In simple terms, effect size is the quantifiable differences between two population parameters. While frequently overlooked in many statistical readings, effect size can provide powerful insight into understanding the effectiveness of particular products or methodologies beyond capabilities of simple hypothesis testing, particularly because of its independence from sample size. In hypothesis testing it can only be said if there is an effect, depending on the acceptance of null hypothesis, the effect size extends the limitations of significance testing and allows to measure the effect on populations. When the null hypothesis is said to be true, the effect size is zero, there is no detectable difference between the two populations. However, when the null hypothesis is found to be false, most statistical testing ends there, however, the effect size allows one to explore the differences that the population groups have based through the effect size.
Investigating a variety of measures of effect size, using simulation to describe their sampling behaviour and auditing a sample of application areas to determine how heavily they are used.
The University of Newcastle
Mikayla is currently completing a Bachelor of Mathematics, with majors in both Applied Mathematics and Statistics, at the University of Newcastle. After always having an interest in numbers, patterns and the way they influence the world around us lead to involvement in many STEM programs throughout school. With programs heavily focused on engineering, she considered a path in engineering. However, after a documentary including statisticians, she discovered a world where mathematics and statistics can be utilised autonomously.
Undergoing a university-funded research scholarship last year, has discovered a new love for programming, areas of computational mathematics and algorithms. Since then she’s focused attention towards applications of statistics and mathematics, how they work, what they mean and how they can teach us about the world we live in. Research interests: statistics, optimisation, linear algebra, computational mathematics and machine learning.