The Advances in Research Designs Symposium (TARDIS) 2015

Presentation videos from TARDIS speakers are now available on YouTube!

TARDIS FlyerThe Office of Research Consulting is pleased to announce the second annual meeting of TARDIS - The Advances in Research Design Symposium. Our theme this year is Alternatives to Statistical Significance Tests. The purpose of the symposium is to expose students and researchers to advances in research methods and analysis.  The presentations are centered on discussing the state-of-the-art in research methods to a wide audience. The schedule for this year is given below. This year we are limiting the number of attendees. So please register soon and encourage your colleagues and students to register. Given the intermediate to advanced nature of the topics, students will be selected based on their completed coursework and advisor's recommendation.

Saturday, September 19, 2015
8:00am - 4:15pm

The Forum at Willis Library
University of North Texas (UNT)

Featured Speakers

Dr. Jeff Gill - Washington University - Why All Social and Behavioral Scientists Should Be a Bayesian

This talk introduces the theoretical and applied foundations of Bayesian statistical analysis in a manner appropriate to social and behavioral scientists. The Bayesian paradigm is ideally suited to the Type of data analysis required in these fields because it recognizes the mobility of population parameters, incorporates prior knowledge that researchers possess, and updates estimates as new data are observed. Examples will be drawn from sociology, political science, economics, psychology, public policy, and anthropology.  Issues in Bayesian Computing will also be discussed.

Dr. Jeff Gill

 

Dr. Warren Thorngate - Emeritus Professor of Psychology, Carleton University, Ottawa, Canada - Testing hypotheses with your fingers: Evidential statistics and ordinal pattern analysis

Most important questions remaining in social science cannot be answered with traditional approaches to statistical analysis. This presentation introduces an alternative approach, Ordinal Pattern Analysis, based on the concept of statistical evidence rather than statistical inference, requiring no sampling or distributional assumptions, and providing easily interpretable, quantitative indices of theory-data fit. Oh, and you can calculate the indices on your fingers. I'll show you how.

Dr. Warren Thorngate

Conference Agenda

Registration

The symposium is free (and includes food and refreshments) for registered participants.

Sponsors

Deans Office, College of Education, University of North Texas
Department of Educational Psychology, University of North Texas
Project TELL (US DOE-H325D110076)

With support from

Toulouse Graduate School, University of North Texas