In this webinar series of two 2-hour sessions, we will show how to analyze complex correlated data structures. 

We will start by clearly formulating the research questions and analyzing the data to answer these research questions. We will first show how to explore each research question using Exploratory Data Analysis and then fit mixed effects models and conduct formal statistical tests to confirm any observed effects. We will discuss appropriate model specification to answer the specific questions, model assumptions and model diagnostics techniques. We will demonstrate how small changes in the research questions will change the appropriate visualizations and model specifications. We will also discuss the limitations of the study design as well as of the analysis itself. While R code for hands-on guidance is provided, the primary focus of this webinar will be on the methodological aspects, but implementation aspects will be discussed for a complex case. You will learn:

- Problem formulation and the importance of the prioritization of the research questions;

- Study design considerations, power of the study design and power of the analysis;

- Exploratory data analysis appropriate for each given research question;

- The linear mixed effect model specification appropriate to answer the specific research question, including model diagnostics to validate the model assumptions;

- Post-hoc analysis involving generating tables and graphs from the models;

- Interpretation of the results;

- Discussion on the limitations of the study design and the analysis itself, including a discussion on potential misuse of the p-value.
.

SESSIONS

Your registration covers 2 two-hour sessions, totaling 4 hours of instruction.

Day 1: Tuesday, Feb 7th, 2023, 10:00 am - 12:00pm

Day 2: Thursday, Feb 9th, 2023, 10:00 am - 12:00pm

This webinar will take place online, Zoom link will be provided to participants prior to the webinars.

PRE-REQUISITES

Linear regression, basic understanding of data visualization.

INSTRUCTOR

Biljana Jonoska Stojkova, PhD, is a Senior Statistical Consultant with ASDa, participating in collaborative research, providing statistical consulting services and tailored education on statistical concepts and  analytics tools both on and off campus. She completed her PhD in Statistics at SFU in 2017, where she focused on developing Bayesian algorithms and methods for multi-modal posterior spaces, which were applied to differential equation models, mixture Gaussian models, epidemiological and ecological models. In the previous roles she has gained experience with probabilistic models to determine different patterns of user behavior from chat messages, with development of relational databases and with machine learning algorithms such as supervised and unsupervised learning. In her consulting role Biljana continues to strengthen her skills in problem formulation, study design, grant proposal development, analysis and implementation, and continued education of non-statisticians, giving webinars, workshops and courses on statistical concepts and methodology to various departments, research groups and at teaching hospitals.

FUNDING AND FEES

Fees are collected on a cost-recovery basis only. We strongly encourage UBC Non-Science students and postdocs interested to ask their research supervisors to cover these fees in order to sustain the webinar offerings.

REGISTRATION INFORMATION

General registration opens on Monday, January 16th at 4:00 PM.

Priority will be given to UBC graduate students from Faculty of Science registered in the current academic session. After registering, you will receive confirmation and additional event details. If you experience any difficulty using the online registration tool, please e-mail us at [email protected]. Please email us if you are registered and no longer able to attend this event.

CONTACT

For questions or further inquiries, please contact Biljana Jonoska Stojkova at [email protected]