1. Model dimensions and operating mode | msmMode, single-species vs. multi-species | initMode, initial age structure | The initial equilibrium catch | estimateMode, what does fit_mod() actually do? | Random-effects toggles | 2. Predation: suitMode (per predator) | 3. Selectivity (per fleet) | Sharing a selectivity between fleets | Sex structure and relative selectivity | Which forms can hold a sex difference in level | 4. Catchability (per fleet) | Index likelihood (Index_distribution) | Which fleets get a catchability | How an index is timed against mortality | A snapshot-timed index on a fishery's selectivity | 5. Composition likelihoods | Ageing error, per fleet | 6. Recruitment / stock-recruit (recFun = build_srr()) | 7. Natural mortality (M1Fun = build_M1()) | M1_model, fixed-effects structure of M1 | M1_re, random-effects structure on M1 | 8. Growth and weight-at-age (growthFun = build_growth()) | growth_model, fixed-effects structure of growth | Growth variability, plus group, length bins and maturity | 9. Harvest control rules (HCR = build_hcr()) | 10. Projection and MSE | 11. Diagnostics and inference | 12. Plotting | References

Setup and plotting data | S3 Methods | Convergence diagnostics | Naming the parameter, not just the block | Fit plots | Composition data | Survey indices | Catch | One-step-ahead (OSA) residuals | Choosing the one-step-ahead method | With random effects, the choice reverses for the aggregate series | Fleets with tail accumulation | Process residuals | Retrospective analysis | Jitter testing | Self-test (simulation–estimation) | Redrawing process error | Likelihood profile | Moving a set of cells together | Catchability | Where the data disagree | Comparing runs | Collecting it into report tables | Model average

In progress! | Population dynamics | Predation sub-model | Suitability | MSVPA Type 2 based suitability | Predation mortality | Single-species mode | MSVPA Type 2 based predation mortality | MSVPA Type 3 based predation mortality | Consumption | Bioenergetics based ration | Input ration-at-age | Fishery and survey observation model | Selectivity parameterizations | Selectivity penalty weights | Fixed selectivity | Non-parametric (Type 1) | Logistic | Time-varying logistic | Double logistic | Time-varying double logistic 1 (ascending and descending time-varying parameters) | Time-varying double logistic 2 (random walk ascending-time varying parameters) | Descending logistic | Time-varying descending logistic | Non-parametric (Type 2) | Time-varying non-parametric (Type 2 for hake) | Catchability parameterizations | Linear time-invariant catchability formulations | Time-varying catchability formulations

Overview | A first example: temperature on K | The linkage_spec() API | Priors | Putting a prior on the parameter itself | Growth SD endpoints | Species- and (species, sex)-specific priors | Per-species formulas | Per-sex formulas | Polynomial and basis-expansion formulas | Time blocks | How the pieces fit together | Natural mortality | Recruitment | Priors and fixed values on R0, alpha and beta | Catchability | A prior on the survey catchability | Selectivity | Data weighting (Dirichlet-multinomial) | A multi-process example | Inspecting and debugging | Behind the scenes: automatic base-parameter handling | init and the base parameter | Stratification | Single-sex models and by = ~ ... + sex | Random effects | Integrated or penalized | Current limitations | See also

Overview | 1. Installation | 2. Data | 3. Fit models | 4. Reading the fitted object | 5. Compare models | 6. Model plots and diagnostics

Fitting the operating model | Fitting the estimation model (Tier 3 HCR) | Running the MSE | Check endyr before you start | Reproducibility | Evaluating the MSE with plots | Summary statistics | Alternative scenarios | Different reference points | Triennial bottom-trawl survey | 4-year assessment cycle and reduced survey coverage | A missed assessment, and a buffer while advice is stale | Climate-linked MSE | Climate-linked OM | Run MSE | Overall summary

When to use each mode | Bering Sea example | Gulf of Alaska example | Predator-prey suitability (suitMode) | Comparing outputs

The quick path: build_data() | Which inputs does my model need? | Building the list by hand | Setup | 1. Species / model controls | 2. Fleet control table | 3. Survey index data | 4. Catch data | 5. Composition data (optional) | 6. Conditional age-at-length (CAAL) data (optional) | 7. Biological inputs | Age-to-length transition matrix | Ageing error matrix | Weight-at-age | Maturity-at-age | Sex ratio at age | Fixed selectivity (optional) | Fixed numbers-at-age (optional) | Natural mortality (M1 base) | Environmental covariate data (optional) | 8. Multi-species bioenergetics parameters (optional in single-species mode) | 9. Validate and fit | 10. Export back to Excel (optional) | 11. Persist and share a run configuration (optional)

