RECENT DEVELOPMENTS IN COUNT DATA MODELLING: THEORY AND APPLICATION

Abstract. This paper deals with statistical methods for modelling individual behavior when the endogenous variable is a nonnegative integer. Examples are the number of children, the number of job changes or the number of shopping trips in a given period. Several approaches—Poisson, robust Poisson, negative binomial (NEGBIN), NEGBIN _k , hurdle Poisson, truncated-at-zero Poisson—are discussed with a focus on specification, estimation, and testing. An application to labor mobility data illustrates the gain obtained by carefully taking into account the specific structure of the data.     

Voting on Unemployment Insurance

In this article, we ask heterogeneous agents in a dynamic general equilibrium economy to vote on the generosity of their unemployment insurance program. We observe the influence on their vote of (1) moral hazard, (2) private alternatives, and (3) changes in employment status. Agents differ in skills, employment probabilities, income prospects, and assets. For a calibration to the United States, we show that: (1) in contrast to the literature, plausible levels of moral hazard need not induce large cuts in optimal benefits. (2) Switching to private insurance is rejected for most status quo, though it would be as generous. (3) Skill groups vote as a block. For reasonable discount factors, solidarity is never broken simultaneously for more than one group.     

Books and Notes

The paper presents the history of input–output tables in Cyprus, outlines the use made of these tables and sketches the future plans for the expansion and development of input–output statistics.     

Vorsorge und Aktienmarkt: Die Zeit der Illusionen ist vorbei

Ohne Zusammenfassung     

Evaluating Pseudo-R2's for binary probit models

Many applied researchers of limited dependent variable models found it disadvantageous that a widely accepted Pseudo-R² does not exist for this type of estimation. The paper provides guidance for researchers in choosing a Pseudo-R² in the binary probit case. The starting point is that R² is best understood in the ordinary least squares (OLS) case with continuous data, which is chosen as the reference situation. It is considered which Pseudo-R² is best able to mimic the OLS-R². The results are surprisingly clear: a measure suggested by McKelvey-Zavoina performs the best under our criterion. However, in the more likely case of low Pseudo-R²'s, a normalization of a measure proposed by Aldrich-Nelson which we suggest is almost as good as the McKelvey-Zavoina, and is in general easier to calculate. We also show that if the underlying R² is predicted using cubic regressions given the Pseudo-R², all measures perform much better.     

The Foreign Exchange Rate Exposure of Nations

Following the well-known approach by Adler and Dumas (Financ Manage 13(2):41–50, 1984), we evaluate the foreign exchange rate exposure of nations. Results based on data from 27 countries show that national foreign exchange rate exposures are significantly related to the current account and financial account balance variables of corresponding economies.     

Does the Interactive Use of Headquarter Performance Measurement Systems in Foreign Subsidiaries Endanger the Potential to Profit from Local Relationships?

Managing distant subsidiaries is a challenge for headquarters of multinational companies. Performance measurement systems (PMS) can assist in this task. Taking a business network perspective, we study the moderating effect of the interactive use of PMS implemented by headquarters at subsidiaries on the relationship between subsidiary embeddedness and subsidiary performance. We test our hypotheses using survey data from 110 subsidiary managers in China. The results suggest that the multinational network surrounding the subsidiary affects overall headquarter control possibilities. Specifically, while interactive use may be helpful in situations of low local embeddedness of the subsidiary, it seems to have negative side effects on the subsidiaries’ ability to benefit from high local embeddedness.     

Robust determinants of health care expenditure growth

Our aim is to disclose robust explanatory variables for health care expenditure (HCE) growth by introducing to this field of research a method that is especially well suited for situations of ‘model uncertainty’: the Extreme Bounds Analysis (EBA). We analyse data for 33 OECD countries over the period 1970–2010 and include – as far as it is statistically feasible – all macroeconomic and institutional determinants of HCE growth in the EBA that have been suggested in the literature. Furthermore, we analyse to what extent outliers in the data influence the results. Our results confirm earlier findings that GDP growth and a variable representing Baumol’s ‘cost disease’ theory emerge as robust and statistically significant determinants of HCE growth. Depending on whether or not outliers are excluded, we find up to six additional robust drivers: the growth in expenditure on health administration, the change in the share of inpatient expenditure in total health expenditure, the (lagged) government share in GDP, the change in the insurance coverage ratio, the growth in land traffic fatalities and the growth in the population share undergoing renal dialysis.     

Testing Okun’s law with Swiss industry data

Okun’s law postulates a stable relationship between quarterly output growth and changes in (un)employment. This proposition has so far been tested with macroeconomic data at the highest level of aggregation. The article goes beyond that in extending the analysis to industry data from Switzerland, applying a method suggested by the International Monetary Fund. Another focus is on whether expansions in production have become more ‘jobless’ over the most recent business cycle compared to earlier ones. This does not seem to be the case in Switzerland, except in the construction industry.