A comparison of two model averaging techniques with an application to growth empirics

Parameter estimation under model uncertainty is a difficult and fundamental issue in econometrics. This paper compares the performance of various model averaging techniques. In particular, it contrasts Bayesian model averaging (BMA) — currently one of the standard methods used in growth empirics — with a new method called weighted-average least squares (WALS). The new method has two major advantages over BMA: its computational burden is trivial and it is based on a transparent definition of prior ignorance. The theory is applied to and sheds new light on growth empirics where a high degree of model uncertainty is typically present.     

An alternative model for the analysis of variance with random effects

The standard model for the analysis of variance with random effects implies, for the case of two independent variables, that single effects must be tested not against the error, but against the interaction mean squares. This causes, in comparison with the fixed effects AV, a considerable loss of test power, particularly for the 2 × 2 table. An alternative modelling of the interaction effect is proposed which completely avoids the loss of power.     

Complexity of Innovation in the public sector: A workgroup-level analysis of related factors and outcomes

Complex innovation incorporates more than one innovation type. Using the number of dimensions of the ‘most significant innovation’ implemented by each public employee’s workgroup as a proxy for innovation complexity, this study explores factors that are associated with complexity and examines how complexity affects innovation outcomes. Employing a sample of 4,369 Australian Government employees, we find that the more complex the innovation, the greater the number of barriers a workgroup has to face in its implementation. A broader (but selective) range of idea sources and a more decentralized workplace where both individual and team creativity is encouraged increase the likelihood of implementing complex innovations. Innovation complexity is positively correlated with the variety of beneficial outcomes, suggesting both policy and management interest in supporting complex innovation in the public sector.     

Akaike-type criteria and the reliability of inference: Model selection versus statistical model specification

Since the 1990s, the Akaike Information Criterion (AIC) and its various modifications/extensions, including BIC, have found wide applicability in econometrics as objective procedures that can be used to select parsimonious statistical models. The aim of this paper is to argue that these model selection procedures invariably give rise to unreliable inferences, primarily because their choice within a prespecified family of models (a) assumes away the problem of model validation, and (b) ignores the relevant error probabilities. This paper argues for a return to the original statistical model specification problem, as envisaged by Fisher (1922), where the task is understood as one of selecting a statistical model in such a way as to render the particular data a truly typical realization of the stochastic process specified by the model in question. The key to addressing this problem is to replace trading goodness-of-fit against parsimony with statistical adequacy as the sole criterion for when a fitted model accounts for the regularities in the data.