Introduction | Alternative model engines | Supported families by modeling engine | Reference DLNM design | Fixed-effect reference model | Conventional random effects | GAM estimation | GAMM estimation | Spatially autocorrelated effects with spaMM | Spatially dependent fields | Independent spatial fields by year | Independent spatial fields across epidemiological replicates | Gaussian generalized least squares | MCMC estimation with brms | Bayesian DLNM with bdlnm | Direct INLA versus B-DLNM | Outputs shared by INLA and B-DLNM | Outputs specific to B-DLNM | Model objects

What does EpiExposure do? | The EpiExposure workflow | Organizing exposure profiles | Inspecting the example dataset | Visualizing exposure profiles | Defining exposure-lag structures | Checking identifiability and numerical stability | Building the epidemic-level design | Preparing the disease response | Fitting the first DLNM | Predicting one complete exposure profile | Where to go next

Introduction | Load example data | Why model selection matters | Searching candidate models | Run the model search | Ranking models | Top-performing models | Visualizing model performance | Understanding validation metrics | Concordance Correlation Coefficient | Root Mean Square Error | Mean Absolute Error | Inspecting specific models | Why use ensembles? | Selecting ensemble candidates | Unweighted ensemble | Inspect results | Weighted ensemble | Stacked ensemble | Comparing ensemble strategies | Visualizing ensemble predictions | Choosing a model-level ensemble strategy | Lag-contribution ensembles | Why construct a lag ensemble? | [ECI_ | Constructing unweighted and weighted lag ensembles | Inspecting selected models and weights | Inspecting ensemble lag contributions | Visualizing signed lag contributions | Visualizing relative lag contributions | Using strict exposure availability | Avoiding optimistic ensemble evaluation | Summary

Introduction | Preparing the example model | From effect interpretation to sensitivity analysis | Generating controlled exposure gradients | Temperature sensitivity | Generating a temperature gradient | Predicting responses along the gradient | Visualizing the response curve | Why sensitivity analysis? | Computing temperature sensitivity | Interpreting sensitivity | Visualizing temperature sensitivity | Elasticity analysis | What is elasticity? | $$E(x) | Visualizing elasticity | Identifying critical regions | Extracting critical points | Visualizing critical points | Comparing environmental drivers | Rainfall sensitivity | Generating a rainfall gradient | Predicting rainfall scenarios | Computing rainfall sensitivity | Leaf wetness sensitivity | Generating a leaf wetness gradient | Predicting leaf wetness scenarios | Computing leaf wetness sensitivity | Combining sensitivity results | Visualizing uncertainty realizations | Summarizing sensitivity uncertainty | Visualizing summarized sensitivity | Comparing sensitivity across variables | Decision-support interpretation | Example interpretation | Interpretation checklist | Summary | Next steps

Introduction | Preparing the example model | Complete exposure profiles | Simulating exposure profiles | Why simulate exposures? | Simulating a background process | Simulating structured exposure events | Predicting disease outcomes | Deterministic prediction | Prediction uncertainty | Scenario simulation | Why construct scenarios? | Defining epidemiological periods | Generating candidate scenarios | Predicting scenario outcomes | Summarizing scenario predictions | Visualizing summarized scenario predictions | Returning individual prediction samples | Visualizing individual prediction samples | Scenario surfaces | Comparing predictions | Comparing complete simulated profiles | Defining Scenario A | Defining Scenario B | Defining Scenario C | Defining Scenario D | Visualizing the candidate profiles | Comparing the exposure profiles | Comparing temperature profiles | Comparing rainfall profiles | Comparing leaf wetness profiles | Visualizing the exposure differences | Comparing the expected outcomes | Summarized comparisons | Draw-specific comparisons | Visualizing comparison uncertainty | Comparing one exposure at a time | Interpreting simulation and prediction outputs | Summary | Next steps

Introduction | Preparing the example model | Reference conditions and effect measures | Lag-specific effects | What are lag-specific effects? | Estimating lag-specific effects | Visualizing lag-specific effects | Local sensitivity and delta effects | Period-specific effects | Why summarize lag periods? | Defining epidemiological periods | Estimating period-specific effects | Returning uncertainty samples | Comparing period-specific effects | Reducing the fitted DLNM association | Why reduce an exposure-lag association? | Overall cumulative exposure-response association | Visualizing the overall reduction | Exposure-response association at a selected lag | Lag-response association at a selected exposure value | Summary versus sample output | Interpreting reduced associations | Exposure Cumulative Impact | Why use ECI? | Calculating ECI | Interpreting ECI | Comparing raw and weighted exposure profiles | Decomposing ECI by lag | Why decompose ECI? | Computing lag contributions | Inspecting lag contributions | Plotting the contribution profile | How the summaries complement one another | Interpretation checklist | Next steps

Introduction | Preparing the epidemiological model | Translating disease predictions into losses | Disease and yield scales | Generating disease scenarios | Simulating yield and economic losses | A single damage function | $$L_ | Visualizing the loss scenarios | Sensitivity to damage-function parameters | Interpreting the loss results | Practical applications | Reporting checklist | Summary | Next steps

