Collapsibility hypotheses and diagnostic bounds in regression analysis

Deleted-case diagnostic statistics in regression analysis are based on changes in estimates due to deleting one or more cases. Bounds on these statistics, suggested in the literature for identifying influential cases, are widely used.  In a linear regression model for Y in terms of X and Z, the model is “collapsible” with respect to Z if the Y−X relation is unchanged by deleting Z from the model. Deleted-case diagnostic statistics can be viewed as test statistics for collapsibility hypotheses in the mean shift outlier model. It follows that, for any given case, all deleted-case statistics test the same hypothesis, hence all have the same p-value, while the bounds correspond to different levels of significance among the several statistics. Furthermore, the bound for any particular deleted-case statistic gives widely varying levels of significance over the cases in the data set. Received: April 1999     

Estimation of the parameters of log-gamma distribution using order statistics

In this work we propose a technique of estimating the location parameter μ and scale parameter σ of log-gamma distribution by U-statistics constructed by taking best linear functions of order statistics as kernels. The efficiency comparison of the proposed estimators with respect to maximum likelihood estimators is also made.     

Corporate Governance and Firm’s Efficiency: The Case of a Transitional Country, Ukraine

In this study, we look for empirical support for the hypothesis that there is a positive relationship between the levels of corporate governance quality across firms and the relative efficiency levels of these firms. This hypothesis is related to Leibenstein’s idea of X-efficiency. We use the data envelopment analysis (DEA) estimator to obtain proxies for X-[in]efficiency of firms in our sample and then analyze them with respect to different ownership structures by comparing distributions and aggregate efficiencies across different groups. We also use truncated regression with bootstrap, following Simar and Wilson Estimation and influence in two stage, semi-parametric models of production process, Simar and Zelenyuk (2003) to infer on relationship of inefficiency to various indicators of quality of corporate governance, ownership variables, as well as industry and year specific dummies. The data is coming from seven industries in Ukraine. “The entrepreneurship structure itself may be critical, with the classic issue of the separation of ownership from control being regarded as one of the earliest and most important sources of X-efficiency” (Button and Weyman-Jones, 1992, American Economic Review). We would like to dedicate this paper to the memory of Christos Panzios—co-editor who handled our paper to almost the very end, whose suggestions and encouragement have helped us substantially improve our paper.     

Supervisor and coworker support: a source congruence approach to buffering role conflict and physical stressors

The buffering effects of supervisor support on the stressor–strain relationship have proven elusive in prior research (Beehr, Farmer, Glazer, Gudanowski and Nair (2003), ‘The Enigma of Social Support and Occupational Stress: Source Congruence and Gender Role Effects,’ Journal of Occupational and Health Psychology, 8, 220–231). We built on emerging work on source congruence and conservation of resource theory to test a series of hypotheses intended to clarify these mixed findings. Using a sample of 768 employees from 45 organizations in North America, results from moderated regression analyses, showed that the effects of supervisor support on the stressor–strain relationship depended on source congruence. In accordance with our predictions, although we found buffering effects for the physical stressors–strain relationship, we found a reverse buffering effect for the role conflict–strain relationship. These differential buffering effects did not emerge when considering coworker support. We discuss the implications of our results for shedding light on the mixed evidence regarding buffering work stressors reported in prior research.     

Control charts for health care monitoring under overdispersion

An attractive way to control attribute data from high quality processes is to wait till r ≥ 1 failures have occurred. The choice of r in such negative binomial charts is dictated by how much the failure rate is supposed to change during Out-of-Control. However, these results have been derived for the case of homogeneous data. Especially in health care monitoring, (groups of) patients will often show large heterogeneity. In the present paper we will show how such overdispersion can be taken into account. In practice, typically neither the average failure rate, nor the overdispersion parameter(s), will be known. Hence we shall also derive and analyze the estimated version of the new chart.     

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.     

The Majoritarian Compromise in large societies

First, we dwell on the definition of the Majoritarian Compromise in the case of an odd number of alternatives. Then, assuming the Impartial Culture hypothesis we calculate the average maximum welfare achievable by the Majoritarian Compromise procedure and show that this social choice rule is asymptotically stable with the proportion of the number of unstable profiles to the total number of profiles being in the order of ,(¹We write in case there is a positive constant C such that for all sufficiently large values of ) where n is the total number of agents. I am grateful to Prof. Semih Koray for his invitation to visit the Center for Economic Design and the Department of Economics of Boğazi?i University in Turkey during the spring semester of 1999. I appreciate the stimulating discussions with Prof. Murat Sertel about the properties of the Majoritarian Compromise which I had during my stay there. I am also grateful to an anonymous referee whose remarks helped to significantly improve the exposition. A partial support from TüBİTAK NATO PC-B Programme is gratefully acknowledged.     

