The effect of estimation method and sample size in multilevel structural equation modeling

Multilevel structural equation modeling (multilevel SEM) has become an established method to analyze multilevel multivariate data. The first useful estimation method was the pseudobalanced method. This method is approximate because it assumes that all groups have the same size, and ignores unbalance when it exists. In addition, full information maximum likelihood (ML) estimation is now available, which is often combined with robust chi‐squares and standard errors to accommodate unmodeled heterogeneity (MLR). In addition, diagonally weighted least squares (DWLS) methods have become available as estimation methods. This article compares the pseudobalanced estimation method, ML(R), and two DWLS methods by simulating a multilevel factor model with unbalanced data. The simulations included different sample sizes at the individual and group levels and different intraclass correlation (ICC). The within‐group part of the model posed no problems. In the between part of the model, the different ICC sizes had no effect. There is a clear interaction effect between number of groups and estimation method. ML reaches unbiasedness fastest, then the two DWLS methods, then MLR, and then the pseudobalanced method (which needs more than 200 groups). We conclude that both ML(R) and DWLS are genuine improvements on the pseudobalanced approximation. With small sample sizes, the robust methods are not recommended.     

Testing structural equation models: the impact of error variances in the data generating process

Yet another paper on fit measures? To our knowledge, very few papers discuss how fit measures are affected by error variance in the Data Generating Process (DGP). The present paper deals with this. Based upon an extensive simulation study, this paper shows that the effects of increased error variance differ significantly for various fit measures. In addition to error variance the effects depend on sample size and severity of misspecification. The findings confirm the general notion that good fit as measured by the chi-square, RMSEA and GFI etc. does not necessarily mean that the model is correctly specified and reliable. One finding is that the chi square test may give support to misspecified models in situations with a high level of error variance in the DGP, for small sample sizes. Another finding is that the chi-square test looses power also for large sample sizes when the model is negligible misspecified. Other results include incremental fit indices as NFI and RFI which prove to be more informative indicators under these circumstances. At the end of the paper we formulate some guidelines for use of different fit measures.     

The impact of desirability and feasibility on entrepreneurial intentions: A structural equation model

There is general agreement that attitudes towards entrepreneurship are determinant factors to decide to be an entrepreneur. In this context, this research is focused on analyzing the relationship between desirability and feasibility on university student’s intentions to create a new firm in Catalonia. A structural equation model supported by Krueger & Brazeal’s Model was tested with different groups of students. The main results reveal most of university students consider desirable to create a new firm, although the perception of feasibility is not positive. Also, there is a statistical significant and positively relationship between credibility and the intention to create a new firm.

Instance sampling in credit scoring: An empirical study of sample size and balancing

To date, best practice in sampling credit applicants has been established based largely on expert opinion, which generally recommends that small samples of 1500 instances each of both goods and bads are sufficient, and that the heavily biased datasets observed should be balanced by undersampling the majority class. Consequently, the topics of sample sizes and sample balance have not been subject to either formal study in credit scoring, or empirical evaluations across different data conditions and algorithms of varying efficiency. This paper describes an empirical study of instance sampling in predicting consumer repayment behaviour, evaluating the relative accuracies of logistic regression, discriminant analysis, decision trees and neural networks on two datasets across 20 samples of increasing size and 29 rebalanced sample distributions created by gradually under- and over-sampling the goods and bads respectively. The paper makes a practical contribution to model building on credit scoring datasets, and provides evidence that using samples larger than those recommended in credit scoring practice provides a significant increase in accuracy across algorithms.     

The impact of on-site mentoring on expatriate socialization: a structural equation modelling approach

While the literature on expatriate adjustment has focused on the importance of back-home mentors and their instrumentality for future career advancement, this research explores the importance of on-site mentors for the effective socialization of expatriates into their current overseas assignments. Using a sample of 179 expatriates located in nineteen countries, this paper presents a structural equation model illustrating the relationships among mentoring received, expatriate socialization and socialization outcomes. Amount of mentoring received positively impacts on expatriate socialization, which in turn positively influences job attitudes, intention to finish the expatriate assignment and expatriate understanding of global business issues. Using Hofstede's typology of national cultures, this research also suggests that the international context of the overseas assignment affects how much on-site mentoring expatriates receive. Specifically, expatriates are more likely to receive mentoring in small power distance, weak uncertainty avoidance and individualistic cultures.     

An empirical test of stakeholder influence strategy models: evidence from business downsizing in Taiwan

Frooman's model of stakeholder influence strategies uses levels of resource dependence to determine the power of stakeholder influence. Our study provides initial empirical tests of his model applied in business downsizing. Data from 18 recently downsized firms in Taiwan, including nine multinational corporations (MNCs), were plotted against the Frooman model. We found that resource-dependence alone as Frooman theorized could not explain the influence strategies that stakeholders (in this case the employees) took in response to firms' downsizing decisions. Further investigation revealed that the institutional factors had a significant effect on how firms structured their downsizing initiatives and hence changed the way the employees reacted to firm decisions. We proposed a new model using both resource-dependence and institutional legitimacy as determinants of stakeholder influence strategy and suggested relationships between these determinants and stakeholder actions. This proposed model has profound research implications for the strategic stakeholder theory, as well as practical implications for human resource management.     

