Factorial experimental designs have been widely used in many industrial areas. This paper presents a Bayesian approach for missing data estimation for the analysis of a factorial experiment. The proposed methodology could be alternative to commonly used statistical approaches in that it features both the easy implementation and the learning capability of Bayesian approach.

factorial experimental design, missing values, Bayesian approach, parameter estimation.

Received: February 23, 2023; Accepted: April 22, 2023; Published: June 16, 2023

How to cite this article: R. Ajantha, A Bayesian approach for estimation of parameters and missing values in factorial experimental designs, Far East Journal of Theoretical Statistics 67(2) (2023), 199-209. http://dx.doi.org/10.17654/0972086323010

This Open Access Article is Licensed under Creative Commons Attribution 4.0 International License

References:

[1] R. Ajantha and N. Ch. Bhatra Charyulu, Bayesian approach for the estimation of missing responses in randomized block design, Thail. Stat. 20(1) (2022), 227-232.
[2] N. Draper and D. Stoneman, Estimating missing values in un-replicated two-level factorial and fractional factorial designs, Biometrics 20 (1964), 443-458.
[3] C. H. Goulden, Methods of Statistical Analysis, 2nd ed., Wiley, New York, Vol. 318, 1952.
[4] W. G. Cochran and G. M. Cox, Experimental Designs, Wiley, New York, Vol. 202, 1950.
[5] T. W. Anderson, Maximum likelihood estimates for the multivariate normal distribution when some observations are missing, J. Amer. Statist. Assoc. 52 (1957), 200-203.
[6] C. K. Enders, Applied Missing Data Analysis, Guilford Press, NY, 2010.