Introduction | Preparing the example model | Reference conditions and effect measures | Lag-specific effects | What are lag-specific effects? | Estimating lag-specific effects | Visualizing lag-specific effects | Local sensitivity and delta effects | Period-specific effects | Why summarize lag periods? | Defining epidemiological periods | Estimating period-specific effects | Returning uncertainty samples | Comparing period-specific effects | Reducing the fitted DLNM association | Why reduce an exposure-lag association? | Overall cumulative exposure-response association | Visualizing the overall reduction | Exposure-response association at a selected lag | Lag-response association at a selected exposure value | Summary versus sample output | Interpreting reduced associations | Exposure Cumulative Impact | Why use ECI? | Calculating ECI | Interpreting ECI | Comparing raw and weighted exposure profiles | Decomposing ECI by lag | Why decompose ECI? | Computing lag contributions | Inspecting lag contributions | Plotting the contribution profile | How the summaries complement one another | Interpretation checklist | Next steps

Introduction | Alternative model engines | Supported families by modeling engine | Reference DLNM design | Fixed-effect reference model | Conventional random effects | GAM estimation | GAMM estimation | Spatially autocorrelated effects with spaMM | Spatially dependent fields | Independent spatial fields by year | Independent spatial fields across epidemiological replicates | Gaussian generalized least squares | MCMC estimation with brms | Bayesian DLNM with bdlnm | Direct INLA versus B-DLNM | Outputs shared by INLA and B-DLNM | Outputs specific to B-DLNM | Model objects

What does EpiExposure do? | The EpiExposure workflow | Organizing exposure profiles | Inspecting the example dataset | Visualizing exposure profiles | Defining exposure-lag structures | Checking identifiability and numerical stability | Building the epidemic-level design | Preparing the disease response | Fitting the first DLNM | Predicting one complete exposure profile | Where to go next

Introduction | Load example data | Why model selection matters | Searching candidate models | Run the model search | Ranking models | Top-performing models | Visualizing model performance | Understanding validation metrics | Concordance Correlation Coefficient | Root Mean Square Error | Mean Absolute Error | Inspecting specific models | Why use ensembles? | Selecting ensemble candidates | Unweighted ensemble | Inspect results | Weighted ensemble | Stacked ensemble | Comparing ensemble strategies | Visualizing ensemble predictions | Choosing a model-level ensemble strategy | Lag-contribution ensembles | Why construct a lag ensemble? | [ECI_ | Constructing unweighted and weighted lag ensembles | Inspecting selected models and weights | Inspecting ensemble lag contributions | Visualizing signed lag contributions | Visualizing relative lag contributions | Using strict exposure availability | Avoiding optimistic ensemble evaluation | Summary

Introduction | Preparing the example model | From effect interpretation to sensitivity analysis | Generating controlled exposure gradients | Temperature sensitivity | Generating a temperature gradient | Predicting responses along the gradient | Visualizing the response curve | Why sensitivity analysis? | Computing temperature sensitivity | Interpreting sensitivity | Visualizing temperature sensitivity | Elasticity analysis | What is elasticity? | $$E(x) | Visualizing elasticity | Identifying critical regions | Extracting critical points | Visualizing critical points | Comparing environmental drivers | Rainfall sensitivity | Generating a rainfall gradient | Predicting rainfall scenarios | Computing rainfall sensitivity | Leaf wetness sensitivity | Generating a leaf wetness gradient | Predicting leaf wetness scenarios | Computing leaf wetness sensitivity | Combining sensitivity results | Visualizing uncertainty realizations | Summarizing sensitivity uncertainty | Visualizing summarized sensitivity | Comparing sensitivity across variables | Decision-support interpretation | Example interpretation | Interpretation checklist | Summary | Next steps

Introduction | Preparing the example model | Complete exposure profiles | Simulating exposure profiles | Why simulate exposures? | Simulating a background process | Simulating structured exposure events | Predicting disease outcomes | Deterministic prediction | Prediction uncertainty | Scenario simulation | Why construct scenarios? | Defining epidemiological periods | Generating candidate scenarios | Predicting scenario outcomes | Summarizing scenario predictions | Visualizing summarized scenario predictions | Returning individual prediction samples | Visualizing individual prediction samples | Scenario surfaces | Comparing predictions | Comparing complete simulated profiles | Defining Scenario A | Defining Scenario B | Defining Scenario C | Defining Scenario D | Visualizing the candidate profiles | Comparing the exposure profiles | Comparing temperature profiles | Comparing rainfall profiles | Comparing leaf wetness profiles | Visualizing the exposure differences | Comparing the expected outcomes | Summarized comparisons | Draw-specific comparisons | Visualizing comparison uncertainty | Comparing one exposure at a time | Interpreting simulation and prediction outputs | Summary | Next steps

Introduction | Preparing the epidemiological model | Translating disease predictions into losses | Disease and yield scales | Generating disease scenarios | Simulating yield and economic losses | A single damage function | $$L_ | Visualizing the loss scenarios | Sensitivity to damage-function parameters | Interpreting the loss results | Practical applications | Reporting checklist | Summary | Next steps