A cross-national comparison and taxonomy of DEA-based hospital efficiency studies

This paper provides the first taxonomy of hospital efficiency studies that uses data envelopment analysis (DEA) and related techniques. We provide a systematic review of 79 such studies published from 1984–2004 that represent 12 countries. Only studies written in English are considered. A cross-national comparison reveals significant differences with respect to important study characteristics such as type of DEA model selected and choice of input and output categories. Compared with US studies, European efforts are more likely to measure allocative rather than technical efficiency, use longitudinal data, and use fewer observations. We take a longitudinal perspective that illustrates the life cycle of this research, as well as its diffusion across disciplines. Our taxonomy can be used by policy makers and researchers to review past, and assemble new, DEA models.     

Principles and Applications of Multilevel Modeling in Human Resource Management Research

Multilevel modeling is important for human resource management (HRM) research in that it often analyzes and interprets hierarchal data residing at more than one level of analysis. However, HRM research in general lags behind other disciplines, such as education, health, marketing, and psychology in the use of a multilevel analytical strategy. This article integrates the most recent literature into the theoretical and applied basics of multilevel modeling applicable to HRM research. A range of multilevel modeling issues have been discussed and they include statistical logic underpinning multilevel modeling, level conceptualization of variables, data aggregation, hypothesis tests, reporting mediation paths, and cross‐level interactions. An empirical example concerning complex cross‐level mediated moderation is presented that will suffice to illustrate the principles and the procedures for implementing a multilevel analytical strategy in HRM research. © 2015 Wiley Periodicals, Inc.     

Analysis of longitudinal data using the hierarchical linear model

The hierarchical linear model in a linear model with nested random coefficients, fruitfully used for multilevel research. A tutorial is presented on the use of this model for the analysis of longitudinal data, i.e., repeated data on the same subjects. An important advantage of this approach is that differences across subjects in the numbers and spacings of measurement occasions do not present a problem, and that changing covariates can easily be handled. The tutorial approaches the longitudinal data as measurements on populations of (subject-specific) functions.     

The Problem of Time Dependent Explanatory Variables at the Context-Level in Discrete Time Multilevel Event History Analysis: A Comparison of Models Considering Mobility Between Local Labour Markets as an Example

The paper deals with the question of how to include time dependent explanatory variables at the context-level in multilevel event history models. In general, context-level explanatory variables in multilevel models are assumed to be time constant. Only time constant context-level explanatory variables perform the task of reducing context-level error variance. Thus, it will be suggested that the analysis should be extended to a three-level model. In this model, time periods of persons constitute level 1 units, time periods of contexts constitute level 2 units and the contexts themselves constitute level 3 units – in which in turn level 2 units are clustered. Considering mobility between local labour markets as an example, four different ways of modelling time varying context-level variables are compared. The result is that the proposed three-level model leads to the most conservative results.     

An inconvenient dataset: bias and inappropriate inference with the multilevel model

The multilevel model has become a staple of social research. I textually and formally explicate sample design features that, I contend, are required for unbiased estimation of macro-level multilevel model parameters and the use of tools for statistical inference, such as standard errors. After detailing the limited and conflicting guidance on sample design in the multilevel model didactic literature, illustrative nationally-representative datasets and published examples that violate the posited requirements are identified. Because the didactic literature is either silent on sample design requirements or in disagreement with the constraints posited here, two Monte Carlo simulations are conducted to clarify the issues. The results indicate that bias follows use of samples that fail to satisfy the requirements outlined; notably, the bias is poorly-behaved, such that estimates provide neither upper nor lower bounds for the population parameter. Further, hypothesis tests are unjustified. Thus, published multilevel model analyses using many workhorse datasets, including NELS, AdHealth, NLSY, GSS, PSID, and SIPP, often unwittingly convey substantive results and theoretical conclusions that lack foundation. Future research using the multilevel model should be limited to cases that satisfy the sample requirements described.     

