Hello,

Given this model output how would I go about extracting the posterior means of the parameters so that I can insert them as starting estimates for the prior parameters ?

I would like to use the same model on some new data (which I believe will share same distributional properties as the original data) and would like to use these estimates are starting values for priors. I do realize that the posterior distribution of the parameters might appear very different from what they started out .

The model is below. Though I have some idea as how to achieve this for the prior for the `os`

fixed effect, but unsure for the rest :(

```
Family: gaussian
Links: mu = identity; sigma = log
Formula: log(ccr + 1) ~ os + s(nvc, m = 1) + (1 + os | c_version)
sigma ~ os
Data: D (Number of observations: 594)
Samples: 4 chains, each with iter = 4000; warmup = 2000; thin = 1;
total post-warmup samples = 8000
Smooth Terms:
Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
sds(snvc_1) 0.39 0.15 0.19 0.76 1.00 2744 3874
Group-Level Effects:
~c_version (Number of levels: 8)
Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
sd(Intercept) 0.08 0.06 0.00 0.24 1.00 2693 3256
sd(osLinux) 0.24 0.16 0.02 0.63 1.00 1885 1963
sd(osWindows_NT) 0.15 0.08 0.04 0.34 1.00 1918 2025
cor(Intercept,osLinux) -0.00 0.48 -0.85 0.88 1.00 2901 3842
cor(Intercept,osWindows_NT) -0.39 0.46 -0.96 0.67 1.00 2202 3385
cor(osLinux,osWindows_NT) -0.18 0.44 -0.89 0.70 1.00 3452 4786
Population-Level Effects:
Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
Intercept 0.61 0.06 0.49 0.73 1.00 5523 4149
sigma_Intercept -0.66 0.05 -0.76 -0.55 1.00 8120 5667
osLinux 0.25 0.13 -0.02 0.52 1.00 3617 3178
osWindows_NT -0.18 0.08 -0.35 -0.02 1.00 5232 4787
sigma_osLinux 0.37 0.07 0.23 0.51 1.00 8210 6322
sigma_osWindows_NT -0.82 0.07 -0.96 -0.67 1.00 7891 6406
Samples were drawn using sampling(NUTS). For each parameter, Eff.Sample
is a crude measure of effective sample size, and Rhat is the potential
scale reduction factor on split chains (at convergence, Rhat = 1).
```

(I believe the idea was covered here: https://osf.io/jrjd2/ )