Variable selection for varying coefficient models with measurement errors

This paper focuses on variable selections for varying coefficient models when some covariates are measured with errors. We present a bias-corrected variable selection procedure by combining basis function approximations with shrinkage estimations. With appropriate selection of the tuning parameters, we establish the consistency of the variable selection procedure, and derive the optimal convergence rate of the regularized estimators. A simulation study and a real data application are undertaken to assess the finite sample performance of the proposed variable selection procedure.     

An algorithm for panel ANOVA with grouped data

In this paper, we present an algorithm suitable for analysing the variance of panel data when some observations are either given in grouped form or are missed. The analysis is carried out from the perspective of ANOVA panel data models with general errors. The classification intervals of the grouped observations may vary from one to another, thus the missing observations are in fact a particular case of grouping. The proposed Algorithm (1) estimates the parameters of the panel data models; (2) evaluates the covariance matrices of the asymptotic distribution of the time-dependent parameters assuming that the number of time periods, T, is fixed and the number of individuals, N, tends to infinity and similarly, of the individual parameters when T → ∞ and N is fixed; and, finally, (3) uses these asymptotic covariance matrix estimations to analyse the variance of the panel data.     

Issues in the analysis of co-authorship networks

Scientific collaboration is a complex phenomenon that improves the sharing of competences and the production of new scientific knowledge. Social Network Analysis is often used to describe the scientific collaboration patterns defined by co-authorship relationships. Different phases of the analysis of collaboration are related to: data collection, network boundary setting, relational data matrix definition, data analysis and interpretation of results. The aim of this paper is to point out some issues that arise in these different phases, highlighting: (i) the use of local archives versus international bibliographic databases; (ii) the use of different approaches for setting boundaries in a whole-network; (iii) the definition of a co-authorship data matrix (binary and weighted ties) and (iv) the analysis and the interpretation of network measures for co-authorship data. We discuss the different choices that can be made in these phases within an illustrative example on real data which is referred to scientific collaboration among researchers affiliated to an academic institution. In particular, we compare global and actor-level network measures computed from binary and weighted co-authorship networks in different disciplines.     

When Less is More: Distinguishing Between Entrepreneurial Choice and Performance

This paper uses NCDS data on individual characteristics to distinguish determinants of entrepreneurial choice, income and job generation. A new model of utility from self-employment shows that relaxing liquidity constraints could inhibit performance. Empirically, we find that a range of inheritance enhances the performance of the self-employed and increases self-employment; while higher education also increases self-employment income and job creation, but reduces the probability of self-employment. Combining these choice and performance effects, we find that education has a positive net effect on job creation, as does inheritance up to a certain threshold.     

How accurate are government forecasts of economic fundamentals? The case of Taiwan

A government’s ability to forecast key economic fundamentals accurately can affect business confidence, consumer sentiment, and foreign direct investment, among others. A government forecast based on an econometric model is replicable, whereas one that is not fully based on an econometric model is non-replicable. Governments typically provide non-replicable forecasts (or expert forecasts) of economic fundamentals, such as the inflation rate and real GDP growth rate.In this paper, we develop a methodology for evaluating non-replicable forecasts. We argue that in order to do so, one needs to retrieve from the non-replicable forecast its replicable component, and that it is the difference in accuracy between these two that matters. An empirical example to forecast economic fundamentals for Taiwan shows the relevance of the proposed methodological approach. Our main finding is that the undocumented knowledge of the Taiwanese government reduces forecast errors substantially.     

Ready or Not? Homosexuality,Unit Cohesion,and Military Readiness

The U.S. military argues that homosexuals are unfit for service because their presence compromises military readiness and unit cohesion. Based on this assumption, it continues to discharge homosexuals at an average rate of approximately 925 per year. On the other hand, the extant research suggests that homosexuals are no more disruptive to military life than their heterosexual counterparts. By integrating the legal and scientific literature, this paper examines the soundness of the military’s assumptions and aims to improve our understanding of the issues involved. Within this context, the efficacy of the military’s “Don’t Ask, Don’t Tell, Don’t Pursue” policy and whether it is in the best interest of the military and its soldiers and sailors is discussed.

How different are the regional factors of high-tech and low-tech start-ups? Evidence from Japanese manufacturing industries

This paper analyzes regional determinants of the start-up ratio in the Japanese manufacturing sector. A major contribution of this study is the comparison between high-tech and low-tech industries. The empirical results using a sample of 253 industrial districts suggest that business density, weight of the manufacturing sector, and the average business size significantly influence the start-up ratio in both high-tech and low-tech industries. Distinct differences between these industries were found with regard to the effects of human capital, research institutes, and the weight of high-tech industries.

Propensity to firm creation: empirical research using structural equations

The identification of the entrepreneurs’ characteristics and the knowledge of the entrepreneurial profile of university students have been assuming a growing importance in the development of educational programs directed towards the entrepreneurship and start-up processes. This study aims to identify the factors that most contribute for the intention to start up a business. The research also tries to identify the profile of a potential entrepreneur student concerning several characteristics: personal attributes, family, demographic variables and motivations. Research findings include the idea that entrepreneurship education is the most relevant factor in what concerns the propensity to business creation. On the other side, personal characteristics have an important role in shaping motivation to start-up a business and perceived hurdles have a negative impact in the intention to start-up. The results may be relevant when developing an adequate educational program directed to the entrepreneurship education and start-up processes.     

Stochastic productivity measurement

Stochastic productivity indicators are defined, and superlative measures of these indicators are derived. It is shown that, in the presence of complete markets or a common-expectations equilibrium, differences in the market values of firms are superlative indicators of cross-sectional productivity differences. Exactness results are used to decompose nonstochastic productivity indicators into a measure of true productivity change and a measure of ‘luck’. The decomposition is illustrated empirically.