On Maximum Likelihood Estimation of Dynamic Panel Data Models

We analyse the finite sample properties of maximum likelihood estimators for dynamic panel data models. In particular, we consider transformed maximum likelihood (TML) and random effects maximum likelihood (RML) estimation. We show that TML and RML estimators are solutions to a cubic first‐order condition in the autoregressive parameter. Furthermore, in finite samples both likelihood estimators might lead to a negative estimate of the variance of the individual‐specific effects. We consider different approaches taking into account the non‐negativity restriction for the variance. We show that these approaches may lead to a solution different from the unique global unconstrained maximum. In an extensive Monte Carlo study we find that this issue is non‐negligible for small values of T and that different approaches might lead to different finite sample properties. Furthermore, we find that the Likelihood Ratio statistic provides size control in small samples, albeit with low power due to the flatness of the log‐likelihood function. We illustrate these issues modelling US state level unemployment dynamics.     

Reporting bias in incomplete information model

Company financial reports are likely to be systematically biased. In this paper, we extend the Duffie and Lando (2001) model with a skewness correction which can account for both random and directional components of reporting noise.     

Discount rates and shadow prices for public investment

This paper extends the Harberger–Sandmo–Drèze model for public discount rates to a many-good economy. It derives a formula for discount rates which are specific to each public enterprise or agency and used by them to discount future outputs and inputs evaluated at market prices. Such an approach is shown to be more efficient than that of simply using a single rate for all public projects. It is also more practical than asking each public firm to use second-best shadow prices in their analyses of investment projects.The general results are first provided; then, simple cases are considered and numerical examples presented to help interpret our formula and analyse its main determinants.     

Structural aspects of social capital: tests for cross-national equivalence in Europe

In this contribution we start from the emerging consensus on the widely disputed phenomenon of social capital. We propose to focus on structural aspects of social capital: formal (contacts within formal organizations) and informal (contacts outside of formal organizations). First, we address methodological questions on the cross-national equivalence of these social capital measurements. Second, we re-visit substantive questions on the patterns of relationships in different European countries. In particular, we inquire to which degree formal and informal social capital can substitute each other, as well as being complementary. We take advantage of recent Eurobaromer data (2004) containing a wide range of valid measurements on both structural aspects of social capital. We find strong evidence for cross-national equivalent measurements regarding formal social capital, employing probabilistic scalogram analyses. For informal social capital, we find strong evidence for configural and metric invariance as well as evidence for partial scalar invariance, employing multi group confirmatory factor analyses. We have to reject the substantive hypothesis on substitution of formal and informal social capital for all countries under consideration, except for Romania. We corroborate the hypothesis on complementarity of formal and informal social capital.     

The effects of dynamic feedbacks on LS and MM estimator accuracy in panel data models

The finite sample behavior is analyzed of particular least squares (LS) and a range of (generalized) method of moments (MM) estimators in panel data models with individual effects and both a lagged dependent variable regressor and another explanatory variable. The latter may be affected by lagged feedbacks from the dependent variable too. Asymptotic expansions indicate how the order of magnitude of bias of MM estimators tends to increase with the number of moment conditions exploited. They also provide analytic evidence on how the bias of the various estimators depends on the feedbacks and on other model characteristics such as prominence of individual effects and correlation between observed and unobserved heterogeneity. Simulation results corroborate the theoretical findings and reveal that in small samples of models with dynamic feedbacks none of the techniques examined dominates regarding bias and mean squared error over all parametrizations examined.     

Cartel dating

The begin and end dates of cartels are often ambiguous, despite competition authorities stating them with precision. The legally established infringement period(s) from documentary evidence need not coincide with the period(s) of actual cartel effects. In this paper, we show that misdating cartel effects leads to a (weak) overestimation of but‐for prices and an underestimation of overcharges. Total overcharges based on comparing but‐for prices to actual prices are a (weak) underestimation of the true amount overcharged, irrespective of the type and size of the misdating. The bias in antitrust damage estimation based on predicted cartel prices can have either sign. We extend the before‐during‐and‐after method with an empirical cartel dating procedure, which infers structural breaks of unknown number and dates that mark the actual begin and end dates of the collusive effects. Empirical findings in the European Sodium Chlorate cartel corroborate our theoretical results.     

