Trichotomous Bayes Factor Analysis [Tri–BFA]: A Post Hoc Probability Confirmatory Data Analysis Assurance Model Designed to Determine the Validity, Viability, and Verifiability of E–Learning Hypotheses

Vol. 6  Issue 1
Year: 2015
Issue:Sep-Nov
Title: Trichotomous Bayes Factor Analysis [Tri–BFA]: A Post Hoc Probability Confirmatory Data Analysis Assurance Model Designed to Determine the Validity, Viability, and Verifiability of E–Learning Hypotheses
Author Name:James Edward Osler
Synopsis:

This paper presents meticulous knowledge about ‘Tri–Factor Analysis: A Model and Statistical Test of Performance, Efficacy, and Content for Electronics and Digital Learning Ecosystems’. This narrative provides an epistemological rational for the use of Bayesian probability statistical testing models for E–Learning via the Tri–Squared Test and subsequent TRINOVA Post Hoc test methodology. TRINOVA is an in–depth [Trichotomous Nomographical Variance] statistical procedure for the internal testing of the transformative process of qualitative data into quantitative outcomes through the Tri–Squared Test. Tri–Bayes Factor Analysis (or “Tri–BFA”) is an advanced statistical measure that is designed to check the validity and reliability of a Tri–Squared Test hypothesis using Bayesian probability. This is a novel approach to advanced statistical post hoc Tri–Squared hypothesis testing. It adds merit and considerable value to the mixed methods approach of research design that involves the holistic combination and comparison of qualitative and quantitative data outcomes. A sequential series of steps using the Tri–Squared Test, TRINOVA, and Tri–BFA mathematical models are provided to illustrate the entire process of advanced statistical Trichotomous inquiry.