The competitions of time-varying and constant loadings in asset pricing models: empirical evidence and agent-based simulations

Journal of Economic Interaction and Coordination - Under two frameworks of cross-section and time-series factors, we implement asset pricing models to dissect the abnormal returns in the Chinese...     

The impact of corporate entrepreneurship and high-performance work systems on employees' job attitudes: empirical evidence from Greece during the economic downturn

In turbulent times, corporate entrepreneurship (CE) and high-performance work systems (HPWSs) are expected to expand and flourish. However, research on the influences of both CE and HPWSs on employees' job attitudes has generally been neglected. The aim of this study is twofold. First is to investigate the effects of CE and HPWSs on facets of job satisfaction and the three components of organisational commitment. Second is, consistent with the social exchange theory, to examine whether psychological contract act as an important mediator for the CE, HPWSs and employees' job attitudes relationships. Empirical evidence was obtained from 424 employees in the Greek manufacturing industry. Results indicate that both CE and HPWSs positively impact employees' level of job satisfaction and organisational commitment. In addition, we find evidence that psychological contract theory provides a coherent theoretical framework for understanding these relationships. Theoretical and practical implications for HR managers conclude the article.     

The impact of role models on entrepreneurial intentions and behavior: a review of the literature

Despite the presence of the term ‘entrepreneurial role model’ (ERM) in the discourse on entrepreneurship, existing empirical evidence on the effects of role models is rather limited. By investigating 86 published journal articles, we provide a structured overview of the academic research on role models’ effects on entrepreneurial intentions and behavior. We reveal that prior research focuses particularly on different types of role models (by whom), at which stage of life (when) and in which context the exposure to role models occurs. We use these research areas to structure our review. By expanding the understanding of the current state of ERM research, we reveal research gaps and provide future research recommendations. Our work could help policy makers and educators consider the different types of role models, the sociocultural context and the life cycle stage of the participants in structuring their entrepreneurship education programs.

     

The effect of labor supply changes on output: empirical evidence from US industries

In this paper we examine the relationship between labor supply and industry-level output in the context of the specific factors model. Jones (Trade, balance of payment and growth: essays in honor of Charles P. Kindleberger, Amsterdam, pp 3–21, 1971) shows that a rise in the amount of labor in the economy will increase the output in all industries. We empirically show which industry output is predicted to expand more when the size of labor force grows. Unlike the commonly used Rybczynski Theorem (Economica 22:336–341, 1955) of the Heckscher-Ohlin model, the specific factors model shows that a comparison both of labor intensities and labor demand elasticities plays an important role in determining which output expands relatively more when the size of labor force grows. For this purpose, we illustrate the importance of the parameters of the model in determining how changes in the labor supply affect the output change, with special reference to elasticities of substitution in production. We estimate the elasticity of substitution by using CES production function and show how these estimates describe the general equilibrium of production with one mobile factor (labor) and 25 industries of the US economy using data for 1979–2001. We show that the increase in the supply of labor raise output in all industries, but the magnitudes of the increases in some industries are more than others depending on the value of the elasticity of substitution along with factor intensities between industries. The largest output effect occurs for educational, health care and social service, where a 1 % supply of labor increase would raise output 10.5 %. However, the growth in the labor supply has a small impact on output growth in the range of 0.1–0.6 % in agriculture, petroleum, coal product and finance and insurance industries.     

The influence of novelty, flexibility, and synergy of package tours on tourist satisfaction: an analysis of structural equation modeling (SEM)

This study utilizes structural equation modeling (SEM) to explore the positive effects of novelty, flexibility, and synergy of package tours on tourist satisfaction in the Taiwanese package tour industry. Although prior research pays much attention to discuss package tours, none explores the positive effects of the novelty, flexibility, and synergy of package tours on tourist satisfaction in the package tour industry. In order to fill this research gap, this study proposes three novel constructs—novelty, flexibility, and synergy of package tours—to explore their positive effects on tourist satisfaction in the Taiwanese package tour industry. The results of this study show that novelty, flexibility, and synergy of package tours positively affect tourist satisfaction. Therefore, tour operators can enhance the novelty, flexibility, and synergy of their package tours to enhance tourist satisfaction. Furthermore, this study suggests that Taiwanese tour operators should change their business models to adopt dynamic packaging entirely, because novelty, flexibility, and synergy of dynamic packaging are better than those of traditional package tours.     

The impact of skills and performance on earnings: evidence from retail bankers in Portugal

This article contributes to the debate on wage flexibility by estimating the return to skills and performance for a sample of Portuguese retail bankers. If the relevance of skills in the contemporary workplace is unquestionable, their role as the main determinant of earnings is doubtful. The argument of this article is that firms are not adjusting individual wages according to information obtained from on-the-job appraisals subsequent to employment. The banks show a selective approach to rewarding skills and performance, and they still manage as an internal labour market. The idiosyncratic nature of skills may offer a partial explanation for the persistence of this model. However, the evidence points to the presence of hybrid models. While the return to organisational skills reinforces the role of specific skills, the return to cognitive skills suggests that there is competition around general skills in the banking industry.     

