Measures of fit in multiple correspondence analysis of crisp and fuzzy coded data

When continuous data are coded to categorical variables, two types of coding are possible: crisp coding in the form of indicator, or dummy, variables with values either 0 or 1; or fuzzy coding where each observation is transformed to a set of "degrees of membership" between 0 and 1, using co-called membership functions. It is well known that the correspondence analysis of crisp coded data, namely multiple correspondence analysis, yields principal inertias (eigenvalues) that considerably underestimate the quality of the solution in a low-dimensional space. Since the crisp data only code the categories to which each individual case belongs, an alternative measure of fit is simply to count how well these categories are predicted by the solution. Another approach is to consider multiple correspondence analysis equivalently as the analysis of the Burt matrix (i.e., the matrix of all two-way cross-tabulations of the categorical variables), and then perform a joint correspondence analysis to fit just the off-diagonal tables of the Burt matrix - the measure of fit is then computed as the quality of explaining these tables only. The correspondence analysis of fuzzy coded data, called "fuzzy multiple correspondence analysis", suffers from the same problem, albeit attenuated. Again, one can count how many correct predictions are made of the categories which have highest degree of membership. But here one can also defuzzify the results of the analysis to obtain estimated values of the original data, and then calculate a measure of fit in the familiar percentage form, thanks to the resultant orthogonal decomposition of variance. Furthermore, if one thinks of fuzzy multiple correspondence analysis as explaining the two-way associations between variables, a fuzzy Burt matrix can be computed and the same strategy as in the crisp case can be applied to analyse the off-diagonal part of this matrix. In this paper these alternative measures of fit are defined and applied to a data set of continuous meteorological variables, which are coded crisply and fuzzily into three categories. Measuring the fit is further discussed when the data set consists of a mixture of discrete and continuous variables.

Employment Protection, International Specialization, and Innovation

We develop a model to analyse the implications of firing costs on incentives for R&D and international specialization. The Key idea is paying the firing cost, the country with a rigid labor market will tend to produce relatively secure goods, at a late stage of their product life cycle. Under international trade, an international product cycle emerges where, roughly, new goods are first produced in the low firing cost country will specialize in 'secondary innovations', that is, improvements in existing goods, while the low firing cost country will more specialize in 'primary innovation', that is, invention of new goods.

PhD Students’ Research Group Social Capital in Two Countries: A Clustering Approach with Duocentred Network Measures

The article examines the structure of the collaboration networks of research groups where Slovenian and Spanish PhD students are pursuing their doctorate. The units of analysis are student-supervisor dyads. We use duocentred networks, a novel network structure appropriate for networks which are centred around a dyad. A cluster analysis reveals three typical clusters of research groups. Those which are large and belong to several institutions are labelled under a bridging social capital label. Those which are small, centred in a single institution but have high cohesion are labelled as bonding social capital. Those which are small and with low cohesion are called weak social capital groups. Academic performance of both PhD students and supervisors are highest in bridging groups and lowest in weak groups. Other variables are also found to differ according to the type of research group. At the end, some recommendations regarding academic and research policy are drawn

Allowing for heterogeneity in the decomposition of measures of inequality in health

This paper shows how recently developed regression-based methods for the decomposition ofhealth inequality can be extended to incorporate heterogeneity in the responses of health to the explanatory variables. We illustrate our method with an application to the GHQ measure of psychological well-being taken from the British Household Panel Survey. The results suggest that there is an important degree of heterogeneity in the association of health to explanatory variables across birth cohorts and genders which, in turn, accounts for a substantial percentage of the inequality in observed health.

Skill-biased technological change and the business cycle

Over the past two decades, technological progress in the United States hasbeen biased towards skilled labor. What does this imply for business cycles?We construct a quarterly skill premium from the CPS and use it to identifyskill-biased technology shocks in a VAR with long-run restrictions. Hours fallin response to skill-biased technology shocks, indicating that at least part of thetechnology-induced fall in total hours is due to a compositional shift in labordemand. Skill-biased technology shocks have no effect on the relative price ofinvestment, suggesting that capital and skill are not complementary in aggregateproduction.

Assesing the political viability of labour market reform: The case of employment protection

We analyze the political support for employment protection legislation.Unlike my previous work on the same topic, this paper pays a lot ofattention to the role of obsolescence in the growth process.In voting in favour of employment protection, incumbent employeestrade off lower living standards (because employment protectionmaintains workers in less productive activities) against longer jobduration. The support for employment protection will then depend onthe value of the latter relative to the cost of the former. Wehighlight two key deeterminants of this trade-off: first, the workers'bargaining power, second, the economy's growth rate-more preciselyits rate of creative destruction.