Optimal redistribution when different workers are indistinguishable

Abstract.  Using the standard non linear income and commodity taxation framework, we examine the optimal policy to be adopted when the same labour disutility can receive two opposite interpretations: taste for leisure and activity limitation. In the absence of complete information about individual characteristics, an income tax does not allow distinguishing lazy from handicapped individuals. One may rely, however, on a combination of commodity and income taxes to redistribute from the former to the latter when they differ in their preferences for commodities. JEL Classification: H21, H41
Redistribution optimale quand les divers travailleurs sont indistincts.  A l'aide du cadre d'analyse conventionnel de fiscalité non linéaire sur les revenus et les biens, ce mémoire examine la politique optimale à adopter quand le même niveau de désutilité du travail peut être interprété de deux manières opposées : goût pour le loisir et souffrance attribuable à une infirmité. En l'absence de renseignements complets à propos des caractéristiques des individus, un impôt sur le revenu ne permet pas de distinguer les individus paresseux de ceux qui sont handicapés. On peut cependant compter sur une combinaison de taxes sur les revenus et les biens pour redistribuer du premier groupe vers le second quand leurs préférences pour les biens diffèrent.     

Optimal Income Taxation With Quasi-Linear Preferences Revisited

Properties of the optimal income tax for quasi-linear in leisure preferences are studied. With utilitarian or maxi-min objectives, closed-form solutions are obtained. Bunching occurs over intervals where the second-order incentive condition is binding. Whether this occurs depends solely on the skill distribution. The patterns of consumption and tax rates in the nonbunched range are independent of whether the second-order incentive constraints are binding. Bunching at the bottom can also occur if a non-negative constraint on incomes is binding for some households. The pattern of marginal tax rates depends on the skill distribution and whether it is truncated.     

International joint ventures,HRM and viable knowledge migration

International joint ventures (IJVs) are an increasingly popular form of voluntary co-operation between organizations of different sizes, sectors and geographical locations to satisfy strategic purposes and manage increasingly complex business environments. However, international joint ventures may fail, and HRM plays an important role in their success or failure. From a systems perspective, IJVs offer several kinds of complexity which may contribute to the generation of conflict and failure. The paper proposes that we explore the role of HRM in IJVs through viable systems theory, especially in relation to knowledge migration and organizational learning. The theory presented distinguishes between the cognitive, organizing and behavioural domains of the IJV as a system in the analysis of the relationship between types of worldview and behaviour in IJVs. It proposes a model of viable knowledge development in IJVs and its relationship to HRM, involving knowledge migration, appreciation and action, leading to organizational learning, and identifies directions for future research.     

Environmentally responsible inventory models: Non-classical models for a non-classical era

Mathematical models of inventory typically include the three inventory associated costs of surplus, shortage and ordering. These classic inventory models are then analysed so as to choose inventory parameters that usually minimise the total cost of operating the inventory system being investigated.Unfortunately, classic inventory models do not provide a meaningful basis for analysing many real and increasingly important practical inventory problems and situations. It is therefore not surprising that over recent years, several authors have discussed these issues in broad terms and suggested that a new paradigm needs to be developed.This paper develops some specific aspects of this discussion. In particular, the paper identifies a range of inventory problems that are not covered appropriately by traditional inventory analysis. One of these is to design responsible inventory systems, i.e. systems that reflect the needs of the environment. The paper then examines the importance of inventory planning to the environment in greater detail. For example, packaging is important, not only because of its costs and the protection that it provides to the inventory items, but also because of its eventual effects on the environment in terms of the use of resources and potential landfill. For similar reasons, waste, which can result from poor inventory management, is highly important. The location of stores is important because location affects transport costs. Thus the influence of the secondary aspects of most inventory models; packaging, waste and location are important but, even more important are the inter-relations with the total system. In particular, the location of the manufacturing plants and the effect that inventory planning has on the logistics chain, potentially have considerable environmental implications. Inventory is part of a wider system.However, until the cost charged for an activity reflects the true environmental cost of that activity, it is likely that decisions will be made on the basis of erroneous data. In that situation, we are faced with either determining the environmental cost of specific actions or to use environmental costs that are somewhat contrived; in which case it may be more sensible to use very different performance measures and models. The paper discusses these ideas and ways in which inventory policies may reassure us with our environmental concerns.