Mikael Bask

Rationally addicted to drinking and smoking

When modelling demand for addictive consumption goods, the most widely used framework is the rational addiction model proposed by Becker and Murphy. This paper extends the rational addiction model to include two addictive consumption goods, alcohol and cigarettes, and using aggregate annual time series on sales volumes for the period 1955–1999, estimates the aggregate demand for these goods in Sweden, where OLS estimates are compared to GMM estimates allowing for possible endogeneity of lagged and lead consumption. First, the demand for alcohol and cigarettes are estimated as separate equations and it is found that alcohol demand is quite well described by the rational addiction model while the same is not true for cigarettes. The own-price elasticities are negative, and alcohol demand is more elastic than cigarette demand. The cross-price elasticities are also negative, showing that alcohol and cigarettes are complements. Since consumption of alcohol and cigarettes are probably simultaneous decisions, the demand for these goods is estimated as a system of equations and it is found that alcohol demand is still positively affected by lagged and lead consumption while cigarette demand is not. It is also found that the elasticities obtained are now generally smaller compared to when estimating the equations separately.

Testing chaotic dynamics via Lyapunov exponents

Abstract This paper presents a bootstrap-based test statistic for testing the presence of chaotic dynamics from data by using the Lyapunov exponents. In particular, a one-sided test statistic in Gencays [Gencay, Physica D 89 (1996) 261–266] framework is designed and its small sample properties are tested on the Henon map. The numerical examples show that the test statistic has desirable small sample properties.

A Positive Lyapunov Exponent in Swedish Exchange Rates

Abstract In this paper, a statistical framework utilizing a blockwise bootstrap procedure is used to test for the presence of a positive Lyapunov exponent in Swedish exchange rates [M. Bask, R. Gencay, Physica D 114 (1998) 1]. This is done since a necessary condition for chaotic dynamics is a positive Lyapunov exponent. Daily data for the Swedish Krona against the Deutsche Mark, the ECU, the US Dollar and the Yen exchange rates are examined. In most cases, the null hypothesis that the Lyapunov exponent is zero is rejected in favor of a positive exponent.

Should one use smokeless tobacco in smoking cessation programs

The rational addiction model is often used for empirical analysis of the demand for addictive goods. We propose an extension of the model to include two goods, cigarettes and Swedish moist snuff, locally known as snus. Demand equations are estimated using aggregated annual time series data (in first differences) for the period 1964–1997. The findings from the dataset used give some support to the rational addiction hypothesis. The cross-price elasticities are negative, which indicates that taking snus contributes to increased smoking. Thus it is not advisable to encourage the use of the less harmful snus in smoking cessation programs.

Dimensions and Lyapunov exponents from exchange rate series

Abstract Detecting the presence of deterministic chaos in economic time series is an important problem that may be solved by measuring the largest Lyapunov exponent. In this paper we present estimates of the largest Lyapunov exponent in daily data for the Swedish Krona vs Deutsche Mark, ECU, U.S. Dollar and Yen exchange rates. In order to estimate the dimension of the systems producing these exchange rate series, we also present estimates of the correlation dimension. We found indications of deterministic chaos in all exchange rate series. However, the estimates for the largest Lyapunov exponents are not reliable, except in the Swedish Krona-ECU case, because of the limited number of data points. In the Swedish Krona-ECU case, we found indications of a low-order chaotic dynamical system.

Market power in the expanding Nordic power market

We examine if the Nordic power market, Nord Pool, has been competitive or if electricity suppliers have had market power. Specifically, since the evolution from national markets to a multi-national and largely deregulated power market has taken place stepwise, we also examine how the degree of market power has evolved during this integration process. The Bresnahan–Lau method together with weekly data during 1996–2004 are used in the analysis, which shows that electricity suppliers have had small, but statistically significant, market power, but that the market power has been reduced as the Nord Pool area has expanded.