• Publications
  • Influence
Pointwise and functional approximations in Monte Carlo maximum likelihood estimation
We consider the use of Monte Carlo methods to obtain maximum likelihood estimates for random effects models and distinguish between the pointwise and functional approaches. We explore theExpand
  • 31
  • 3
The monte carlo newton-raphson algorithm
It is shown that the Monte Carlo Newton-Raphson algorithm is a viable alternative to the Monte Carlo EM algorithm for finding maximum likelihood estimates based on incomplete data. Both Monte CarloExpand
  • 52
  • 2
Determination of the unknown age at first capture of western rock lobsters (Panulirus cygnus) by random effects model.
We propose a method for fitting growth curves to multiple recapture data of lobsters when the age at first capture is unknown. The von Bertalanffy growth curve is used to model the growth. To accountExpand
  • 17
The role of unit evaluation, learning and culture dimensions related to student cognitive style in hypermedia learning
Recent developments in learning technologies such as hypermedia are becoming widespread and offer significant contributions to improving the delivery of learning and teaching materials. A key factorExpand
  • 12
The Cgmanova Model
The Completely General MANOVA (CGMANOVA) model may be used to analyze many complex designs including the GMANOVA, EGMANOVA, MSUR models, the multivariate seemingly unrelated growth curve model, andExpand
  • 6
Modelling the missing annuli count in North Pacific spiny dogfish (Squalus suckleyi) by nonlinear mixed effects models
North Pacific spiny dogfish (Squalus suckleyi, Girard 1854) are aged with annuli count on the second dorsal spine. As this spine grows, enamel at the distal tip is worn away producing a zone ofExpand
  • 2
Two-stage generalized simulated annealing for the construction of change-over designs
Kunert (1983) has found sufficient conditions for the optimal estimation of direct treatment effects from change-over designs. In this paper, a two-stage generalized simulated annealing algorithmExpand
  • 1
Constructions for optimal non-strongly-balanced change-over designs
In this paper we use a modification of the Williams's difference sets for complete and quasi-complete Latin squares to construct universally optimal change-over designs for the estimation of bothExpand
  • 2