A Partially Heterogeneous Framework for Analyzing Panel Data

This article proposes a partially heterogeneous framework for the analysis of panel data with fixed T. In particular, the population of cross‐sectional units is grouped into clusters, such that slope parameter homogeneity is maintained only within clusters. Our method assumes no a priori information about the number of clusters and cluster membership and relies on the data instead. The unknown number of clusters and the corresponding partition are determined based on the concept of ‘partitional clustering’, using an information‐based criterion. It is shown that this is strongly consistent, that is, it selects the true number of clusters with probability one as N→∞. Simulation experiments show that the proposed criterion performs well even with moderate N and the resulting parameter estimates are close to the true values. We apply the method in a panel data set of commercial banks in the US and we find five clusters, with significant differences in the slope parameters across clusters.     

Prediction of <Emphasis Type="Italic">k</Emphasis>-records from a general class of distributions under balanced type loss functions

We study the problem of predicting future k-records based on k-record data for a large class of distributions, which includes several well-known distributions such as: Exponential, Weibull (one parameter), Pareto, Burr type XII, among others. With both Bayesian and non-Bayesian approaches being investigated here, we pay more attention to Bayesian predictors under balanced type loss functions as introduced by Jafari Jozani et al. (Stat Probab Lett 76:773–780, 2006a). The results are presented under the balanced versions of some well-known loss functions, namely squared error loss, Varian’s linear-exponential loss and absolute error loss or L ₁ loss functions. Some of the previous results in the literatures such as Ahmadi et al. (Commun Stat Theory Methods 34:795–805, 2005), and Raqab et al. (Statistics 41:105–108, 2007) can be achieved as special cases of our results. Partial support from Ordered and Spatial Data Center of Excellence of Ferdowsi University of Mashhad is acknowledged by J. Ahmadi. M. J. Jozani’s research supported partially by a grant of Statistical Research and Training Center. é. Marchand’s research supported by NSERC of Canada. A. Parsian’s research supported by a grant of the Research Council of the University of Tehran.     

Fixed effects demeaning in the presence of interactive effects in treatment effects regressions and elsewhere

The present paper shows that cross-section demeaning with respect to time fixed effects is more useful than commonly appreciated, in that it enables consistent and asymptotically normal estimation of interactive effects models with heterogeneous slope coefficients when the number of time periods, T, is small and only the number of cross-sectional units, N, is large. This is important when using OLS but also when using more sophisticated estimators of interactive effects models whose validity does not require demeaning, a point that to the best of our knowledge has not been made before in the literature. As an illustration, we consider the problem of estimating the average treatment effect in the presence of unobserved time-varying heterogeneity. Gobillon and Magnac (2016) recently considered this problem. They employed a principal components-based approach designed to deal with general unobserved heterogeneity, which does not require fixed effects demeaning. The approach does, however, require that T is large, which is typically not the case in practice, and the results reported here confirm that the performance can be extremely poor in small-T samples. The exception is when the approach is applied to data that have been demeaned with respect to fixed effects.     

Information Matrices for Non Full Rank Subsystems

Consider the standard linear model Y=X θ + ε. If the parameter of interest is a full rank subsystem K′θ of mean parameters, the associated information matrix can be defined via an extremal representation. For rank deficient subsystems, Pukelsheim (1993) introduced the notion of generalized information matrices that inherit many properties of the information matrices. However, this notion is not a direct extension of the full rank case in the sense that the definition of the generalized information matrix applied to full rank subsystems does not lead to the usual information matrix. In this paper, we propose a definition of the information matrix via an extremal representation that encompasses the full rank and the non-full rank cases. We also study its properties and show its links with the generalized information matrices.     

