Search results1 – 6 of 6
The variance targeting estimator (VTE) for generalized autoregressive conditionally heteroskedastic (GARCH) processes has been proposed as a computationally simpler and…
The variance targeting estimator (VTE) for generalized autoregressive conditionally heteroskedastic (GARCH) processes has been proposed as a computationally simpler and misspecification-robust alternative to the quasi-maximum likelihood estimator (QMLE). In this paper we investigate the asymptotic behavior of the VTE when the stationary distribution of the GARCH process has infinite fourth moment. Existing studies of historical asset returns indicate that this may be a case of empirical relevance. Under suitable technical conditions, we establish a stable limit theory for the VTE, with the rate of convergence determined by the tails of the stationary distribution. This rate is slower than that achieved by the QMLE. The limit distribution of the VTE is nondegenerate but singular. We investigate the use of subsampling techniques for inference, but find that finite sample performance is poor in empirically relevant scenarios.
Explores the challenges faced by principals of one‐teacher schools in the New South Wales Department of School Education as they attempt to implement departmental policy…
Explores the challenges faced by principals of one‐teacher schools in the New South Wales Department of School Education as they attempt to implement departmental policy changes during a time of unprecedented structural and organisational change. It examines the substantial international transformations which have taken place in the public sector over the last two decades and their influence on state education in Australia. Highlights the changing relationships between the principals of small schools and senior managers of the department. The study found that over a period of five years the approach to change employed by senior management to have principals implement departmental policy changes altered significantly from an authoritarian approach to one of involvement and partnership.
Financial crime costs the world economy more than $1tn. Yet policing responses continue to apply traditional law enforcement methods to detect, identify and disrupt…
Financial crime costs the world economy more than $1tn. Yet policing responses continue to apply traditional law enforcement methods to detect, identify and disrupt criminal actors in financial systems. The purpose of this paper is to challenge existing thinking around law enforcement practices in financial crime within an Australian context, by presenting an alternative model grounded in management cybernetics and systemic design (SD), which the author terms “cyber-systemics”.
This study reflects on prior research work across cybernetics and SD to suggest an integrated approach as a conceptually useful basis for considering regulation of financial crime, and to demonstrate utility using a case study.
The Fintel Alliance between financial crime regulators and financial institutions in Australia demonstrates a strong connection with, and example of, this study’s cyber-systemic regulatory framework. It will be demonstrated that the form of co-design framework offered under cyber-systemics is both consistent with cybernetic and SD literature, but also a means of avoiding regulatory disconnection in times of change and disruption. This study also invites consideration of how future forms of governance might be structured using cyber-systemics as a conceptual backbone.
This work proposes a novel methodology at odds with traditional law enforcement ways of doing, inevitably requiring a change of regulatory mindset. In addition, this paper is purely conceptual and therefore more research on an empirical basis is required to prove the potential benefits in a real-world regulatory environment.
This is (to the author’s knowledge) the first conceptual exploration of blending SD and management cybernetics in the field of criminal law regulation.
We consider conditional distribution and conditional density functionals in the space of generalized functions. The approach follows Phillips (1985, 1991, 1995) who…
We consider conditional distribution and conditional density functionals in the space of generalized functions. The approach follows Phillips (1985, 1991, 1995) who employed generalized functions to overcome non-differentiability in order to develop expansions. We obtain the limit of the kernel estimators for weakly dependent data, even under non-differentiability of the distribution function; the limit Gaussian process is characterized as a stochastic random functional (random generalized function) on the suitable function space. An alternative simple to compute estimator based on the empirical distribution function is proposed for the generalized random functional. For test statistics based on this estimator, limit properties are established. A Monte Carlo experiment demonstrates good finite sample performance of the statistics for testing logit and probit specification in binary choice models.