Fixed and random effects models: making an informed choice

This paper assesses the options available to researchers analysing multilevel (including longitudinal) data, with the aim of supporting good methodological decision-making. Given the confusion in the literature about the key properties of fixed and random effects (FE and RE) models, we present these models’ capabilities and limitations. We also discuss the within-between RE model, sometimes misleadingly labelled a ‘hybrid’ model, showing that it is the most general of the three, with all the strengths of the other two. As such, and because it allows for important extensions—notably random slopes—we argue it should be used (as a starting point at least) in all multilevel analyses. We develop the argument through simulations, evaluating how these models cope with some likely mis-specifications. These simulations reveal that (1) failing to include random slopes can generate anti-conservative standard errors, and (2) assuming random intercepts are Normally distributed, when they are not, introduces only modest biases. These results strengthen the case for the use of, and need for, these models.

     

Information systems offshore outsourcing: managerial conclusions from academic research

In the light of the growing interest raised by Information Systems Offshore Outsourcing both in the managerial world and in the academic arena, the present work carries out a revision of the research in this area. We have analysed 89 research articles on this topic published in 17 prestigious journals. The analysis deals with aspects such as research methodologies, level of analysis in the studies, data perspective, economic theories used or location of vendors and clients of these services; and it additionally identifies the most frequent topics in this field as well as the most prolific authors and countries. Although other reviews about the research in this area have been published, the present paper achieves a greater level of detail than previous works. The review of the literature in the area could have interesting implications not only for academics but also for business practice.     

Can emotional intelligence be trained? A meta-analytical investigation

Human resource practitioners place value on selecting and training a more emotionally intelligent workforce. Despite this, research has yet to systematically investigate whether emotional intelligence can in fact be trained. This study addresses this question by conducting a meta-analysis to assess the effect of training on emotional intelligence, and whether effects are moderated by substantive and methodological moderators. We identified a total of 58 published and unpublished studies that included an emotional intelligence training program using either a pre-post or treatment-control design. We calculated Cohen's d to estimate the effect of formal training on emotional intelligence scores. The results showed a moderate positive effect for training, regardless of design. Effect sizes were larger for published studies than dissertations. Effect sizes were relatively robust over gender of participants, and type of EI measure (ability v. mixedmodel). Further, our effect sizes are in line with other meta-analytic studies of competency-based training programs. Implications for practice and future research on EI training are discussed.     

A Tutorial on Multilevel Survival Analysis: Methods,Models and Applications

Data that have a multilevel structure occur frequently across a range of disciplines, including epidemiology, health services research, public health, education and sociology. We describe three families of regression models for the analysis of multilevel survival data. First, Cox proportional hazards models with mixed effects incorporate cluster‐specific random effects that modify the baseline hazard function. Second, piecewise exponential survival models partition the duration of follow‐up into mutually exclusive intervals and fit a model that assumes that the hazard function is constant within each interval. This is equivalent to a Poisson regression model that incorporates the duration of exposure within each interval. By incorporating cluster‐specific random effects, generalised linear mixed models can be used to analyse these data. Third, after partitioning the duration of follow‐up into mutually exclusive intervals, one can use discrete time survival models that use a complementary log–log generalised linear model to model the occurrence of the outcome of interest within each interval. Random effects can be incorporated to account for within‐cluster homogeneity in outcomes. We illustrate the application of these methods using data consisting of patients hospitalised with a heart attack. We illustrate the application of these methods using three statistical programming languages (R, SAS and Stata).     

Able,willing, and knowing: the effects of HR practices on commitment and effort in 26 European countries

This study extends previous studies of human resource (HR) practices by examining how organizational commitment and work effort are related to the use of HR practices enhancing discretion and skills based on international comparative survey data from 26 European countries. By analyzing individual level data instead of the organizational level data that are examined in prior studies, this article allows investigating whether and how employee perceptions of HR practices are related to their attitudes and behavior. The multilevel analyses largely support the hypotheses that both the intensity and the consistency of these HR practices contribute to organizational commitment and work effort since they enhance the ability of employees and their willingness to cooperate and inform them about the expectations of the organization.     

