1. Areal data & neighborhood graph | 2. Intrinsic Conditional Auto-Regressive (ICAR) models | 2.1 Stan implementation | 3. BYM2 model | 3.1 BYM2 reparameterization for disconnected graphs | 3.2 Stan implementation for both connected and disconnected graphs | 4. Case study: COVID infection estimation | References

Initializing the workflow | 1. Data preparation | 1.1 Preprocessing the sample data | 1.2 Assembling poststratification data | 1.2.1 Linking to ACS | 1.2.2 Importing custom poststratification data | 2. Descriptive statistics | 3. Model building | 3.1 Model specification | 3.2 Model fitting | 3.3 Posterior summaries and diagnostics | 3.4 Saving and loading models | 4. Result visualization | Further reading

Data requirements | Individual-level vs. aggregated data | Required columns and naming conventions | Data modules | Data preprocessing steps | Geographic identifiers and covariates | Poststratification tables

MRPWorkflow | compare_models() | covar_hist() | create_model() | demo_bars() | estimate_map() | estimate_plot() | link_acs() | load_pstrat() | outcome_map() | outcome_plot() | pp_check() | preprocess() | preprocessed_data() | sample_size_map() | MRPModel | check_estimate_exists() | check_fit_exists() | diagnostics() | fit() | formula() | metadata() | model_spec() | save() | stan_code() | summary()

MRP for cross-sectional data | MRP for time-varying data with measurement error | More readings

Overview | Key steps | 1. Data preparation | 2. Descriptive statistics | 3. Model building | 4. Result visualization | Additional resources