Introduction | Age stratification example | Geography | Disease subtype | Conclusion

Download jar files using Maven | Caching of Java libraries | Using local repository Jar files in rJava | Java compilation | Step 0: write some java code | Step 1: compile the jar | Step 2: use the jar | Options and configuration | What else could you do? | Further work

Background | Simulation

Background | Simulation with weekly data

Background | Specifying time varying parameters | Step and linear functions | Random functions | Delay distributions and delay RNGs | Periodic functions | Simulation cookbook | Count based simulations | Basic growth rate possion model with ascertainment noise. | Seasonal outbreak using a reproduction number | Line list simulations | Basic outbreak with delays and censoring | Variant introduction: Alpha example | Two variants: Delta outbreak | Over-dispersion | Age stratification & contact matrices | Future steps

Line lists vs. time series | Coercing data into ggoutbreak format | A simple linelist | Count data | More detail on time periods | Times in ggoutbreak and conversion of line-lists | Aggregating time series datasets.

Incidence and growth rate from case positive counts | Reproduction number estimation | Prevalence and growth rate from test positivity rates | NHS COVID app

Introduction | Methods | Numerical stability | Infectivity profile uncertainty | Implementation | Results | Conclusion

Conclusion

COVID-19 proportions in England | Multinomial proportions model. | Binomial proportions model

Incidence Poisson rate model | Proportion model | Pre test probability

Alternative resampling | Conclusion | Addendum

Locfit models | Simple incidence test with a poisson model | Multinomial data | Poisson model | One versus others Binomial model | Multinomial model | GLM models | Binomial model

Introduction | Step 1: Define the Model, Data, and Priors (Recap) | Step 2: Run ABC-Adaptive | Step 3: Visualize the Results | Step 4: Diagnose Convergence | Step 5: Visualize Parameter Evolution | Step 6: Check Parameter Correlations | Conclusion

Introduction | Step 1: Define the Simulation Function | Step 2: Define the Scoring Function | Step 3: Generate Observed Data (Ground Truth) | Step 4: Visualize the Observed Data | Step 5: Define Prior Distributions | Step 6: Run ABC Rejection Sampling | Step 7: Plot the Results | Conclusion

Introduction | Reparameterised statistical distributions | Core Functions | Selected Examples | List of Additional Families | Specialized Random Number Generators | Distribution family S3 class: | Creating dist_fns Objects | From Standard Families | Creating Multiple Distributions with pmap_dist_fns | Manipulating dist_fns Objects in Data Frames | Applying Transformations: Truncation Example | Combining dist_fns: Mixture Distributions | Fitting Empirical Distributions | From Quantiles using empirical_cdf | Ensemble of Quantile-Based Distributions as a Mixture | From Samples using empirical_data | Weighted Sample Fitting | Using wquantile for Quantiles from Weighted Data | Conclusion

Introduction | Step 1: Define the Model and Data (Recap) | Step 2: Inform Scoring Weights (Optional but Recommended) | Step 3: Run ABC-SMC | Step 4: Visualize the Results | Step 5: Diagnose Convergence | Step 6: Visualize Parameter Evolution | Step 7: Check Parameter Correlations | Conclusion

Introduction | 1. Writing the Simulation Function (sim_fn) | Inputs | Output | Example | 2. Writing the Scoring Function (scorer_fn) | Combining Scorer Outputs and Comparison to Observed Scores | Score Weights (scoreweights) | 3. Debugging and Parallelisation | 4. The Convergence Function (converged_fn) | Inputs to converged_fn | Output of converged_fn | The default_termination_fn | 5. Writing a Custom Convergence Function | Structure | Example: Convergence Based on ESS and Distance Reduction | Example: Convergence Based on Parameter Variance | Key Considerations for Custom Functions | Conclusion

Background | Maps and capacity data | Containment | Intersection | Areal interpolation | Geography as network | Preview a map with points of interest overlaid | Estimating the catchment areas of hospitals. | Displaying e.g. London as a popout | Facetted plot labelling

Tracking data provenance | Basic operation - comments and stratification | Status - Further analysis in the workflow | Filtering, exclusions and inclusions | Excluded data | Formatting options | Advanced handling of the history graph. | Combined data flows

Global configuration | Formatting options | Recording options | Naming conventions for groups | Default text | Subgroup count | Exclusions | Reporting exclusions which do nothing | Maximum groupings | Verbose output

Maximum groupings

Background | Installation | Features | Simulation | Models: | Time varying parameters: | Scoring | Estimation methods | Infectivity profile estimation | Poisson rate models | Binomial proportion models | Multinomial proportion models | $R_t$ estimation methods: | EpiEstim wrapper | Reimplementation of Cori method | Wallinga and Lipsitch growth rates method | $R_t$ from modelled incidence | Bootstrapped renewal eqaution

Rationale | Dispatch | Grouping based dispatch

Rationale | Defining an interface | Extension and composition | Grouping | Documentation | Type coercion | More complex type constraints | Default dataframe values | Conclusion

Automating iface specifications | Dataframe documentation | roxygen2 documentation

Configuration and formatting options | Column labelling | Content format | Summary types | Customising the number of decimal places | Summary format customisation | Custom layouts | Footer customisation

Formula versus tidyselect interface | Simple population description example | Comparing the population by intervention | Analysis of missing data | Conversion of discrete data | Making missing factors explicit: | Non biomedical data

Toy example

CONSORT statement | Excluded data | Tagging the pipeline | Reusable functions | References

Nesting & list columns | Conclusion

Toy example

Joins across data sets | Unions