Two questions

Find my analysis

Tell us what you recorded and what you want to know. You get the module that fits, what it needs, and a prompt to paste into Claude.

1. What did you record?

Nothing fits?

Describe your data and question to Claude anyway. The agent picks from the same catalog and says so if no module fits, rather than forcing your data into the wrong model. A new module can be built and validated, but that takes much longer than using an existing one.

All 29 analyses, by type of data

Prefer to browse? Every module, grouped by area. Each page says when to use it and when not to.

Regression and causal inference

GLM / GLMM with biological interpretation: One response measured on sampling units (sites, plots, nests, animals, quadrats, surveys) and the question is how it changes with habitat, environmental or treatment predictors…
Causal effects from observational data (DAG + g-computation): The question is causal ("does canopy cover increase trout?", "what would happen to native plants if pastures were not grazed?") and the data are observational (field surveys, monitoring).
Structural equation models (piecewise SEM and lavaan): Several measured variables on the same sampling units (plots, sites, lakes, animals) are thought to influence each other as a network (e.g. fire -> canopy -> shrubs -> birds)…

Occupancy

Single-species occupancy (static single-season and dynamic multi-season): Detection/non-detection surveys repeated at sites (camera traps, call surveys, eDNA replicates, point counts reduced to 0/1)…
Multispecies occupancy with species interactions (Rota et al. 2016): Detection/non-detection surveys of 2 or 3 species at the same sites (camera traps, call surveys, eDNA, point counts reduced to 0/1), repeated so detection can be estimated…
Two-species conditional occupancy (dominant/subordinate; Richmond et al. 2010, Waddle et al. 2010): Repeated detection/non-detection surveys of TWO species at the same sites, where one species can reasonably be treated as dominant (predator, invasive competitor…
Spatial, multi-species and integrated occupancy (spOccupancy): Detection/non-detection surveys repeated at sites with known coordinates, when (a) occupancy is likely spatially clustered beyond what the covariates explain (single species, spPGOcc)…
Abundance-mediated species interactions (dominant abundance -> subordinate occupancy): Camera-trap (or other repeated detection/non-detection) surveys of two species where one (dominant, e.g. a predator or competitor) may affect where the other (subordinate) occurs…

Abundance

N-mixture models for repeated counts (closed and open): The same sites (points, plots, transects, stream reaches) were counted two or more times within a period when the number of animals there did not change…
Distance sampling (conventional, multiple-covariate and hierarchical): Observers walked line transects or stood at points and recorded the distance (perpendicular for lines, radial for points) to every animal or group they detected…

Spatial capture-recapture

Spatial capture-recapture (closed population density): Individually identified animals detected at fixed detectors over repeated occasions within one closed season (camera traps of marked/spotted species, DNA from hair snares…
Spatial mark-resight (SMR) and generalized spatial mark-resight (gSMR): Only part of the population carries individual marks (collars, ear tags, natural marks on a subset) and cameras (or other resighting detectors) photograph both marked and unmarked animals…
Search-encounter SCR (scat-detection dogs, snow-tracking, transect searches for genetic samples): Individuals identified from noninvasive genetic samples (scats, hair, feathers, urine in snow) found along recorded search routes (GPS tracks of detection-dog teams, snow-tracking…
Open-population spatial capture-recapture (Jolly-Seber SCR): Individually identified animals (hair-snare or scat DNA, camera traps of marked/spotted species, live traps) detected at fixed detectors over repeated occasions in each of several seasons or years…

Demography and population dynamics

Cormack-Jolly-Seber apparent survival: Individually marked animals (bands, PIT tags, photo-ID, genetic tags) recaptured or resighted on repeated occasions; the question is how many survive from one occasion to the next and whether…
Multistate and multievent capture-recapture (Arnason-Schwarz / Pradel multievent): Individually marked animals are caught or resighted on repeated occasions and each capture records a state (site or wetland, breeding vs non-breeding, infected vs uninfected, size class)…
Jolly-Seber open-population capture-recapture (abundance, survival, recruitment): Individually marked animals (tags, PIT tags, bands, photo-ID, genetic ID) captured on 3+ occasions (usually years or seasons) in an open population…
Integrated population model (counts + capture-recapture + productivity): A local population studied for several years (>= 8, ideally 12+) with three kinds of data on the same population (annual counts of breeders…
Population time series - trends, density dependence and drivers of growth (state-space models): One count or abundance index per year (aerial/ground counts, nest counts, redd counts, CPUE, BBS-style route totals) for one population or several sub-populations, 10+ years…
Population viability analysis - count-based (diffusion / state-space) and matrix-model PVA: The question is extinction or quasi-extinction RISK - "how likely is this population to fall below N animals within 10, 25 or 50 years…

Distribution and community

Species distribution from presence-only records (point process, Maxent, integrated with surveys): You have presence-only records of a species (museum/herbarium specimens, iNaturalist/eBird-style incidental sightings, agency incidental reports, trapper/hunter reports) with coordinates…
Joint species distribution model (HMSC): Presence/absence or counts of many species (about 5-60) recorded at the same sampling units (plots, point-count stations, traps, lakes)…
Community composition - ordination, RDA and variation partitioning, PERMANOVA with dispersion test, beta-diversity partitioning, indicator species: A site x species table (counts, cover, biomass or presence/absence) from many sites plus a site table of environmental variables and/or groups (habitat types, treatments, regions, years)…

Movement

Hidden Markov models for animal movement (behavioural states): GPS / Argos-quality-filtered telemetry with fixes at a (roughly) regular interval, and the question is which movement modes an animal switches between (e.g. encamped/foraging vs travelling)…
Habitat selection from telemetry - integrated step selection (iSSA), RSF and home ranges: GPS (or other regular-interval) telemetry from several animals plus habitat rasters; the question is which habitats animals select or avoid while moving, how strongly (relative selection strength)…

Conservation genetics

Genetic diversity and population structure (FST, FIS, isolation by distance, DAPC): Multilocus genotypes (microsatellites, or SNPs coded 0/1/2 or in a VCF) from individuals sampled in several populations or sites…
Effective population size and relatedness: Genotypes (microsatellites or SNPs) from one or more samples of a population; question is how large the genetically effective population is (Ne), how fast it is losing diversity…

Fisheries

Fish growth (von Bertalanffy) and length-weight condition: Individual age-length data (otolith/scale ages) for one or more groups (populations, lakes, sexes, years); question is how fast fish grow, how large they get, at what age they approach maximum size…
Fish stock assessment - catch curves, stock-recruitment and surplus production: Fisheries questions about mortality, recruitment or stock status. (1) catch_curve - aged fish from a survey or fishery sample (one year or several years)…