Package: bml 0.12.0

1. What's the difference between a multiple-membership model and a conventional multilevel model? | 2. What's the difference between a conventional MMMM and the extended MMMM implemented in bml? | 3. When should I use bml instead of other multilevel modeling packages? | 4. What outcome types and distributions does bml support? | 5. How do I specify the weights, and what are the scale and ar options? | 6. How do I fix parameters to known values? | Main equation and hm() blocks: Using fix() | Weights w(): Omitting parameters | 7. I get "Error in node w.1[...]: Invalid parent values" — what does this mean? | 8. I'm coming from brms — what maps onto what?

1. Install JAGS | 2. Install bml R package | Option A: Install from CRAN | Option B: Install development version from GitHub | Troubleshooting

1. Overview | 2. Running Example | 3. Notation and Data Structure | 4. The Extended Multiple-Membership Multilevel Model | 4.1 Full Model Specification | 4.2 Group-Level Effect | 4.3 Hierarchical Nesting-Level Effect | 4.4 Aggregated Member-Level Effect | 5. Parameterizable Weight Functions | 5.1 Conventional MMMM: Fixed Weights | 5.2 Extended MMMM: Parameterizing Weights | 5.3 Testing Alternative Aggregation Mechanisms | 6. Emergent Aggregation Functions | 6.1 User-written reductions: the expression DSL | 6.2 Named blocks and interactions | 7. Generalized Outcomes | 8. Variance Decomposition and Intraclass Correlation | 8.1 Intraclass Correlation Coefficients (ICC) | 9. Extensions | 9.1 Multiple MM Blocks | 9.2 Autoregressive Random Effects | 9.3 Complementary Membership Groups | 10. Comparison with Conventional MMMM | 11. Model Assumptions | 12. Estimation | 13. Further Information

1. All friends, or just your best friend? (network regression) | Model 1: linear-in-means | Model 2: best friend only | Comparing the two models | Cross-validation: which aggregation does the data prefer? | 2. Air quality and home values (spatial regression) | Data and spatial weights | Baseline bml: equal weights | Parameterised weights: similarity across covariates | Do the weights actually vary with similarity? | Benchmark: spatial Durbin error model | Model comparison | 3. Political parties and the survival of coalition governments (micro-macro regression) | The data | Equal-weight baseline | Letting weights vary across parties | Prime minister's party against equal weights | Prime minister against seat share | Comparing the models | MCMC diagnostics | brms-style accessors | 4. Does the average matter, or the spread? (emergent features) | 5. What is the aggregation function? (estimating f itself) | 6. Does context change the aggregate's effect? (cross-level interaction) | 7. Heterogeneous member effects (explained and residual)

Introduction | Installation | Basic Example | Understanding the Data Structure | Model 1: Basic Multiple-Membership Model | Model 2: Parameterizing the Weight Function | Model 3: Beyond the sum — emergent features | Visualizing Results | Next Steps | Key Concepts