Distortions of Asymptotic Confidence Size in Locally Misspecified Moment Inequality Models

This paper studies the behavior, under local misspecification, of several confidence sets (CSs) commonly used in the literature on inference in moment (in)equality models. We propose the amount of asymptotic confidence size distortion as a criterion to choose among competing inference methods. This criterion is then applied to compare across test statistics and critical values employed in the construction of CSs. We find two important results under weak assumptions. First, we show that CSs based on subsampling and generalized moment selection (Andrews and Soares (2010)) suffer from the same degree of asymptotic confidence size distortion, despite the fact that asymptotically the latter can lead to CSs with strictly smaller expected volume under correct model specification. Second, we show that the asymptotic confidence size of CSs based on the quasi‐likelihood ratio test statistic can be an arbitrary small fraction of the asymptotic confidence size of CSs based on the modified method of moments test statistic.     

The impact of knowledge properties on international manufacturing transfer performance

Abstract

This paper examines how knowledge properties of a manufacturing activity transfer in international manufacturing network impact performance during the transfer itself and after steady state has been reached. Hierarchical regression was used to test the relationship on survey data from 178 companies. Knowledge properties as a group was significantly affected by both performance measures when controlling for the effects of sender unit experience, sender unit size and receiver unit experience. The activities transferred thus impact the success of the transfer. The control variables of sender unit experience and receiver unit experience have their relatively strongest performance effects after steady state has been reached. Independency was the single knowledge property dimensions with the strongest relative performance effect. This is one of the first survey studies to cover both the performance of the transfer itself and after reaching steady state of manufacturing transfers. Several strands of further research were therefore identified.     

Knowledge and valuation in markets

The purpose of this theoretical article is to contribute to the analysis of knowledge and valuation in markets. In every market actors must know how to value its products. The analytical point of departure is the distinction between two ideal types of markets that are mutually exclusive, status and standard. In a status market, valuation is a function of the status rank orders or identities of the actors on both sides of the market, which is more entrenched than the value of what is traded in the market. In a market characterized by a standard, the situation is reversed; the scale of value is more entrenched than the rankings of actors in the market. In a status market actors need to know about the other actors involved as there is no scale of value for evaluating the items traded in the market independently of its buyers and sellers. In a standard market it is more important to know how to meet the standard in relation to which all items traded are valued. The article includes empirical examples and four testable hypotheses.

---

Market Fashioning

Theory and Society - How do markets come about? This article offers a first systematic analysis of three different ideal types of market fashioning: mutual adjustment, organization, and fields....     

The Mirror to Our Soul? Comparisons of Spontaneous and Posed Vocal Expression of Emotion

It has been the subject of much debate in the study of vocal expression of emotions whether posed expressions (e.g., actor portrayals) are different from spontaneous expressions. In the present investigation, we assembled a new database consisting of 1877 voice clips from 23 datasets, and used it to systematically compare spontaneous and posed expressions across 3 experiments. Results showed that (a) spontaneous expressions were generally rated as more genuinely emotional than were posed expressions, even when controlling for differences in emotion intensity, (b) there were differences between the two stimulus types with regard to their acoustic characteristics, and (c) spontaneous expressions with a high emotion intensity conveyed discrete emotions to listeners to a similar degree as has previously been found for posed expressions, supporting a dose–response relationship between intensity of expression and discreteness in perceived emotions. Our conclusion is that there are reliable differences between spontaneous and posed expressions, though not necessarily in the ways commonly assumed. Implications for emotion theories and the use of emotion portrayals in studies of vocal expression are discussed.     

What is Qualitative in Qualitative Research

Qualitative Sociology - What is qualitative research? If we look for a precise definition of qualitative research, and specifically for one that addresses its distinctive feature of being...     

Patterns of working and living conditions: a holistic, multivariate approach to occupational health studies

The objective of the study was to develop a multivariate approach to occupational health studies that is: capable of identifying groups with similar working conditions; relevant for studies of associations between working and living conditions and health; and an appropriate basis for preventive actions. Data at the individual level were obtained through measurements, observations, interviews and questionnaires, and at the organizational level, through interviews with managers. Cluster analyses were applied with the purpose of identifying groups of individuals with small, within-group differences. Eighty work sites and a sample of employees at each site were strategically selected. The study group comprised 203 men and women, and was characterized by large variation. The final analysis produced eight clusters of individuals, denoted according to their best-defining characteristic, i.e. 'decent', 'boundary-less', 'locked', 'exposed', 'heavy and monotonous', 'changed', 'mobile' and 'restrained'. The clusters differed with regard to 'what' characterized working conditions, 'where' on the labour market they were found, and 'who' clustered in these groups. The holistic approach revealed conditions that were important for health and had higher explanatory power in relation to ill-health than applying socio-economic groupings or the demand-control-support model. It showed how psychosocial, ergonomic-physical and occupational hygiene factors combine and interact to create settings with different risks of ill-health. The chosen strategy is recommended for future occupational health studies and is particularly suitable as guidance for preventive actions relevant to specific clusters of working and living conditions.     

On the Asymptotic Sizes of Subset Anderson–Rubin and Lagrange Multiplier Tests in Linear Instrumental Variables Regression

We consider tests of a simple null hypothesis on a subset of the coefficients of the exogenous and endogenous regressors in a single‐equation linear instrumental variables regression model with potentially weak identification. Existing methods of subset inference (i) rely on the assumption that the parameters not under test are strongly identified, or (ii) are based on projection‐type arguments. We show that, under homoskedasticity, the subset Anderson and Rubin (1949) test that replaces unknown parameters by limited information maximum likelihood estimates has correct asymptotic size without imposing additional identification assumptions, but that the corresponding subset Lagrange multiplier test is size distorted asymptotically.     

Finite Sample Properties of the Two-Step Empirical Likelihood Estimator

ABSTRACT

We investigate the finite sample properties of two-step empirical likelihood (EL) estimators. These estimators are shown to have the same third-order bias properties as EL itself. The Monte Carlo study provides evidence that (i) higher order asymptotics fails to provide a good approximation in the sense that the bias of the two-step EL estimators can be substantial and sensitive to the number of moment restrictions and (ii) the two-step EL estimators may have heavy tails.