Model controls | Fleets | Catch data | Survey indices | Composition data | Ageing error | Weight-at-age | Other inputs | Verifying the conversion against SS | See also

Helper functions in AgeingError | Writing the data file | Writing the specifications file | Convenience wrapper: write_files() | Running the model | Adding data to an SS3 or FIMS model

fishprior | Data | Filtering

Setup | Fixed-F projections | Recruitment in the projection period | Manual recruitment deviations | Stochastic recruitment via sample_rec() | Comparing projection scenarios | Random recruitment effects | Available harvest control rules

Overview | Load data and inspect the growth dataset | Build a growth model with linkages | What this linkage does | Time-varying growth | Fit the model | Inspect the linkage table and prior contributions | Compare with an unlinked baseline model and Richards model | Matching a Stock Synthesis growth specification | Notes on priors through linkages

Overview | Setup and data loading | Quality assurance and quality control | Prepare and format data | Model design and fit | Model diagnostics and validation | Reproducibility

FIMS | Loading the package | Getting help | Memory | Data | data_big | FIMSFrame() | Parameters | setup_default_parameters() | Update parameters | Fit | initialize_fims() | fit_fims() | Example | Logging system | Sensitivities | Initial values | Age-specific selectivity | Age only | Length

Main Example: Estimable VonBertalanffySchnute With Generated Data | Build a Compact Generated Data Set | Configure the VonBertalanffySchnute Model | Fit the Model | Plot the Observed and Predicted Growth Curve | Plot Residuals | One Light Downstream Check of the Shared Size Path | Architecture Path | Next Steps

Other sources of information | Data format | data_big | FIMSFrame() | Catch (type == "catch") | Indices (type == "index") | Age compositions (type == "age_comp") | Length compositions (type == "length_comp") | Length bins (type == "length_bin") | Weight-at-age data (type == "weight_at_age") | Age-to-length conversion (type == "age_to_length_conversion")

Load data | Simple model with constant bycatch, no covariates

Load data | Simple model with constant bycatch, no covariates | Make plots | Extracting model selection information (LOOIC) | Negative binomial example | Zero - inflated example | Continuous models | Example with covariates | Fit model with time-varying effects | Fit model with no bycatch events

Load data | Fit a model | Plot the prediction distribution for a single year

Overview | Who Should Use This Guide | Prerequisites | FIMS Code Structure | Directory Structure | Naming Conventions | C++ Naming Conventions | R Naming Conventions | Module-Specific Conventions | Step-by-Step Guide | Related documentation | Documentation expectations | Step 1: Create the C++ implementation | Class roles in the C++ layer | 1.1 Create or update the base class | 1.2 Create or update the implementation class | 1.3 Create or update the umbrella header | Step 2: Build the Rcpp interface | 2.1 Understand the parameter objects first | 2.2 Create or update the interface class | 2.3 Register parameters with TMB in add_to_fims_tmb_internal() | 2.4 Extract results in finalize() | Step 3: Register the module with the R API | 3.1 Update src/fims_modules.hpp | 3.2 Update R/FIMS-package.R | Step 4: Connect the module to the current R workflow | 4.1 Update the configuration and default-parameter path | 4.2 Update initialize_modules.R | 4.3 Keep the full run path in mind | Step 5: Add targeted tests | 5.1 C++ Google tests | 5.2 R testthat tests | Step 6: Finalize the documentation and build checks | 6.1 Module-specific documentation | Files to modify: complete checklist | Required or commonly required files | Validation checklist | Common patterns and best practices | Parameter handling | ID management and lifecycle | TMB integration | Namespace organization | Troubleshooting | Common issues | "undefined symbol" errors when loading the package | Parameters are not being estimated | Values are not appearing back in R after a run | The module initializes in R but is missing expected fields | Getting help | Examples and references | Code examples | Documentation resources | Summary

Modules in R | Rcpp Interface | fims namespace | What is a namespace? | Maturity example | fims_popdy::LogisticMaturity class | Population class | Overview | Thinking in R

What is C++ | Definition | Why use C++ | Writing C++ | Basics | Types | Hello World example | add example | Vectors | Constants | Templates | Syntax in FIMS | Compiling directions | Classes | MyClass example | Instantiate and initialize | Inheritance | Polymorphism | Pointers and References | Pointers | References | Modifying Pointers | Memory Management | Shared pointers

