Semi-Parametric Time-Series Models: Computation and Simulation

The project will make developments to extending the semi-parametric time-series modelling framework proposed in Fung & Huang (2015) to handle INGARCH (Integer-valued Generalized Autoregressive Conditional Heteroscedastic) models. This will primarily focus on INGARCH(1,1) models on count time-series data. Firstly, extensive background reading will be performed before tackling computation, estimation and simulation of semi-parametric time-series models from various distributions. The project will then move on to applying the semi-parametric model to common examples and applications in INGARCH time-series literature, comparing with parametric estimations given by various authors. Finally, the project will explore relevant software to handle a general INGARCH(p,q) models within the semi-parametric framework.

Kyle Macaskill

The University of Queensland

Kyle has completed his third year of a dual degree of a Bachelor of Mathematics (Statistics) / Computer Science (Machine Learning) at the University of Queensland. Kyle has a passion for mathematical statistics, mathematical analysis and probability theory. In particular, he has taken a strong interest in applications of mathematics in finance, sports and health, as well as combining skills in both mathematics and programming to solve real-world problems. The AMSI Vacation Research Scholarship will provide Kyle with an excellent experience to develop his communication skills and apply concepts for his future academic studies.

You may be interested in

Abhishek Varghese

Abhishek Varghese

Adaptive Tolerance Selection for SMC ABC
Joseph Kwong

Joseph Kwong

SO(n)-invariant Einstein metrics
Juan Avila Molina

Juan Avila Molina

Finding the Body of Minimal Resistance
Daniel Dunmore

Daniel Dunmore

C*-Algebras of Discrete Groups
Contact Us

We're not around right now. But you can send us an email and we'll get back to you, asap.

Not readable? Change text.