Lilian M. de Menezes

Review of guidelines for the use of combined forecasts

Abstract A large literature has evolved in the thirty years since the seminal work on combining forecasts. Despite this, when evaluating performance we only look at measures of accuracy and thus ignore most of the rigour of time series analysis. Furthermore, the output from a combination of forecasts is just a single point estimate which is insufficient for business planning models that take explicit account of risk and uncertainty. In this paper, we review evidence on the performance of different combining methods with the aim of providing practical guidelines based on three properties of the forecast errors: variance, asymmetry and serial correlation. The evidence indicates that using different criteria leads to distinct preferences, and that the properties of the individual forecast errors can strongly influence the characteristics of the combinations errors. We show that a practical approach to combining also requires a degree of judgement on the attributes of error specification.

Flexible Working and Performance: A Systematic Review of the Evidence for a Business Case

Interest in the outcomes of flexible working arrangements (FWAs) dates from the mid-1970s, when researchers attempted to assess the impact of flexitime on worker performance. This paper reviews the literature on the link between FWAs and performance-related outcomes. Taken together, the evidence fails to demonstrate a business case for the use of FWAs. This paper attempts to explain the findings by analysing the theoretical and methodological perspectives adopted, as well as the measurements and designs used. In doing so, gaps in this vast and disparate literature are identified, and a research agenda is developed.

Family‐Friendly Management in Great Britain: Testing Various Perspectives

Five main perspectives on family-friendly management are differentiated by their conceptions about the nature of such management and not just by its assumed predictors. Multivariate analysis of the relationships among a set of family-oriented practices shows that some but not all are used in a systematic way. Regression analysis reveals that employers’ adoption of family-friendly approaches is explained by factors that span all five perspectives, but overall, the organizational adaptation perspective fares best.

Comparing perspectives on high involvement management and organizational performance across the British economy

We identify three perspectives on the link between high involvement management and organizational performance. In particular, we distinguish between high involvement management as a set of complementary best practices, as a set of synergistic practices, and as an underlying orientation or philosophy. We show that no study has investigated all perspectives simultaneously, and those that have tested one or two of them have produced mixed results. Consequently, we design and report a study aimed at testing the three viewpoints, which uses data from a large representative sample of workplaces across the British economy. The results show that, individually, practices tend to be unrelated to performance and do not have significant synergistic relationships. A high involvement orientation as measured by a latent variable that is centred on flexible working is related to the level and rate of change in labour productivity. Yet its association with the level of productivity is in combination with a TQM orientation; for productivity change, it is in combination with variable pay. Moreover, it is discrete from work enrichment practices, which are more strongly associated with labour productivity. Variable pay and the TQM orientation are more strongly related to productivity change than is the high involvement orientation, which is also not associated with labour turnover, but, unexpectedly, it is positively associated with absenteeism.

The reality of flexible work systems in Britain

Recent literature on human resource systems is predominantly focused on their links with performance. In contrast, this study steps back from this vogue and addresses the conceptualization and measurement of human resource systems and examines the nature of the collective use of human resource practices in Britain. Drawing on Baileys (1993) three dimensions of ‘high performance work systems’, this paper uses data from Britains Workplace Employee Relations Survey of 1998 on a full range of human resource practices to examine whether a managerial orientation underlies the triad, and any association that may exist between them and total quality management (TQM). Managerial orientations are unveiled via latent variable analyses and similarities in the adoption of human resource practices are addressed via cluster analyses. The results suggest the presence of managerial orientations that are centred on high involvement and are either integrated or associated with TQM. Although clusters suggest some similarity in the use of Baileys motivational practices, this reflects neither managerial orientations nor high involvement management.

Human resources development practices and their association with employee attitudes: Between traditional and new careers

This is a study of human resource development practices (as perceived by employees) and their association with their attitudes in the context of new career theories. It uses two heterogeneous UK samples of employees from six companies in different industries. Both regression models (from the 1997 and 2000 cohorts) support the mediating role of satisfaction with development on the relationship between perceived significance of development practices and organizational commitment. There are trends in attitudes about the significance of various development factors between cohorts of employees (with respondents in 2000 more inclined to state that self-motivation has been a significant factor in improving their Job performance, and with lateral development also reported as more significant in 2000). A shift in development practices can be observed as a progression from knowledge acquisition via formalized training courses, towards development as a participation model based on challenging work and coaching by an immediate supervisor.

Family-friendly management, organizational performance and social legitimacy

Research on family-friendly practices has concentrated on the predictors of their use, particularly from the perspective of either institutional theory or the high involvement or commitment management vogue. This paper first shows how such perspectives can be used to generate hypotheses about the link between family-friendly management and organizational performance. Second, the paper reports research designed to test these, using data from a national representative sample of workplaces across the British economy, the Workplace Employment Relations Survey of 2004 (WERS2004). The results support the high commitment thesis that family-friendly management will strengthen the relationship between commitment and key economic outcomes, as the relationships between workforce commitment and productivity or quality are stronger in organizations when friendly management is high, which is consistent with social exchange theory. Family-friendly management is not, however, related to the human resource outcomes of labour turnover and absenteeism. Nor does the study find support for the argument that its use in conjunction with high involvement management enhances the performance effects of both. Equally, there is no support for the hypothesis from the institutional thesis that family-friendly management has positive effects on the legitimacy of the organization.

The persistence of specification problems in the distribution of combined forecast errors

Abstract Combinations of several forecasts are now quite commonly used as inputs into business planning models. In such cases, where uncertainty and risk are also being explicitly considered, the statistical specification of the distribution of the combined forecast errors becomes particularly important. In this paper, the shape of the combined forecast error distribution is investigated, non-normality is considered and skewness emerges as a relevant criterion for specifying the method of combination. Subsequently, the stochastic nature of the forecast errors is addressed, and an assessment of current empirical work is presented.

Sequential Bayesian kernel modelling with non-Gaussian noise

This paper presents a sequential Bayesian approach to kernel modelling of data, which contain unusual observations and outliers. The noise is heavy tailed described as a one-dimensional mixture distribution of Gaussians. The development uses a factorised variational approximation to the posterior of all unknowns, that helps to perform tractable Bayesian inference at two levels: (1) sequential estimation of the weights distribution (including its mean vector and covariance matrix); and (2) recursive updating of the noise distribution and batch evaluation of the weights prior distribution. These steps are repeated, and the free parameters of the non-Gaussian error distribution are adapted at the end of each cycle. The reported results show that this is a robust approach that can outperform standard methods in regression and time-series forecasting.

Comparing Fits of Latent Trait and Latent Class Models Applied to Sparse Binary Data: An Illustration with Human Resource Management Data

Abstract This paper addresses the problem of comparing the fit of latent class and latent trait models when the indicators are binary and the contingency table is sparse. This problem is common in the analysis of data from large surveys, where many items are associated with an unobservable variable. A study of human resource data illustrates: (1) how the usual goodness-of-fit tests, model selection and cross-validation criteria can be inconclusive; (2) how model selection and evaluation procedures from time series and economic forecasting can be applied to extend residual analysis in this context.