Conditions for invariance of the multivariate versions of grubbs’ test and bartlett’s test under a general dependency structure

Summary This paper generalizes a result by Stadje (1984) by deriving conditions for which a general dependency structure for multivariate observations, given in Pavur (1987), yields a positive definite covariance structure. This general dependency structure allows the sample covariance matrix to be distributed as a constant times a Wishart random matrix. It is then demonstrated that the maximum squared-radii test and a test for equal population covariance matrices have null distributions which remain unchanged when the new general dependency structure, rather than the usual independence structure, for the vector observations, is assumed. Moreover, under a general dependency structure for which the population covariance matrices are unequal, it is shown that the distribution of the test statistic for testing equal covariance matrices is identical to the distribution of the same test statistic when the population covariance matrices are equal and the observations are independent.     

Bounds for the difference between median and mean of beta and negative binomial distributions

Summary We obtain bounds for the difference between the median and mean of the beta and negative binomial distributions using elementary methods.     

An interview with FDA Commissioner Frank Young. Interview by Carmella Bocchino

The Food and Drug Administration (FDA) has recently been the target of congressional investigations and has seen recent changes in its approval procedures. In this interview, FDA Commissioner Frank Young responds to harsh congressional criticisms and details the FDA approval process.     

Financial Pressure and Balance Sheet Adjustment by Firms*

This paper examines the financial policies and balance sheet adjustment of companies. Using a large panel of UK‐listed firms we consider how companies resolve pressures on their balance sheet, estimating models for dividends, new equity issuance and investment. The results indicate that companies resolve balance sheet pressures by each of these means. Financial policies, through dividends and new equity issuance, and real investment decisions, respond to the underlying level of debt and the borrowing cost of servicing that debt. Dividends are estimated to be slow to adjust in the short run.     

Industrial Targeting and Non‐shiftable Capital in the Harris–Todaro Model*

This paper shows that, in the 2 × 3 sector‐specific capital Harris–Todaro model, capital growth owing to either domestic or foreign investment always enhances the welfare of the country (i.e. non‐immiserizing), and this result of non‐immiserizing foreign investment holds regardless of initial holdings of foreign capital; the policy of industrial targeting via capital investment is more effective vis‐à‐vis the (neoclassical) 2 × 2 mobile‐capital Harris–Todaro model or the Heckscher–Ohlin model; in contrast to the recent generalization by Marjit and Beladi (2003 ), capital growth cannot be immiserizing in the present model, even if it destroys the “envelope theorem.”     

Entrepreneurship and envy

This paper is a critical evaluation of Hayek's “Atavism of social justice” thesis, suggesting an alternative explanation of the widespread demands for social justice in contemporary society. It is based on the analysis of the nature of entrepreneurship and its tendency to incite envy. The advantages of the proposed explanation include a better understanding of the persistent hostility against commerce and the market system and the possibility of a systematic exploration of the factors which make the demand for social justice stronger or weaker. An earlier draft was presented at the Friedrich August von Hayek Memorial Symposium, Bleibach, Germany, June 9–12, 1993. I thank the participants of the symposium for their helpful comments and suggestions.     

Technological growth curves : A competition of forecasting models

In order to determine procedures for appropriate model selection of technological growth curves, numerous time series that were representative of growth behavior were collected and categorized according to data characteristics. Nine different growth curve models were each fitted onto the various data sets in an attempt to determine which growth curve models achieved the best forecasts for differing types of growth data. The analysis of the results gives rise to a new approach for selecting appropriate growth curve models for a given set of data, prior to fitting the models, based on the characteristics of the data sets.     

Unemployment and Property Crime: Not a Simple Relationship

A bstract . While previous studies on the unemployment-crime hypothesis have yielded equivocal results, here nonsignificant Pearson correlation coefficients were found for theft rates and the percentage of unemployed men and unemployed women for 20 nations. This raises additional cross-cultural questions about the validity both of strain theories that predict positive correlations, and competing theories that predict negative correlations. Implications for research on the unemployment-crime hypothesis are discussed.     

The service sector and economic growth: some cross-section evidence

It has often been claimed that a relative expansion of the service sector has a deleterious effect on economic growth. This paper uses cross-section country-level data from three decades –1960s, 1970s and 1980s – to see whether in fact this negative relation is reflected in the data. It is found that the effect is negative or positive depending on how the role of the service sector is measured, but there is a strong case that effect is in fact usually negative.     

Culture and consumption expenditure patterns: comparison between Korean and United States households

Abstract The purpose of this study was to identify household consumption expenditure patterns in the US and to determine if these patterns are different from those of Korean households. Data were cluster analysed, and the results revealed four different consumption expenditure patterns for US and Korean households. Logit analysis showed that consumption expenditure patterns of households in both countries are likely to vary depending on socioeconomic factors. Similarities and differences in consumption expenditure patterns between cultures are discussed, and implications are provided.