Search

BackgroundA socioeconomically disadvantaged childhood has been associated with elevated self-harm and violent criminality risks during adolescence and young adulthood. However, whether these risks are modified by a neighbourhood's socioeconomic profile is unclear. The aim of our study was to compare risks among disadvantaged young people residing in deprived areas versus risks among similarly disadvantaged individuals residing in affluent areas.MethodsWe did a national cohort study, using Danish interlinked national registers, from which we delineated a longitudinal cohort of people born in Denmark between Jan 1, 1981, and Dec 31, 2001, with two Danish-born parents, who were alive and residing in the country when they were aged 15 years, who were followed up for a hospital-treated self-harm episode or violent crime conviction. A neighbourhood affluence indicator was derived based on nationwide income quartiles, with parental income and educational attainment indicating the socioeconomic position of each cohort member's family. Bayesian multilevel survival analyses were done to examine the moderating influences of neighbourhood affluence on associations between family socioeconomic position and sex-specific risks for the two adverse outcomes.Findings1 084 047 cohort members were followed up for 12·8 million person-years in aggregate. Individuals of a low socioeconomic position residing in deprived neighbourhoods had a higher incidence of both self-harm and violent criminality compared with equivalently disadvantaged peers residing in affluent areas. Women from a low-income background residing in affluent areas had, on average, 95 (highest density interval 76–118) fewer self-harm episodes and 25 (15–41) fewer violent crime convictions per 10 000 person-years compared with women of an equally low income residing in deprived areas, whereas men of a low income residing in affluent areas had 61 (39–81) fewer self-harm episodes and 88 (56–191) fewer violent crime convictions per 10 000 person-years than men of a low income residing in deprived areas.InterpretationEven in a high-income European country with comprehensive social welfare and low levels of poverty and inequality, individuals residing in affluent neighbourhoods have lower risks of self-harm and violent criminality compared with individuals residing in deprived neighbourhoods. More research is needed to explore the potential of neighbourhood policies and interventions to reduce the harmful effects of growing up in socioeconomically deprived circumstances on later risk of self-harm and violent crime convictions.FundingEuropean Research Council, Lundbeck Foundation Initiative for Integrative Psychiatric Research, and BERTHA, the Danish Big Data Centre for Environment and Health funded by the Novo Nordisk Foundation Challenge Programme.

The use of fixed alpha levels in statistical testing is prevalent in management research, but can lead to Lindley's paradox in highly powered studies. In this article, we propose a sample size-adjusted alpha level approach that combines the benefits of both frequentist and Bayesian statistics, enabling strict hypothesis testing with known error rates while also quantifying the evidence for a hypothesis. We present an R-package that can be used to set the sample size-adjusted alpha level for generalized linear models, including linear regression, logistic regression, and Poisson regression. This approach can help researchers stop relying on mindless defaults and avoid situations where they reject the null hypothesis when the evidence in the test actually favors the null hypothesis, improving the accuracy and robustness of statistical analysis in management research.

Prediction of waste production is an essential part of the design and planning of waste management systems. The quality and applicability of such predictions depend heavily on model assumptions and the structure of the collected data. Ordinarily, municipal waste generation data are organized in hierarchical structures with municipal or county levels, and multilevel models can be used to generalize linear regression by directly incorporating the structure into the model. However, small amounts of data can limit the applicability of multilevel models and provide biased estimates. To cope with this problem, Bayesian estimation is often recommended as an alternative to frequentist estimation, such as least squares or maximum likelihood estimation. This paper proposes a multilevel framework under a Bayesian approach to model municipal waste generation with hierarchical data structures. Using a real-world dataset of municipal waste generation in Denmark, the predictive accuracy of multilevel models is compared to aggregated and disaggregated Bayesian models using socio-economic external variables. Results show that Bayesian multilevel models outperform the other models in prediction accuracy, based on the leave-one-out information criterion. A comparison of the Bayesian approach with its frequentist alternative shows that the Bayesian model is more conservative in coefficient estimation, with estimates shrinking to the grand mean and broader credible intervals, in contrast with narrower confidence intervals produced by the frequentist models.

We review 10 years of research published in the Strategic Management Journal (SMJ) and find the wide use of log-transformed dependent variables (LTDVs) to be based on statistical myths, with possible detrimental effects for the validity of research findings. We find that many researchers use LTDVs for the wrong reasons, and very often in a way that is misaligned with the hypothesis they intend to examine. Researchers also appear unaware of the severe shortcomings of LTDVs. Using LTDVs implies estimating an exponential model, which represents a non-linear relationship. We identify three myths that are widely followed by researchers: (1) LTDVs should be used to make distributions more normal; (2) linear hypotheses can be tested with LTDVs; and (3) LTDVs are the best way to estimate an exponential model. We call on researchers to exhibit caution when planning to use LTDVs and recommend instead the use of generalized linear models (GLMs) with quasi-maximum likelihood estimation. The superiority of GLMs is demonstrated by two empirical examples from recently published studies.

