For all the subsequent calculations implementing various demographic models (see below) the subtype specific rate was employed as mean fixed rate for models enforcing a strict molecular clock, and as mean fixed rate with exponentially distributed evolutionary rates as prior for models enforcing a relaxed molecular clock [34].
This article has proposed a new LCAR prior for modeling residual spatial autocorrelation, which is flexible enough to capture either spatial smoothness or a distinct step change in the data between adjacent areal units.
The lack of flexibility in the intrinsic and convolution CAR models and the collinearity problems highlighted by Hodges and Reich (2010) and others has motivated us to develop a new localized conditional autoregressive (LCAR) prior for modeling residual spatial autocorrelation, which is presented in Section 3. Existing solutions to these problems have been proposed by Reich et al.
We assumed independent distributions of all of the priors for model parameters and we assumed normal observation noise with unknown variance σ2.
It incorporates external information in a principled way via the prior edge probabilities, transforms the data to reduce spurious correlations, and uses Zellner's g-prior for model parameters, with g estimated from the data.
Priors for model coefficients were based on a normal distribution (with a mean of 0.5 and a precision of 5e-04).
informative priors for model: the prior density of the estimated model parameters (Se 1, Se 2, Sp 1, Sp 2, and π ) was centered at their true values.
It is also important to remember that considerable uncertainty remains in our understanding of HPV natural history which influence our specification of priors for model parameters.
Although several simulation studies on Bayesian IRT models have been discussed in the literature, the studies arbitrarily select non-informative or weakly informative priors for model parameters without a clear elicitation process (e.g., [ 22, 23]).
Two independent runs of four chains were completed for 1 100 000 Metropolis-coupled Markov chain Monte Carlo generations, using the default priors for model parameters, the WAG (amino acids) and HKY85 (nucleotides) model as the rate matrix (fixed) and the gamma model for between-site rate variation.