Stochastic monotonicity of the MLEs of parameters in exponential simple step-stress models under Type-I and Type-II censoring

In two recent papers by Balakrishnan et al. (J Qual Technol 39:35–47, 2007; Ann Inst Stat Math 61:251–274, 2009), the maximum likelihood estimators [^(q)]₁{\hat{\theta}_{1}} and [^(q)]₂{\hat{\theta}_{2}} of the parameters θ ₁ and θ ₂ have been derived in the framework of exponential simple step-stress models under Type-II and Type-I censoring, respectively. Here, we prove that these estimators are stochastically monotone with respect to θ ₁ and θ ₂, respectively, which has been conjectured in these papers and then utilized to develop exact conditional inference for the parameters θ ₁ and θ ₂. For proving these results, we have established a multivariate stochastic ordering of a particular family of trinomial distributions under truncation, which is also of independent interest.     

The Impact of Consumption Hassle on Pricing Schedules

A curious phenomenon in the retail pricing of many product categories (e.g., tuna, frozen orange juice, and tomato paste) is the existence of quantity surcharges. A related curiosity is the existence of both discounts and surcharges within the same product category. To explain the former phenomenon, extant research invokes heterogeneity in consumption parameters, heterogeneity in search costs, or concern for retail price image. To the best of our knowledge, there is no received explanation for the latter phenomenon. We add to this rich stream of work by proposing a novel explanation for quantity surcharges. Our explanation is based on the notion of consumption hassle. We analyze a market that is heterogeneous in a hedonic parameter that influences valuations as well as the effective cost of the consumption hassle. We then derive consumer choices (small pack, large pack, or two small packs) taking into account Individual Rationality (IR) and Incentive Compatibility (IC) constraints. In the absence of consumption hassle, we obtain two segments with one purchasing the small pack and the other purchasing the large pack. Moreover, the optimal pricing for the seller involves quantity discounts. However, with the introduction of consumption hassle, the market potentially splits into three segments: one purchasing the small pack, another purchasing two small packs, and the third purchasing the large pack. Moreover, the optimal pricing for the seller involves quantity surcharges. Overall, our analytical findings offer an additional explanation for the phenomenon of quantity surcharges. More importantly, they offer a rationale for the existence of multiple pricing schedules within the same product category by explicitly recognizing variations in consumption hassle. Copyright © 2012 John Wiley & Sons, Ltd.     

Tests und Konfidenzintervalle für exponentielle Verteilungen und deren Anwendung auf einige diskrete Verteilungen

Zusammenfassung Es werden Verteilungen betrachtet, die (bezüglich irgendeines Ma?es) eine Dichte der GestaltC(ϑ) exp [ϑ x] besitzen. Für solche Verteilungen werden (ein- und zweiseitige) Tests und Konfidenzintervalle mit gewissen Optimalit?tseigenschaften entwickelt, und zwar fürϑ, für die Differenzϑ ₁ −ϑ ₂, sowie für einige Versionen desk-Stichproben Problems. Sodann werden einige Hilfss?tze über den bedingten Erwartungswert und die bedingte Varianz von zweiparametrigen Verteilungen abgeleitet, die bezüglich des einen Parameters reproduktiv sind und eine bezüglich des zweiten Parameters ersch?pfende und vollst?ndige Funktion besitzen. Schlie?lich werden die allgemeinen Ergebnisse auf einige diskrete Verteilungen (Binomial, Poisson, negativ Binomial, Pascal) angewendet und der Zusammenhang mit verschiedenen bekannten Tests diskutiert.

---

Summary Probability distributions are considered which (with respect to any measure) possess a density function of the typeC(ϑ) exp [ϑ x]. For distributions of this type (one and twosided) tests and confidence intervals with some optimal properties are given, namely forϑ, for the differenceϑ ₁ −ϑ ₂, and for several versions of thek-sample problem. Furthermore, some lemmas concerning the conditional expectation and the conditional variance are proved for two-parameter families of distributions which are reproductive in one parameter and possess a complete statistic, sufficient for the second parameter. Finally the general results are applied to some discrete distributions (binomial, Poisson, negative binomial, Pascal) and the relationship to several fairly known tests is discussed.

     

Social support and turnover among entry-level service employees: Differentiating type,source, and basis of attachment

Previous research on social support and turnover has yielded mixed results. To advance research in a more comprehensive manner, the present study examined how turnover is influenced by type of support (emotional or instrumental), source of support (coworker or supervisor), and basis of attachment (affective commitment and constituent attachment as mediators). In the context of entry-level service employees, these relationships were examined with a sample of restaurant servers company-wide from a casual dining restaurant chain in the USA. Coworker emotional support was directly and negatively related to turnover, and coworker instrumental support was directly and positively related to turnover. Furthermore, supervisor emotional support and instrumental support were indirectly related to turnover through affective commitment. When the mediators were considered independently, coworker and supervisor emotional support were both indirectly related to turnover through constituent attachment.     