Occupational Careers and Longitudinal Data: Tools and Perspectives of Research

Over the last years, the start of an increasing number of longitudinal researches and the development of suitable techniques of analysis have made possible the study of an increasing number of questions about social mobility and individual careers. Yet there is not just one way to face the study of careers. For the richness of the information they contain, longitudinal data offer the possibility to carry out different types of analysis according to the different questions of research. In this article four different approaches to the study of work-life careers will be introduced. The objective is twofold. On one hand, the study intends to offer a brief introduction to the most recent and sophisticated techniques that can be used for the analysis of careers. On the other hand, the article aims to point out the theoretical contribution that each technique can give to the debate on social mobility. The main potentialities and limits of the techniques will be stressed too.The techniques introduced in this article represent a fruitful approach for the study of work-life histories and occupational careers. Nevertheless they can be used for the analysis of all kinds of social careers.     

Direct and indirect effects of FDI in emerging European markets: A survey and meta-analysis

We review a large body of literature dealing with the effects of Foreign Direct Investment (FDI) on economies during their transformation from a command economic system toward a market system. We report the results of a meta-analysis based on the literature on externalities from FDI. The studies on emerging European markets covered in our survey report direct and indirect FDI effects weakening over time, similarly as in other FDI destination countries. This is imputable to a publication bias that is detected and to the fact that more sophisticated methods and more controls can be used once a sufficient time span is available. Panel studies are likely to find relatively lower spillover effects. The choice of the research design (definition of firm performance and foreign firm presence) matters. More specific to the sampled studies is the role played by forward and backward spillovers which dominate other channels in driving FDI externalities.     

The Advantages and Limitations of Using Meta-analysis in Human Resource Management Research

This article provides an introduction to the special issue titled “Using meta-analysis to advance research in human resource management.” It begins by defining meta-analysis and considering the advantages and limitations of using this method in HRM research. For instance, we argued that meta-analysis is a valuable tool because (a) it provides a better estimate of the relation that exists in the population than single studies, (b) the estimates are more precise because there is an increased amount of data and statistical power, (c) hypothesis testing and biases associated with publications can be examined, and (d) it helps resolve inconsistencies in research, and identifies potential moderating or mediating variables. However, we also maintained that there are a number of limitations associated with the method. For example, the results of meta-analysis may be limited by the (a) selection of an incomplete set of studies, (b) inclusion of studies that lack internal, external, construct, and statistical conclusion validity, (c) presence of studies with small sample sizes, and (d) heterogeneity of methods used in studies that may lead to erroneous inferences. Finally, the article presents a brief review of the studies included in the special issue.     

A META-ANALYSIS OF FDI AND PRODUCTIVITY SPILLOVERS IN DEVELOPING COUNTRIES

This meta-analysis reviews the intrasector heterogeneity of productivity spillovers from foreign direct investment (FDI) in 31 developing countries through a larger more comprehensive data set. We investigate how the inconsistencies in the reported spillover findings are affected by publication bias, characteristics of the data, estimation techniques, and empirical specification, analyzing 1450 spillover estimates from 69 empirical studies published in 1986–2013. Our findings suggest that reported FDI spillover estimates are affected by publication bias. In combination with model misspecification of the primary studies, the bias overstates the genuine underlying meta-effect, but the meta-effect remains economically and statistically significant. Our results emphasize that spillovers and their sign largely depend systematically on specification characteristics of the primary studies and publication bias. Publication bias is not caused by “best practice” choices. Future research needs to cover more developing countries and to investigate not only whether spillovers occur, but also to explore inside the black box of how spillovers actually emerge.     

Conducting multilevel studies in purchasing and supply management research

Purchasing and supply management (PSM) research commonly covers multiple levels of theory and analysis. The theorizing and simultaneous testing of hypotheses across multiple levels is referred to as multilevel analysis (MLA) and is commonly performed using hierarchical linear modeling (HLM). Researchers in the PSM domain have paid little attention thus far to the topic of multilevel studies. Although MLA holds the potential to yield novel insights into PSM issues, it also generates new challenges for authors and reviewers alike. We contribute to this methodological dialogue by examining reasons for conducting multilevel PSM research and offering practical guidance for increasing its methodological rigor.     