PurposeThe purpose of this paper is to investigate the role of CEO narcissism in corporate acquisitions with a focus on frequency and size and furthermore to examine the subsequent stock market reaction.Design/methodology/approachThe authors investigate 751 acquisitions made by 158 UK nonfinancial firms and 202 CEOs in the 10-year period 2007–2016. The authors use the ratio of first-person singular pronouns to total first-person pronouns in CEO speech as the main proxy for CEO narcissism but the results are robust to the use of signature size and picture as alternative measures.FindingsThe authors find that increased CEO narcissism is associated with an increase in M&A expenditures, an increase in deal size and a decrease in deal frequency. Thus, the authors find that narcissistic CEOs favor size over frequency (“go big”). Furthermore, the authors find that the stock market reacts less favorably to acquisitions announced by firms run by narcissistic CEOs.Originality/valueThe paper contributes to upper echelon research by investigating the association between CEO narcissism and corporate decisions in a UK setting. More specifically, the paper contributes to the existing literature by investigating how CEO narcissism is associated with corporate acquisitions in terms of the size and frequency of deals and how such irrational behavior is penalized by the stock market. Previous literature has focused on the more broad association between CEO narcissism and M&A expenditures.

For scientific discoveries to be valid—whether in theory or empirically—a phenomenon must be accurately described: The scientist must use appropriate counterfactuals and eliminate competing explanations. Empirical work must also use an appropriate design and method, and empirical claims made about the phenomenon must be correctly characterized. Moreover, valid empirical discoveries must be reliable in the sense that scientists who reexamine the data must be able to reproduce the finding or to replicate the effect from data gathered in a similar context. Only discoveries adhering to the above criteria can be scientifically informative, serve as building blocks for theory, or have policy implications. Unfortunately, as several recent surveys of the literature show, much of the published works in the management and applied psychology fields are uninformative; contributing reasons include several intractable problems in the study design and analysis as well as the failure of the field to adopt open science practices. Against this backdrop, we identify common methodological mistakes made in applied work. We group these mistakes into three major categories: (a) study design and data collection (e.g., fit between hypotheses and methods, design, measurement, open science, literature reviews), (b) data analysis (e.g., data preprocessing, choice of estimators, analysis of data, issues concerning endogeneity, and use of instrumental variables), and (c) diagnostics, inferences, and reporting. We also explain how to avoid these issues, so that published work makes for a useful contribution to the scientific record.

International business researchers commonly estimate proportions, percentages, rates, or fractions – so-called “proportional dependent variables”. In this paper, we posit that two regression strategies are particularly pertinent to the international business field: Tobit and fractional regression. Reviewing recent international business research, we find that, while fractional regression is rarely used, analyses from Tobit regression are often incomplete or erroneously interpreted with consequences for the validity of the reported results. Accordingly, we clarify how researchers should choose between Tobit and fractional regression and interpret their results. We present insights based on simple simulations and data examples with associated Stata code and a decision tree for choosing between types of models for use with proportional dependent variables.

Equal treatment is a key feature of modern bureaucracy. However, several studies have shown that public organizations discriminate against ethnic and racial minorities to different degrees. Which organizational features explain differences in discrimination is largely unknown. This article proposes that organizational performance relates to an organization's likelihood of engaging in employment discrimination and argues that poor-performing organizations tend to be less open to new ideas and that decision makers in such organizations are more prone to stereotyping behavior. The study combines a field experiment in which applications were sent to real job vacancies in 71 Danish public schools with administrative data on the schools. Bayesian analyses show that minority applicants generally faced discrimination but that they experienced a higher callback rate from better-performing schools than from poorer-performing schools. Implications for practice and research are discussed.

Field experiments have long been the gold standard in studies of organizational topics such as ethnic discrimination in recruitment. The recent use of survey experiments, also known as experimental vignettes, suggests that some researchers believe that survey experiments could be used as an alternative to field experiments. In this study we put this notion to the test. We perform a field experiment followed by two survey experiments on ethnic discrimination in recruitment. While the results of our field experiment are consistent with previous evidence on discrimination, one survey experiment concludes no difference between native and immigrant employees while another concludes positive discrimination. These results should invoke caution in researchers wanting to investigate organizational topics using survey experiments.

