Related Experiment Video
Updated: Sep 13, 2025
Behavioral Approaches to Studying Innate Stress in Zebrafish
Published on: May 1, 2019
A Tutorial on Conducting and Interpreting a Bayesian Independent T-Test Using Open-Source Software
Helen Evelyn Malone1, Imelda Coyne1
1School of Nursing and Midwifery, Trinity College Dublin, Dublin, Ireland.
Aim:
To demonstrate a worked-out example of a Bayesian independent t-test using open-source software, simulated data, a hypothetical nurse education intervention and a randomised controlled study design. This tutorial explains relevant Bayesian concepts and highlights literature that provides statistically principled justifications for replacing or complementing the frequentist independent t-test with its Bayesian counterpart.
Design:
Bayesian t-test analysis tutorial.
Methods:
A pedagogical framework was applied.
Data Source:
Simulated data generated in Microsoft Excel was uploaded to the Open Science Framework, accessible at: osf.io/4t9gn.
Results:
The Bayesian independent t-test in JASP provides: (1) a Bayes factor quantifying the relative evidence for determining which of two competing theories, that is, the null (H0) or the alternative (H1) hypotheses, better supports the experimental data and (2) the posterior probability distribution, with its median point estimate plus a 95% credible interval, quantifying the magnitude and uncertainty of the effect size estimate.
Conclusions:
This article provides a practical method for nursing and midwifery researchers to conduct Bayesian analysis, offering statistical, practical and ethical advantages, including the application of sequential analysis and optimal stopping rules enhancing research efficiency.
Implications For The Profession And/Or Patient Care:
This article increases awareness of the feasibility and benefits of Bayesian analysis in nursing and midwifery research, emphasising its ease of implementation through open-source software. Clear step-by-step guidance is provided to support its wider adoption and strengthen methodological rigour in nursing and midwifery research.
Impact:
Nursing and midwifery research has traditionally relied upon frequentist statistical techniques, based on p values and confidence intervals. Bayesian methods can: (a) improve nursing and midwifery decision-making with probabilistic evidence and (b) reduce publication bias by avoiding binary interpretation of research results.
Reporting Method:
The methodology aligns with van Doorn et al. (2021) guidelines for conducting and reporting a Bayesian analysis.
Patient Or Public Contribution:
No patient or public contribution.
Related Concept Videos
01:09Statistical Methods to Analyze Parametric Data: Student t-Test and Goodness-of-Fit Test
The Student's t-test is a statistical test that examines if there is a statistically significant difference between the means of two groups. This test is instrumental when dealing with...
01:09Comparing Experimental Results: Student's t-Test
01:16Statistical Hypothesis Testing
Statistical significance measures the probability that an observed result occurred by chance. If this probability, known as...
01:16Statistical Inference Techniques in Hypothesis Testing: Parametric Versus Nonparametric Data
Parametric statistics, as the name suggests, assumes that data follow a specific distribution, often a normal distribution. This assumption enables robust hypothesis testing and estimation. Parametric methods, like the Student's t-test or Goodness-of-fit test, are frequently employed in biostatistics due to their robustness. For instance,...
01:21Introduction to Test of Independence
The test statistic for a test of independence is similar to that of a goodness-of-fit test:
01:25Microsoft Excel: Student's t-Test
To conduct a t-test in Excel, use the T.TEST function or the "Data...