What is Rcpp | Definition | Why use Rcpp | Writing C++ functions | Inline C++ code in R | Calling .cpp files from R | Benchmarking against R | C++ in FIMS | Rcpp Types | Rcpp scalar classes | Rcpp vector classes | SEXP in R | Type conversion | Rcpp methods | Rcpp modules | RCPP_MODULE | RCPP_EXPOSED_CLASS | Modules in FIMS

Introduction | Methods | Time-series model | Catch-at-age model | Parameters | Code | Results

Set up FIMS model | Likelihood profile | Visualize results | Clean up | Retrospective analysis | Mohn's Rho | Visualize the results

Projections in FIMS | Without projections | Projections | Data | Model | Model fit | Model summaries

Introduction | Development guidelines | Step 1: Extract Formatted Data | Step 2: Mock the Design Object | Step 3: Write the RTMB Objective Function | Template: Custom Objective Function | Step 4: Integrate and Submit

Load packages | Create a spatial grid | Add zone ID variable to the spatial object | Plot | Save spatial grid | Reassign zone ID in primary data

Data | Join data

Data | Check data format | Read and process data | Sightings | Effort | Strata | Comments

Mental model | The input_list accumulator pattern | SPoRC_rtmb() — the objective function | Naming conventions | File map | Extending the model: a checklist

Combining estimates using sample sizes | Variance weighting | Model based weighting | Combining estimates using meta-analysis | Model 1: Known standard errors only | Model 2: Known standard errors with residual variance | Model 3: Known standard errors with residual variance and random effects

Captions and alternative text (alt text) | How are captions and alt text constructed? | How can I alter the captions and/or alt text? | If I recreate a figure or table, will its caption and/or alt text be updated/overwritten? | How can I change or update captions and alt text? | Individual figures/tables (e.g., plot_biomass()) | All available figures and tables (e.g., save_all_plots())

Installing the r4ss R package | Basic installation | Loading the package and reading help pages | Alternative versions | Reading model output and making default plots | Creating select plots | Scripting Stock Synthesis workflows with r4ss | Read in Stock Synthesis files | Investigate the model | Modify the model | Write out the modified models | Download the Stock Synthesis executable from GitHub | Run the modified model | Investigate the model run | Should I script my whole Stock Synthesis workflow? | Functions for common stock assessment tasks | Running retrospectives | Jittering | Tuning composition data

Overview | Installing mizer | Setting the model parameters | Running a simulation | Exploring the results | Size-spectrum models | Single-species model | Community model | Trait-based model | Multispecies model | Which model to use | References

Introduction | R package | Input files | Data file | Separate Data Sets | Combined Data Set | Other Considerations | Specifications file | Bias options | Sigma options | Example Specifications file | Examples | Blue Grenadier | Bight Redfish | School Whiting | Sablefish | Trouble Shooting | Acknowledgements | References

Load data and packages | Setup model | Setup Recruitment Dynamics | Setup biological dynamics | Setup Movement and Tagging | Setup Catch and Fishing Mortality | Setup Fishery Indices and Compositions | Setup Survey Indices and Compositions | Setup Fishery Selectivity and Catchability | Setup Survey Selectivity and Catchability | Setup Model Weighting | Fit model | Fit model (Without Francis) | Fit model (With Francis) | Check Model Results | Convergence | Time Series Results | Catch and Index Fits | Composition Fits | Fishery Ages | Fishery Lengths | Survey Ages | Retrospectives | Retrospectives (Without Francis) | Retrospectives (With Francis) | Likelihood Profiles | Jitter Analysis | MCMC | Reference Points and Projections | Reference Points | Projections | Spawning Biomass Projections | Catch Projections | Catch Advice under $F_{40%}$ | Fishing Mortality Projections

Unstructured Markov | Age Blocks | Year Blocks | Sex Blocks | Blocks Across all Dimensions | Continuous-Time Markov Chain (CTMC) | Constant Movement | Age-Varying | Linear | Spline | Movement Across all Dimensions | Process Error

Background | Set up and format | Naming Conventions | Final Formatting | Helpful Functions to Manipulate Data

Overview | Creating plots | Example: Creating plots from simple and adding a custom tab | read model output | make the default plots and associated HTML files | Make custom plots and write CSV file with info about them | Add custom plots to the .csv | Getting the plots onto github

Summary | Sampling for ADMB models | Setting up the model | Sampling with sample_nuts and sample_rwm | mceval phase and posterior outputs | Bounds & Priors | Initializing chains | Parallel sampling | Diagnostics and plotting results | Diagnosing MCMC chains | Plotting output | Mass matrix adaptation | Sampling for TMB models | The no-U-turn sampler implementation | Brief review of Hamiltonian Monte Carlo | Algorithm implementation details | User intervention | Algorithm validity | References

