Equivalence Tests: A Practical Primer for t Tests, Correlations, and Meta-Analyses.

Area of Science:

• Psychology
• Statistics

Background:

• Researchers often misinterpret nonsignificant results as evidence of no effect.
• There is a need for robust statistical methods to support the absence of a meaningful effect.

Purpose of the Study:

• To introduce and facilitate the use of equivalence testing in psychological research.
• To provide tools and guidance for implementing the two one-sided tests (TOST) procedure.

Main Methods:

• The article explains the two one-sided tests (TOST) procedure for equivalence testing.
• It highlights the importance of specifying equivalence bounds based on the smallest effect size of interest.
• A practical primer with a spreadsheet and R package is provided for easy implementation.

Main Results:

• Equivalence tests, specifically TOST, allow researchers to statistically reject the presence of worthwhile effects.
• The provided tools enable psychologists to perform equivalence tests and power analyses using standardized effect sizes.

Conclusions:

• Adopting equivalence tests enhances statistical and theoretical inferences in psychological research.
• This approach offers a valuable method for demonstrating the absence of meaningful effects, improving scientific rigor.