Increasing immigration is creating multiethnic labor markets in many countries. As convincingly identified by a growing body of research, substantial ethnic discrimination inhibits immigrants' access to employment. The public sector may play an important role in creating labor market integration by setting a good example. Yet, little is known about sector differences in employment discrimination and whether public sector organizations are more or less likely than private firms to ethnically discriminate against prospective employees. Both theory and empirical studies suggest that public sector organizations discriminate less. To investigate these phenomena, we conducted two studies. Study 1 is a field experiment designed to explicitly investigate private and public sector differences in ethnic discrimination in Danish organizations' recruitment processes. Observing extensive discrimination favoring applicants with a Danish name, we find little evidence that the public sector is fairer in hiring decisions. Study 2, which is based on register data, highlights that sector differences and similarities in discrimination are context contingent and depend on organizational size and location. We propose a framework of sector and context interaction to explain organizational differences in ethnic discrimination.

We investigate the long-run stock return performance of European cross-border merger and acquisition (M&A) bidders for the period 2002–2012. Our analysis shows that, though acquirers underperform their matched control firms over the thirty-six months following deal completion, this underperformance is not ascribed to the acquisition event, but rather explained by differences between acquirers and control firms in seven firm characteristics. Results are obtained by applying the augmented buy-and-hold abnormal return (BHAR) method. We enhance the robustness of our results by introducing the propensity score methodology to the analysis in addition to matching based on size and book-to-market equity.

Background A family history of specific disorders (e.g., autism, depression, epilepsy) has been linked to risk for autism spectrum disorder (ASD). This study examines whether family history data could be used for ASD risk prediction. Methods We followed all Danish live births, from 1980 to 2012, of Denmark-born parents for an ASD diagnosis through April 10, 2017 (N = 1,697,231 births; 26,840 ASD cases). Linking each birth to three-generation family members, we identified 438 morbidity indicators, comprising 73 disorders reported prospectively for each family member. We tested various models using a machine learning approach. From the best-performing model, we calculated a family history risk score and estimated odds ratios and 95% confidence intervals for the risk of ASD. Results The best-performing model comprised 41 indicators: eight mental conditions (e.g., ASD, attention-deficit/hyperactivity disorder, neurotic/stress disorders) and nine nonmental conditions (e.g., obesity, hypertension, asthma) across six family member types; model performance was similar in training and test subsamples. The highest risk score group had 17.0% ASD prevalence and a 15.3-fold (95% confidence interval, 14.0–17.1) increased ASD risk compared with the lowest score group, which had 0.6% ASD prevalence. In contrast, individuals with a full sibling with ASD had 9.5% ASD prevalence and a 6.1-fold (95% confidence interval, 5.9–6.4) higher risk than individuals without an affected sibling. Conclusions Family history of multiple mental and nonmental conditions can identify more individuals at highest risk for ASD than only considering the immediate family history of ASD. A comprehensive family history may be critical for a clinically relevant ASD risk prediction framework in the future.

Strategy and management researchers often employ log-transformed dependent variables (LTDVs). Such a transformation means that researchers estimate an exponential model, which implies estimating a ...

Background: Early-life socioeconomic position (SEP) is associated with lifestyle-related diseases in adulthood. However, evidence is lacking on the extent to which adult SEP mediates this association.Methods: Time to either chronic obstructive pulmonary disease (COPD), cardiovascular disease or diabetes were assessed in the Danish population born between 1961 and 1971 (n = 793 674) from age 30 until 2015. Early-life position was assessed in 1981 (by parental) and again at age 30 (own) by four markers; income, occupation, education-divided into high, middle, low-and a combined score for all markers. Using a counterfactual approach, we estimated the total effect of early-life position on disease onset and the degree to which adult position mediated this effect.Results: Results of the time-to-event analysis showed a gradient of all early-life markers on the risk of developing all lifestyle-related diseases. Notably, comparing those in the lowest to the highest educational position, the hazard of COPD was 130% higher for women [hazard ratio = 2.30(95% confidence interval = 2.20-2.41)] and 114% higher for men [2.14 (2.05-2.25)]. About 67%(63-70%) of the effect of educational position was mediated through adult position for COPD, 55% for cardiovascular disease and 50% for diabetes. For the combined score 44, 29 and 33%, respectively, was mediated.Conclusion: About one-tenth to two-thirds of the effect of early-life position is mediated by the position attained in adulthood. The degree mediated depend on the outcome investigated, gender and the social position marker used indicating that alternative pathways may play a key role in developing effective policies targeting early-life behaviours.