Templates | Calculating and exporting captions and alternative text | Connecting the tables & figures with the captions & alternative text | Expected outcomes | Single plot functions | Multi-plot functions

Data Inputs for Defining Model Dimensions | Data Inputs for Defining Recruitment Processes | Data Inputs for Defining Biological Processes | Data Inputs for Defining Movement Processes | Data Inputs for Defining Tagging Processes | Data Inputs for Defining Catch and Fishing Mortality Processes | Data Inputs for Defining Fishery Indices and Compositions | Data Inputs for Defining Survey Indices and Compositions | Data Inputs for Defining Fishery Selectivity and Catchability | Data Inputs for Defining Survey Selectivity and Catchability | Data Inputs for Defining Model Weighting

Fishery Removals | Fishery Selectivity | Fishery Catchability | Fishery Composition Likelihoods | Survey Selectivity | Survey Catchability | Survey Composition Likelihoods | Natural Mortality | Recruitment | Movement | Tagging

Process Equations | Population Initialization | Recruitment Processes | Population Projection | Movement Processes | Observation Equations | Fishery Observation Model | Survey Observation Model | Tagging Observation Model | Fishery and Survey Selectivity | Likelihoods | Observation Likelihoods | Fishery Catches | Fishery and Survey Indices | Fishery and Survey Compositions | Structuring Compositions and Ageing Error | Tagging | Parameter Priors and Process Error Penalties | Parameter Priors | Natural Mortality | Fishery and Survey Catchability | Steepness | Recruitment Proportions | Movement | Tag Reporting Rates | Process Error Penalties | Initial Age Deviations | Recruitment Deviations | Fishing Mortality Deviations | Joint Likelihood | References

Biological Processes | Fishery Processes | Survey Processes | Tagging Processes | Likelihoods | Parameter Deviations | Derived Quantities (also reported in ADREPORT)

Setup Model Dimensions | Setup Recruitment Dynamics | Setup Biological Dynamics | Setup Movement and Tagging Dynamics | Setup Catch and Fishing Mortality | Setup Index and Composition Data (Fishery and Survey) | Setup Selectivity and Catchability (Fishery and Survey) | Setup Model Weighting | Fit Model and Plot

Define Operating Model | Define Management Options | Define Estimation Model | Define and Run Closed-Loop Simulation

Reference Points | Single Region | Spawning Potential Ratio | Maximum Sustainable Yield (Beverton-Holt) | Multi-Region | Independent | Global | Local | Deriving Catch Advice and Projections | Code Demonstration | Getting Reference Points | Multi Region | Conducting Catch Projections to Derive Catch Advice (Deterministic Recruitment) | Conducting Stochastic Population Projections | References

Starting Values | Mapping | Fixing Parameters | Sharing Parameters

Steepness | Natural Mortality | Catchability | Selectivity | Movement | Tag Reporting Rates | Recruitment Proportions

Overview | Estimation Model | Projection Options | Functions to Determine Catch | Management Procedures | Simulation Loop (Single Replicate) | Simulation Loop (Parrallelized) | Condition Closed Loop Simulation | Run Simulations | Process Results | Visualize

Load data | Simple model with constant bycatch, no covariates | Make table of expanded bycatch estimates | Make table of total bycatch estimates | Derived quantities | Simulating future values

Overview | Simple two-stream example | Fitting a multi-stream model | Plotting results | Stream-specific summaries | Three-stream example | Comparing to pooled data | Different distributions | Adding covariates | Time-varying effects

Overview | ☁️ Google Cloud Workstations | 🌐 GitHub Codespaces | 🐧 WSL2 | 🧑‍💻 Local | 🙋 Need Help?

Overview | Other families | Fixed effect covariates | Time varying parameters | Expanding estimates

Setup Model Dimensions | Setup Recruitment Dynamics | Setup Biological Dynamics | Setup Movement and Tagging | Setup Catch and Fishing Mortality | Setup Fishery Indices and Compositions | Setup Survey Indices and Compositions | Setting up Fishery Selectivity and Catchability | Setting up Survey Selectivity and Catchability | Setup Model Weighting | Fit Model and Plot

Simulation Settings | Population, Recruitment, and Biological Processes | Fishery Processes | Survey Processes | Tagging

Simulation Cross-Testing in SPoRC | Define Model Dimensions | Fishing Processes | Survey Processes | Biological Dynamics | Tagging and Movement | Recruitment | Run the Operating Model | Define Estimation Model | Run Cross-Test Analysis | Self Testing

