Introduction | Installation | Example data | The multiple-methods design | Simulated data | Your own data | The multiple-methods false-positive occupancy model | Basic model description | Parameter names | Fitting the constant-rate model with fp_occu() | Convergence and model adequacy | Convergence | Posterior predictive check | Modelling the false-positive rate | Why the occupancy slope is biased | A false-positive rate that tracks the occupancy covariate | A false-positive rate that tracks the confusing gradient | Sensitivity to the priors | Variation that the covariates do not explain | Model comparison with LOO | Prediction | Detection covariates and recorder effects | The observation-confirmation design | Next steps | References
Package: crywolf 1.2.0
crywolf: Bayesian False-Positive Occupancy Models with Calibration Checks
Fits single-season occupancy models that correct for false positives from automated detectors, such as acoustic classifiers, using the multiple-methods (site-confirmation) design of Miller et al. (2011) <doi:10.1890/10-1396.1>, in which a subset of detections is verified. Models are written in 'Stan' and fitted through 'cmdstanr'. The false-positive rate can be constant or depend on site covariates, and the true-detection process accepts observation covariates and a recorder random effect. The package also simulates data under homogeneous, unstructured, and structured false-positive regimes and runs simulation-based calibration checks, so users can ask whether the correction keeps nominal interval coverage for their own design and how much verification it needs.
Authors:
crywolf_1.2.0.tar.gz
crywolf_1.2.0.zip(r-4.7-any)crywolf_1.2.0.zip(r-4.6-any)crywolf_1.2.0.zip(r-4.5-any)
crywolf_1.2.0.tgz(r-4.6-any)crywolf_1.2.0.tgz(r-4.5-any)
crywolf_1.2.0.tar.gz(r-4.7-any)crywolf_1.2.0.tar.gz(r-4.6-any)
crywolf_1.2.0.tgz(r-4.6-emscripten)
manual.pdf |manual.html✨
DESCRIPTION |NEWS
card.svg |card.png
crywolf/json (API)
| # Install 'crywolf' in R: |
| install.packages('crywolf', repos = c('https://diogoprov.r-universe.dev', 'https://cloud.r-project.org')) |
Bug tracker:https://github.com/diogoprov/crywolf/issues
Pkgdown/docs site:https://provetelab.org
Datasets:
- curiango - Passive acoustic monitoring of the Common Pauraque in the Pantanal
Last updated from:62633f489c. Checks:9 OK. Indexed: yes.
| Target | Result | Time | Files | Syslog |
|---|---|---|---|---|
| linux-devel | OK | 175 | ||
| source / vignettes | OK | 744 | ||
| linux-release | OK | 165 | ||
| macos-release | OK | 127 | ||
| macos-oldrel | OK | 123 | ||
| windows-devel | OK | 110 | ||
| windows-release | OK | 93 | ||
| windows-oldrel | OK | 113 | ||
| wasm-release | OK | 145 |
Exports:as_draws_dffp_calibratefp_calibrate_fitfp_compilefp_datafp_data_widefp_occufp_ppcfp_priorsfp_stan_filefp_verification_curveloosimulate_fp
Dependencies:abindbackportscheckmateclicmdstanrdata.tabledistributionalgenericsgluejsonlitelifecycleloomagrittrmatrixStatsnumDerivpillarpkgconfigposteriorprocessxpspurrrR6rlangtensorAtibbleutf8vctrswithr
Introduction to crywolf
Last update: 2026-10-16
Started: 2026-10-14
Simulating false-positive regimes
What a simulation returns | Three false-positive regimes | Homogeneous | Unstructured | Structured | The observation process | From one dataset to a calibration check | References
Last update: 2026-10-16
Started: 2026-10-15
The Stan model
Data | Binomial rows | Parameters | Likelihood | Parallel likelihood | Priors and model block | Generated quantities | Modifying a copy | References
Last update: 2026-10-16
Started: 2026-10-15
Checking calibration and how much to verify
The workflow | How much to verify | What to expect | Calibrating a fitted model | Plotting
Last update: 2026-10-16
Started: 2026-10-14
Case study: the Common Pauraque in the Pantanal
The data | Fitting | Convergence | How often does each classifier err? | Occupancy with and without false positives | Does the false-positive rate track the environment? | Model comparison | Posterior predictive checks | Predicted occupancy | References
Last update: 2026-10-15
Started: 2026-10-15
Coming from unmarked::occuFP()
The data layout | The same model fitted both ways | Formulas | What crywolf adds | Predictions | References
Last update: 2026-10-15
Started: 2026-10-15
Readme and manuals
Help Manual
| Help page | Topics |
|---|---|
| Passive acoustic monitoring of the Common Pauraque in the Pantanal | curiango |
| Simulation-based calibration check for a study design | fp_calibrate |
| Calibration of a fitted model on data like the real ones | fp_calibrate_fit |
| Compile (or load) the Stan model | fp_compile |
| Assemble data for a false-positive occupancy model | fp_data |
| Assemble data from detection matrices | fp_data_wide |
| Fit a Bayesian false-positive occupancy model | fp_occu |
| Methods for fp_occu fits | as_draws_df.fp_occu coef.fp_occu fp_occu-methods loo.fp_occu predict.fp_occu print.fp_occu print.summary.fp_occu summary.fp_occu |
| Posterior predictive check for a false-positive occupancy model | fp_ppc |
| Prior settings for fp_occu() | fp_priors |
| Path to the Stan program | fp_stan_file |
| Coverage as a function of verification effort | fp_verification_curve |
| Plot the results of a calibration check | plot.fp_calibration |
| Simulate data for a false-positive occupancy model | simulate_fp |
| Simulate data from a fitted model | simulate.fp_occu |