The Multilevel Approach to Repeated Measures for Complete and Incomplete Data

Repeated measurements often are analyzed by multivariate analysis of variance (MANOVA). An alternative approach is provided by multilevel analysis, also called the hierarchical linear model (HLM), which makes use of random coefficient models. This paper is a tutorial which indicates that the HLM can be specified in many different ways, corresponding to different sets of assumptions about the covariance matrix of the repeated measurements. The possible assumptions range from the very restrictive compound symmetry model to the unrestricted multivariate model. Thus, the HLM can be used to steer a useful middle road between the two traditional methods for analyzing repeated measurements. Another important advantage of the multilevel approach to analyzing repeated measures is the fact that it can be easily used also if the data are incomplete. Thus it provides a way to achieve a fully multivariate analysis of repeated measures with incomplete data. This revised version was published online in June 2006 with corrections to the Cover Date.     

Aggregate Versus Disaggregate Data in Measuring School Quality

This article develops a measure of efficiency to use with aggregated data. Unlike the most commonly used efficiency measures, our estimator adjusts for the heteroskedasticity created by aggregation. Our estimator is compared to estimators currently used to measure school efficiency. Theoretical results are supported by a Monte Carlo experiment. Results show that for samples containing small schools (sample average may be about 100 students per school but sample includes several schools with about 30 or less students), the proposed aggregate data estimator performs better than the commonly used OLS and only slightly worse than the multilevel estimator. Thus, when school officials are unable to gather multilevel or disaggregate data, the aggregate data estimator proposed here should be used. When disaggregate data are available, standardizing the value-added estimator should be used when ranking schools.     

R&D,concentration and advertising: A simultaneous equations model

This study employs a simultaneous equations model to test the relationships among industrial R&D spending, market structure and advertising. The R&D data employed are the Line of Business data collected by the FTC and published at the three- and fourdigit SIC level. The results are, in general, complementary to several other recent studies that used data sets involving different degrees of aggregation as well as different measures of research activity.     

Approaching evaluation from a multilevel perspective: A comprehensive analysis of the indicators of training effectiveness

We propose a multilevel framework that addresses the criteria that can be used to assess training effectiveness at the within-person, between-person, and macro levels of analysis. Specifically, we propose four evaluation taxa—training utilization, affect, performance, and financial impact—as well as the specific evaluation metrics that can be captured to examine the facets of each taxon. Our multilevel framework also clarifies the appropriate level of analysis for assessing each criterion variable and articulates when it appropriate to aggregate responses from a lower level of analysis to assess training effectiveness at a higher level of analysis. Finally, we illustrate how training evaluation criteria are interrelated because understanding constructs' nomological network is essential for gauging the depth of knowledge that can be inferred by any evaluation effort.     

Methods for Handling Dropouts in Longitudinal Clinical Trials

This paper focuses on the monotone missing data patterns produced by dropouts and presents a review of the statistical literature on approaches for handling dropouts in longitudinal clinical trials. A variety of ad hoc procedures for handling dropouts are widely used. The rationale for many of these procedures is not well-founded and they can result in biased estimates of treatment comparisons. A fundamentally difficult problem arises when the probability of dropout is thought to be related to the specific value that in principle should have been obtained; this is often referred to as informative or non-ignorable dropout. Joint models for the longitudinal outcomes and the dropout times have been proposed in order to make corrections for non-ignorable dropouts. Two broad classes of joint models are reviewed: selection models and pattern-mixture models. Finally, when there are dropouts in a longitudinal clinical trial the goals of the analysis need to be clearly specified. In this paper we review the main distinctions between a 'pragmatic' and an 'explanatory' analysis. We note that many of the procedures for handling dropouts that are widely used in practice come closest to producing an explanatory rather than a pragmatic analysis.