Effective HR implementation: the impact of supervisor support for policy use on employee perceptions and attitudes

Abstract

Effective implementation of human resource (HR) policies appears to depend on supervisors’ active involvement in the intervention process. Following recommendations of a recent intervention evaluation framework, we examine how perceived supervisor support during the implementation of a work-life intervention helps to change participants’ perceptions of organizational family supportiveness, and how this ultimately changes participants’ engagement and turnover intentions. A three-wave longitudinal study in a professional services firm (N = 434) that has formally involved supervisors in the process of a work-life intervention showed support for our study hypotheses. Supervisor support for policy use influenced employees’ positive work–home culture perceptions, which in turn strengthened employees’ work engagement and diminished their turnover intentions over time. We discuss practical implications and give recommendations on the future design of HR interventions and related policies.     

Interpersonal Targets and Types of Workplace Aggression as a Function of Perpetrator Sex

We investigated the relationship between biological sex of the perpetrator and enactment of two forms of psychological workplace aggression (i.e., overt and covert) against two different interpersonal targets (i.e., supervisors and co-workers). Based on theories of power, we tested hypotheses using two samples (n ₁  = 155, 57% females; n ₂  = 152, 54% females). In comparison to women, results showed that men enacted greater levels of overt aggression against both supervisors and co-workers. Men and women reported enacting equal levels of covert aggression against both supervisors and co-workers. Taken together, these findings suggest that although biological sex of the perpetrator distinguishes levels of enacted overt aggression in the workplace, there are no differences between the sexes on levels of enacted covert aggression in the workplace.     

Learning and relationship orientation: an empirical examination in European museums

• The purpose of this paper is to assess the interrelations between learning orientation, innovation strategy, relationship orientation and economic and social performance in the management of cultural organizations such as museums. We first provide a review of the literature addressing the main constructs involved in the research: learning orientation, innovation, relationship orientation and performance, and we detail the model's hypotheses reflecting the interrelations amongst the proposed variables. Building on extensive literature, a model is developed and empirically tested using survey data collected from 491 European museums in Spain, France, Italy and the UK. Data are analysed through structural equation modelling. In the present study, evidence is found to support the positive and significant link between learning orientation and internal (organizational innovation) as well as external (relationship orientation) changes in museums. Further, we find that organizational innovation and relationship orientation aid the introduction of greater technological developments in these organizations. We also find evidence to support the idea that learning orientation, innovation strategy and relationship orientation impact the economic and social performance of museums. Findings clearly show that achieving organizational objectives through learning processes necessarily entails the introduction of internal changes—innovation—and external relationships—relationship orientation.

Copyright © 2014 John Wiley & Sons, Ltd.     

Notes and Comments: Sup-convolutions of HARA utilities in the affine term structure

Abstract In the financial literature, the problem of maximizing the expected utility of the terminal wealth has been investigated extensively (for a survey, see, e.g., Karatzas and Shreve (1998), p. 153, and references therein) by using different approaches. In this paper, we extend the existing literature in two directions. First, we let the utility function U(.) of the financial agent (who is a price taker) be implicitly defined through I(.)=(U ^′ (.))^–1, which is assumed to be additively separable, i.e., I(.)=∑ _k=1 ^N I _k (.). Second, we solve the investment problem in the general affine term structure model proposed by Duffie and Kan (1996) in which the functions I _k (.), k=1,...,N are associated to HARA utility functions (with possibly different risk aversion parameters), and we show that the utility maximization problem leads to a Riccati ODE. Moreover, we extend to the multi-factor framework the stability result proved in Grasselli (2003), namely, the almost-sure convergence of the solution with respect to the parameters of the utility function. Mathematics Subject Classification (2000): 91B28 Journal of Economic Literature Classification: G11     

Criterion-robust optimal product designs for discrimination between nested response surface models

Consider the problem of discriminating between two rival response surface models and estimating parameters in the identified model. To construct designs serving for both model discrimination and parameter estimation, the M _γ-optimality criterion, which puts weight γ (0≤γ≤1) for model discrimination and 1 − γ for parameter estimation, is adopted. The corresponding M _γ-optimal product design is explicitly derived in terms of canonical moments. With the application of the maximin principle on the M _γ-efficiency of any M _γ'-optimal product design, a criterion-robust optimal product design is proposed.