method and findings with the WALS approach of Magnus et al. (2010).