“…On the other hand, Kejzlar et al (
2021) used an empirical Bayes approach, wherein instead of placing a prior distribution on the unknown parameters, including
,
,
,
,
, and
, the method estimates these parameters directly from the data. To enhance the efficiency of the MCMC methods, Rumsey and Huerta (
2021) employed the eigenvalue decomposition to approximate the inverse of the covariance matrix in the likelihood (), that is,
, which can be computed in nearly quadratic time. Furthermore, Kejzlar and Maiti (
2023) used variational Bayes inference (Blei et al,
2017), an alternative Bayesian inference to MCMC, which has been widely used to approximate the posterior distribution through optimization as it tends to be faster and easier to scale to massive datasets.…”