Forest fires: Evaluation of government intervention measures

The purpose of this paper is to examine the relation between government measures, volunteer participation, climate variables and forest fires. A number of studies have related forest fires to causes of ignition, to fire history in one area, to the type of vegetation and weathercharacteristics or to community institutions, but there is little research on the relation between fire production and government prevention and extinction measures from a policy evaluation perspective.An observational approach is first applied to select forest fires in the north east of Spain. Taking a selection of fires with a certain size, a multiple regression analysis is conducted to find significant relations between policy instruments under the control of the government and the number of hectares burn in each case, controlling at the same time the effect of weather conditions and other context variables. The paper brings evidence on the effects of simultaneity and the relevance of recurring to army soldiers in specific days with extraordinary high simultaneity. The analysis also brings light on the effectiveness of twopreventive policies and of helicopters for extinction tasks.

Expertise and finance: Mergers motivated by technological change

This paper argues that a large technological innovation may lead to a merger wave by inducing entrepreneurs to seek funds from technologically knowledgeable firms -experts. When a large technological innovation occurs, the ability of non-experts (banks) to discriminate between good and bad quality projects is reduced. Experts can continue to charge a low rate of interest for financing because their expertise enables them to identify good quality projects and to avoid unprofitable investments. On the other hand, non-experts now charge a higher rate of interest in order to screen bad projects. More entrepreneurs, therefore, disclose their projects to experts to raise funds from them. Such experts are, however, able to copy the projects and disclosure to them invites the possibility of competition. Thus the entrepreneur and the expert may merge so as to achieve product market collusion. As well as rationalizing mergers, the model can also explain various forms of venture financing by experts such as corporate investors and business angels.

Technological change and the wealth of nations

We discuss a unified theory of directed technological change and technologyadoption that can shed light on the causes of persistent productivity differencesacross countries. In our model, new technologies are designed in advanced countries and diffuse endogenously to less developed countries. Our framework is richenough to highlight three broad reasons for productivity differences: inappropriatetechnologies, policy-induced barriers to technology adoption, and within-countrymisallocations across sectors due to policy distortions. We also discuss the effectsof two aspects of globalization, trade in goods and migration, on the wealth ofnations through their impact on the direction of technical progress. By doing so,we illustrate some of the equalizing and unequalizing forces of globalization.

Effects of employment protection and product market regulations on the Italian labor market

Labor market regulations have often being blamed for high and persistentunemployment in Europe, but evidence on their impact remains mixed. Morerecently, attention has turned to the impact of product market regulationson employment growth. This paper analyzes how labor and product marketregulations interact to affect turnover and employment. We present a matchingmodel which illustrates how barriers to entry in the product market mitigatethe impact of labor market deregulation. We, then, use the Italian SocialSecurity employer-employee panel to study the interaction between barriersto entry and dismissal costs. We exploit the fact that costs for unjustdismissals in Italy increased for firms below 15 employees relative to biggerfirms after 1990. We find that the increase in dismissal costs after 1990decreased accessions and separations in small relative to big firms,especially for women. Moreover, consistent with our model, we find evidencethat the increase in dismissal costs had smaller effects on turnover for womenin sectors faced with strict product market regulations.

European research funding and regional technological capabilities: Network composition analysis

We use network and correspondence analysis to describe the compositionof the research networks in the European BRITE--EURAM program. Our mainfinding is that 27\% of the participants in this program fall into one oftwo sets of highly ``interconnected'' institutions --one centered aroundlarge firms (with smaller firms and research centers providing specializedservices), and the other around universities--. Moreover, these ``hubs''are composed largely of institutions coming from the technologically mostadvanced regions of Europe. This is suggestive of the difficulties of attainingEuropean ``cohesion'', as technically advanced institutions naturally linkwith partners of similar technological capabilities.

The political economy of employment protection

This paper develops a model of job creation and job destruction in agrowing economy with embodied technical progress, that we use toanalyze the political support for employment protection legislationssuch as the ones that are observed in most European countries.We analyze the possibility of Condorcet cycles due to the fact thatworkers about to become unemployed prefer both an increase and areduction in firing costs over the status quo. Despite this problem, we show the existence of local, and sometimes global majority winners.In voting in favour of employment protection, incumbent employeestrade off lower living standards (because employment protectionmaintains workers in less productive activities) against longer job duration. We show that the gains from, and consequently the politicalsupport for employment protection (as defined by maximunjob tenure) are larger, the lower the rate of creative destruction and the largerthe worker's bargaining power. Numerical simulations suggest a hump-shaped response of firing costs to these variables, as well as negative impact of exogeneous turnover on employment protection.

The political consequences of unemployment

We analyze the channels by which an ill-functioning labor market changes the preferences of the people for public policy and therefore the decisions that are made. We not only discuss labour market reform but other important aspects of policy making such as the size and structure of government spending. Theclass of mechanisms that we highlight can be summarized as the very existence of unemployment generating political support for "sclerosis". This may help to explain the timid pace of reform, in particular the fact that any recovery sends them at the backfront of the political agenda, and the sometimes violent opposition generated by some measures, as we have seen mostly in France.