News & Events

Subscribe to email list

Please select the email list(s) to which you wish to subscribe.
CAPTCHA
This question is for testing whether or not you are a human visitor and to prevent automated spam submissions.
Image CAPTCHA

Enter the characters shown in the image.

User menu

You are here

2 UBC Statistics Students' MSc Presentations

Tuesday, October 4, 2016 - 11:00
Jeff Bone and Creagh Briercliffe, UBC Statistics Graduate Students
Statistics Seminar
Room 4192, Earth Sciences Building (2207 Main Mall)

11am - 11:30am

Speaker:  Creagh Briercliffe, current Statistics PhD student, presenting his UBC Statistics MSc work
 

Title: Poisson Process Infinite Relational Model: a Bayesian nonparametric model for transactional data

Abstract: Transactional data consists of instantaneously occurring observations made on ordered pairs of entities. Visually, it can be represented as a networkor more specifically, a directed multigraphwith edges possessing unique timestamps. In this talk, I present work from my master's thesis, which explores a Bayesian nonparametric model for discovering latent class-structure in transactional data. Furthermore, by pooling information within clusters of entities, this model can be used to infer the underlying dynamics of the time-series data. 
This talk will cover the following: (i) examples of transactional data, (ii) details of the Bayesian model and approximate inference scheme, (iii) procedures used to validate computational correctness and evaluate the model's performance, and (iv) an example of the model applied to real data from historical records of militarized disputes between nations.

--------------------------------------------------------------------------

11:30am - 12:00pm

Speaker:  Jeff Bone, Statistics MSc student

Title:  Instantaneous Dynamics of Functional Data

Abstract:  Time dynamic systems can be used in many applications to data modeling. In the case of longitudinal data, the dynamics of the underlying differential equation can often be inferred under minimal assumptions via smoothing based procedures.

In many cases, one wants to learn the dynamics of a differential equation that incorporates more than just one stochastic process. We propose extensions to existing two-step smoothing methods that allow for the presence of additional functional data arising from a second stochastic process. We further introduce model comparison techniques to assess the hypothesis that there is a significant change in fit provided by this additional process. These techniques are applied to the instantaneous dynamics of mouse growth data and allow us to make comparisons between mice who have been assigned different genetic and physical conditions.