Researchers who model fractional dependent variables often need to consider whether their data were generated by a two-part process. Two-part models are ideal for modeling two-part processes because they allow us to model the participation and magnitude decisions separately. While community-contributed commands currently facilitate estimation of two-part models, no specialized command exists for fitting two-part models with process dependency. In this article, I describe generalized two-part fractional regression, which allows for dependency between models’ parts. I show how this model can be fit using the community-contributed cmp command (Roodman, 2011, Stata Journal 11: 159–206). I use a data example on the financial leverage of firms to illustrate how cmp can be used to fit generalized two-part fractional regression. Furthermore, I show how to obtain predicted values of the fractional dependent variable and marginal effects that are useful for model interpretation. Finally, I show how to compute model fit statistics and perform the RESET test, which are useful for model evaluation.

Purpose The mechanisms of knowledge acquisition and their impact on innovation are particularly relevant in the context of rapidly growing emerging markets. The purpose of this paper is to investigate the relationship between firm acquisition characteristics and post-acquisition knowledge exploration and exploitation in the Chinese domestic acquisition market. Design/methodology/approach By using patent and company data of 188 domestic Chinese deals completed between 2002 and 2013, the paper replicates the measurements and analytical methods of the US-based study by Phene, Tallman and Almeida (2012) to address the acquirer’s opportunity to explore and/or exploit external knowledge, its ability to absorb and effectively assimilate such knowledge and thus establish innovations in new technologies. Findings The paper finds support for a positive effect of knowledge uniqueness of the target on the bidder’s post-acquisition exploration. The findings also support that the post-acquisition exploitation is facilitated by the commonality of technological knowledge between the bidder and the target, a result that, although expected, was not be supported in the US-based study. Originality/value This paper qualifies the generalizability of US-based findings about post-acquisition exploration and exploitation in the context of China. It also responds to the call for China-focused knowledge management research by capturing innovation capability building by Chinese firms through domestic acquisitions. Finally, it contributes to the nascent literature on replication in management studies.

Modeling bounded outcomes in the form of a fraction or proportion is tricky in the face of endogeneity. Reviewing SMJ articles from 2007-2016 that included the modeling of a fractional outcome, I f...

PurposeThe purpose of this paper is to systematically assess the empirical support for central relationships in the empirical literature on foreign market entry mode. The reviewing method overcomes methodological limitations in past reviews.Design/methodology/approachThis review provides a systematic assessment of empirical support through a simple quantitative procedure using transparent criteria for article selection. In total, 1,217 statistical tests from 119 studies published in 44 different scientific journals in the period 1997-2013 are examined across a range of dimensions.FindingsFindings question the frequent use of commonly used measures (e.g. advertising intensity) and control variables (e.g. firm size) and suggest that statements about the importance of mode choice for subsidiary performance may be premature. Methodologically, this study identifies critical issues with regard to interpretation of interactions and the entry mode choice set.Research limitations/implicationsThis study limits itself to study the direction of relationships and does not analyze effect sizes. Further, future research may benefit from broadening the entry mode choice by extending the use of multiple outcome models as well as implementing the correct interpretational tools when investigating interactions.Originality/valueThe review is relevant to researchers seeking an overview over the research literature or practitioners interested in the link between mode choice and subsidiary performance.

This article examines the relationship between transformational, transactional, and empowering leadership and the innovative behavior of public sector employees. Instead of investigating their association individually, this article focuses on the interaction between different types of leadership. The analysis is based on a survey from one of Denmark’s largest hospitals (n = 1,647). The main result is that empowering leadership, which focuses on employee capacity, moderates the association between transformational leadership, which is directed at motivation, and innovative behavior. The findings emphasize the importance of not only focusing on a single leadership style but also understanding how they work in combination.

This article provides guidelines and illustrates practical steps necessary for an analysis of results from the multinomial logit model (MLM). The MLM is a popular model in the strategy literature because it allows researchers to examine strategic choices with multiple outcomes. However, there seem to be systematic issues with regard to how researchers interpret their results when using the MLM. In this study, I present a set of guidelines critical to analyzing and interpreting results from the MLM. The procedure involves intuitive graphical representations of predicted probabilities and marginal effects suitable for both interpretation and communication of results. The practical steps are illustrated through an application of the MLM to the choice of foreign market entry mode.

We replicate an important study by Phene, Tallman and Almeida (2012) that investigates the relationship between firm acquisition characteristics and post-acquisition knowledge exploration and explo...

Many outcomes of interest to management and strategy researchers are fractional in nature. Fractional outcomes are attractive to researchers because they are easy to understand and facilitate inter...

Integrating ethnic and racial minorities into the labor market is one of the grand challenges societies face today. In the public sector, this challenge may be especially important as research on r...

Research has found considerable ethnic discrimination in employment decisions of private firms. Yet, little is known about sector differences in employment discrimination and whether public organiz...

This study investigates whether the relationship between mode of international market entry and non-location bound international experience is weaker for firms that are large or have a high foreign...