The processes of social capital and employee creativity: empirical evidence from intraorganizational networks

The aim of this paper is to extend and elaborate social capital approaches to organizational creativity by identifying different mechanisms that employees can deploy to promote the development of social capital through social interaction, relationship quality and network ties. The findings, based on data from a sample of 382 employees across different areas of expertise and countries in a multinational manufacturing firm, indicate that relationship quality and network ties play a mediating role between social interaction and organizational creativity. The findings of this study contribute to the development of a conceptual theoretical model for explaining the interrelationships among three mechanisms of social capital and organizational creativity performance.     

Loneliness,job satisfaction,and organizational commitment of migrant workers: empirical evidence from China

This study examines the relationship between loneliness, job satisfaction, and organizational commitment of migrant workers. 213 migrant workers completed the survey. This study found that migrant workers are satisfied with their jobs and are committed to their organizations. Contrary to expectation, migrant workers are not lonely. Age and gender do not have influence on loneliness or organizational commitment. Single migrant workers feel lonelier than the married migrant workers. Married and longer-tenured migrant workers are more committed to the organization. There is no significant correlation between loneliness and organizational commitment. This research also indicates that lonelier migrant workers have higher job satisfaction while job satisfaction has significant positive correlation with organization commitment. Implications include having favorable policies to improve the management and services for migrant workers, a need for regulations to safeguard the migrant workers' rights and interests, and providing favorable living arrangements.     

Trade,wages, and the specific factors model: empirical evidence from manufacturing industries in Ghana

This study analyzes the impact of trade on wages in the context of the specific factors model by focusing on the link between trade and the average real wage. A recent paper by Jones and Ruffin (Rev Int Econ, 16:234–249, 2008) shows how one can use the specific factors model to predict how labor should fare from an improvement in the terms of trade. For this purpose, I use annual firm-level data on the manufacturing sector in Ghana during the period 1991–1997. I find that a ceteris paribus increase in the price of exportables in the wood industry would help labor but labor would be hurt by price increases in the food-baker, furniture, textile-garment, and metal-machinery industries.

The impact of managerial quality on organizational performance: evidence from German soccer

In this paper we use a novel panel data set from the German premier soccer league (Bundesliga) as a case to show how variations in managerial compensation impact positively upon organizational (team) success. Using stochastic frontier analysis, we find that a team that hires a better quality coach can expect to achieve a higher league points total by reducing technical inefficiency. However, our results also suggest that the market for head coaches may be allocatively inefficient in that coaches are paid below their marginal revenue products. Copyright © 2008 John Wiley & Sons, Ltd.     

The development of a work-value model assessing the cumulative impact of individual and cultural differences on managers' work-value systems: empirical evidence from French and British managers

This study is the first attempt in Europe to develop an analytical model, based on multidimensional scaling and regression analysis, which enables the operationalization of cultural concepts related to the work context at both the individual and cultural levels of analysis. The development of the model consists of adapting Schwartz's motivational theory of human values (1992, 1994, 1999) to the work context by testing his theory on the domain of work-values and social behaviour in the workplace. For this purpose, two new questionnaires were developed: 1) a new work-value questionnaire based on both Schwartz's and Hofstede's conceptual frameworks – the purpose of this questionnaire was to enable the assessment of the cumulative impact of both cultural and individual differences, and 2) a new Communication Style Questionnaire which enabled us to establish the cross-cultural validity at the behavioural level of the newly developed workvalue dimensions. The model was empirically tested with a population of French and British managers from two different sectors, bank/insurance and pharmaceutical/healthcare organizations. This was done so that the impact of organizational culture differences could be controlled. In total more than 2,500 questionnaires were collected for statistical analysis. The final four work-value scales (Self-enhancement; Individual dynamics; Consideration for others; Group dynamics) elicited through rigorous five-step analysis successfully achieved the purpose of the model's development.     

The impact of working-time reductions on actual hours and wages: evidence from Swedish register-data

The paper studies the impact on actual hours worked and hourly wages of a 5% reduction in working-time for one class of shift workers in Sweden using individual level panel data from employers' payroll records during the second quarter of each year. The main results are that actual hours only declined by approximately 35% of the reduction in standard hours, while hourly wages rose sharply—almost enough to leave monthly wages unaffected. Much larger effects on hours are found when studying the effects of the employees' locally determined scheduled hours. This indicates that a low rate of actual implementation may account for the limited impact on actual hours and suggests that using variation in self-reported, rather than contractual, standard hours may have biased the results of previous studies.     

城市空间结构对交通出行影响研究的进展——单中心与多中心的论争

通过多中心城市空间结构的构建来疏解单中心城市的交通拥挤是城市规划历来的理想,但这种理想正日益受到实证研究的挑战.关于多中心空间结构能否节省通勤距离与通勤时间,存在截然相反的观点.分析表明,两种截然相反的实证结论源于两种不同形成机制的多中心结构,改善交通出行的多中心结构是以就业与居住就地平衡为前提的.