THIS README IS FOR THE INLA_w_MCMC DIRECTORY, EACH SUB-DIRECTORY WILL ALSO CONTAIN IT'S OWN README FILE.

THIS DIRECTORY CONTAINS ALL CODE AND IMPLEMENTATIONS OF THE INLA WITHIN MCMC, UNIVARIATE AND MULTIVARIATE, TO THE US CITY MOTOR VEHICLE THEFT AND FOR A QUICK SIMULATION STUDY AND TIMING TEST.

THESE DIRECTORIES WILL CONTAIN THE SIMULATED DATA OR THE INLA OR INLA WITHIN MCMC OUTPUTS BUT NOT THE US CITIES COUNT DATA OR THE MESHES. HOWEVER, THROUGH THE DATA AND NECESSARY CODE IN THE DATA DIRECTORY AND ITS SUB-DIRECTORIES, THE REQUIRED DATA FOR THESE IMPLEMENTATIONS CAN BE RE-CREATED.

- IwMFUNCTIONS: this contains the functions and sub-functions for the implementation of the Univariate and Multivariate INLA within MCMC algorithms, where the Multivariate IwM code allows the covariate effects to be shared between the different study regions.

- USCITIESIwM: this contains the R script that will run the Univariate or Multivariate IwM algorithm on the Los Angeles or Los Angeles and New York motor vehicle theft data, respectively. It will contain the results for only the full Metropolis-Hastings output as well as the BMA output with the burn-in runs removed from the MCMC iterations and then used to produced the BMA posterior marginals. Code for, and the results of, running INLA-only implementations to each city individually are also present. We also have plots for the LA and NYC data sets at the resolution of the grid and mesh that we use for the implementation of the INLA, Unvariate and Multivariate IwM algorithms.
	-- *_MH_*.rda: this denotes the output from the Metropolis-Hastings step only, where the number of runs is included in the filename.
	-- *_BMA_*_*.rda: this denotes the output from the BMA 		implementation, the output includes the MCMC chains with 		the removed burn-in iterations as well as the INLA marginals for the remaining iterations and the final approximated posterior marginals for the fixed, hyperpar (internal rep., transformed internal rep. and INLA output external rep.) as well as the combination of the MH samples with the marginals for its respective fixed effect (only for the Multvariate outputs of course and for the non-base study region). The total iterations of the original MH run as well as the number of iterations taken as a burn-in are given in the filename.

- IwMSIMSTUDY: this contains the R script and outputs from the implementations of the Multivariate INLA within MCMC algorithm to the simulated scenarios on a regular polygon across two study regions as well as the outputs from the INLA-only runs to the separate study region data sets. The naming convention for the INLA within MCMC outputs are as for the US Cities.

- IwMMULTICITYTIMINGTEST: this contains a rough R script for the testing of the speed of the Multivariate INLA within MCMC between two US cities and 3 US cities and also comparing how the mclapply() mcores variable is set. This directory also contains the results from 10 iteration tests for the time taken.

- IwMOUTPUTSUMMARY: this contains an R script with functions to create data frames for producing summary tables and plots for the results of the INLA within MCMC algorith, univariate or multivariate with the possibility of including the results from an INLA-only implementation for the comparison of the results between algorithms.