The use of statistical distributions for modeling, specifically evaluating the similarity between two probability distributions using various divergence measures, has recently attracted the attention of many of researchers to measure in context of machine learning. Given the importance of the topic, this article introduces several the divergence criteria, including Kullback-Leibler divergence, total variation divergence, alpha divergence, and power divergence, and computes the divergence parameters for two normal distributions. The parameters are estimated using both maximum likelihood and Bayesian methods. In the Bayesian approach, a conjugate distribution is used as the prior, taking into account the behavior of the parameters. Finally, the estimation methods for two normal distributions are evaluated bsased on the mean square error criterion.
Afshar Moghaddam, S. , Nasiri, P. and Yarmohammadi, M. (2025). Estimators of divergence criteria for two normal distributions with Bayesian approach. Journal of Statistical Modelling: Theory and Applications, 6(1), 83-91. doi: 10.22034/jsmta.2026.23601.1191
MLA
Afshar Moghaddam, S. , , Nasiri, P. , and Yarmohammadi, M. . "Estimators of divergence criteria for two normal distributions with Bayesian approach", Journal of Statistical Modelling: Theory and Applications, 6, 1, 2025, 83-91. doi: 10.22034/jsmta.2026.23601.1191
HARVARD
Afshar Moghaddam, S., Nasiri, P., Yarmohammadi, M. (2025). 'Estimators of divergence criteria for two normal distributions with Bayesian approach', Journal of Statistical Modelling: Theory and Applications, 6(1), pp. 83-91. doi: 10.22034/jsmta.2026.23601.1191
CHICAGO
S. Afshar Moghaddam , P. Nasiri and M. Yarmohammadi, "Estimators of divergence criteria for two normal distributions with Bayesian approach," Journal of Statistical Modelling: Theory and Applications, 6 1 (2025): 83-91, doi: 10.22034/jsmta.2026.23601.1191
VANCOUVER
Afshar Moghaddam, S., Nasiri, P., Yarmohammadi, M. Estimators of divergence criteria for two normal distributions with Bayesian approach. Journal of Statistical Modelling: Theory and Applications, 2025; 6(1): 83-91. doi: 10.22034/jsmta.2026.23601.1191
)