.png){kind=icon}
.png){kind=icon}
Return
The Computational Preacher: Bayesian Statistics and Computational Methods
.png){kind=icon}
PRE
AI
DOI：10.1177/10497315251388449.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
This paper provides a conceptual overview of Classical/Frequentist and Bayesian statistical inference, focusing on their philosophical foundations and relevance to social work research. While most social workers are trained in Frequentist methods which highlight null hypothesis significance testing, Bayesian inference offers a different framework that assigns probabilities to hypotheses and emphasizes degrees of belief given observed data. The paper explains key differences between the two approaches, explores the role of the Metropolis Algorithm in Bayesian inference, and shows how this algorithm can approximate posterior distributions and credible intervals. The discussion aims to encourage social work researchers to broaden their methodological toolkit by considering Bayesian approaches, especially when addressing substantive applied questions.
Keywords:
Bayesian inference
classical statistics
social work research
Metropolis Algorithm
Journal
R
IF:
1.5
Papers:
107
Citations:
2.8K