Identifiability Limits in Density-Dependent Leslie Models Under Partial Observation: Linking demographic stochasticity to inference bias in structured population time series (Δt = 1)

This article content was AI-generated for the purposes of establishing design and formatting only.

Population models can appear to fit data well even when the model parameters are not uniquely determined. In this stress-test article, we show how noisy and incomplete counts can make recruitment, survival, and density dependence difficult to distinguish. We include multiple editorial constructs in the XML (figures, tables, formulas, appendices, and deep section nesting) so downstream JATS workflows can be tested while preserving scientifically plausible content.

This article content was AI-generated for the purposes of establishing design and formatting only.

Structured population models are frequently inferred from incomplete demographic time series, yet parameter identifiability can fail even when models fit well. We study a density-dependent Leslie model with demographic stochasticity and partial observation, and derive sufficient conditions under which distinct parameter sets induce indistinguishable likelihoods using simulation-based calibration and profile-likelihood diagnostics. Recruitment and survival parameters become confounded when observation error is non-negligible, and density feedback is weak relative to environmental noise. We provide practical diagnostics to detect non-identifiability and recommend reporting a confounding map alongside point estimates. This XML additionally functions as a JATS 1.1 stress-test fixture.