Dear Frede,
Many thanks for all your help (papers and suggestions/ideas) and I am very
grateful for this.
Yes, you are right, joint Gaussian distribution is best for my situation.
I have had a look at INLA as you suggested and still exploring it to find out
if I can figure out something from there and I will notify the list if I am
successful regarding this hoping that it might help others too in the future.
Also, I have had a looked at geostatsp/geostatinla packages but it seems they
are tailored towards fitting standard spatial regression models without
considering random effects at other higher levels of the data (say children
nested within households in which I wish to accommodate the household specific
random effects in my analysis)
I am still reading more literature on this and I am looking forward to more
suggestions too.
Many thanks.
Kind regards
*****************************************
Justice Moses K. Aheto
PhD Candidate in Medicine (United Kingdom)
MSc Medical Statistics (United Kingdom)
BSc Statistics (Ghana)
HND Statistics (Ghana)
Chief Executive Officer
Statistics and Analytics Consultancy Services Ltd.
Skype: jascall12
Mobile: +447417589148.
[[alternative HTML version deleted]]
_______________________________________________
R-sig-Geo mailing list
[email protected]
https://stat.ethz.ch/mailman/listinfo/r-sig-geo