Setup Model Dimensions | Setup Recruitment Dynamics | Setup Biological Dynamics | Setup Movement and Tagging Dynamics | Setup Catch and Fishing Mortality | Setup Index and Composition Data (Fishery and Survey) | Setup Selectivity and Catchability (Fishery and Survey) | Setup Model Weighting | Fit Model and Plot

Model parameters | Differences between Rpath and EwE balances

Setting up a food web model | Parameter file generation | Model parameters | Stanza Parameters | Diet Parameters | Pedigree parameters

Setting up pkgdown | Setting up code coverage

Running Rpath

Ecosense | Setting up Ecosense | Generating an ensemble of Ecosim parameter sets | Run the kept systems with a perturbation

Installation | References

Unit Tests | Details | Regenerating Baseline Files | List of Tests | AB and RK4 Sim Run Tests: | AB and RK4 Sim Run Tests with Jitter on ForcedBiomass: | AB and RK4 Sim Run Tests with Jitter on ForcedMigrate: | AB and RK4 Sim Run Tests with Stepped Noise on ForcedBiomass: | AB and RK4 Sim Run Tests with Stepped Noise on ForcedMigrate: | AB and RK4 Sim Run Tests with Jitter on ForcedEffort: | AB and RK4 Sim Run Tests with Jitter on ForcedFRate: | AB and RK4 Sim Run Tests with Jitter on ForcedCatch: | AB and RK4 Sim Run Tests with Stepped Noise on ForcedEffort: | AB and RK4 Sim Run Tests with Stepped Noise on ForcedFRate: | AB and RK4 Sim Run Tests with Stepped Noise on ForcedCatch: | Figures | Example plots:

Background | Install packages | Load libraries | Create a function that shows perceptions of palettes | Test main palettes | Test alternative regional color palette | Create alternative palettes | Show alternative palettes | Show alternative palettes in figures

Theming presentations | Color theming | Font theming | Background images | Extra css

Dependency graph

Installation | Configuration | Create a token | Back up repositories | Upload the zip file to a Google Drive folder | Schedule the run

Overview | Installation | Using the dir_size function | Output

Comparison with phylolm | Generalized linear models | Poisson-distributed response | Binomial regression | Summary of PGLM results | Compare with phylopath | Comparison with sem | Comparison with Rphylopars

Estimability for multiple covariance transformations | Scaling of runtime with increased tree size

Model comparison: some important differences | Model fitting: sometimes different

Preparing the Then et al. mortality database | Fitting and selecting among phylogenetic structural equation models | Visualizing output | Sensitivity to using taxonomic tree

Introduction to the DFA model | DFA model with no extreme events | DFA model with extreme events | Fitting DFA models with non-Gaussian families | Alternative loadings for DFA models | Including autoregressive (AR) or moving-average (MA) components on trends | Applying Hidden Markov Models to identify latent regimes | DFA model with weights

Documentation | Tutorials | For Statisticians | CITATION | PUBLICATIONS | NOAA Disclaimer

tldr; | The MARSS model | Model specification | Data and fitting | Data | Fit call | Different fitting methods | Defaults for model list | form="marxss" | form="dfa" | Showing the model fits and getting the parameters | Tips and Troubleshooting | Tips | Troubleshooting | More information and tutorials | Shortcuts and all allowed model structures | Z | B | U and x0 | A | Q, R and V0 | D and C | d and c | G and H | Covariates, Linear constraints and time-varying parameters | Covariates | Linear constraints | Time-varying parameters

Example

Case 1: unequal trend variability | Candidate models | Recovering loadings | Recovering trends | Summary

Data simulation | Sampling argument | Posterior optimization | Posterior approximation

Data simulation | Estimating trends as B-splines | Estimating trends as P-splines | Estimating trends as Gaussian processes | Comparing approaches

Notation review for DFA models | Observation covariates | Process covariates | Examples -- observation covariates | Examples -- process covariates

2 - trend model | 3 - trend model

simulate_population_harvest IBM to simulate a fish population and catches. | LH_sample Bootstrap sampling routine to estimate life history parameters | LH_plot Produce plots from an LH_sample object

Common metrics for ESUs | Dynamic linear modeling for time-varying trend estimation | Multivariate DLMs for analysis of multiple time series from one ESU | Treatment of NAs and 0s | Model selection | Code to fit a multivariate DLM | Wild spawner and fraction wild estimates | Summary statistics

Instructions to run a demo | Instructions to run your own data | Modifying the tables

Notes | Example data file

Overview | Import SDM predictions | Overlay predictions | Calculate evaluation metrics | Create and evaluate ensemble predictions | References