Systems of differential equations are used as the basis to define mathematical structures for moments, like the mean and variance of probability distributions of random variables. Nevertheless, the integration of a deterministic model and a probabilistic one, in order to describe a random phenomenon, and take advantage of the observed data for making inferences on certain population dynamic characteristics, can lead to parameter identifiability problems for the observed sample. Furthermore, approaches to deal with those problems are usually inappropriate. In this paper, the shape of the likelihood function of a SIR-Poisson model is used to describe the relationship between flat likelihoods and the practical parameter identifiability problem. In particular, we show how a flattened shape for the profile likelihood of the basic reproductive number R0, arises as the observed sample (over time) becomes smaller, causing ambiguity regarding the shape of the average model behavior. We conducted some simulation studies to analyze the flatness severity of the R0likelihood, and the coverage frequency of the likelihood-confidence regions for the model parameters. Finally, we describe some approaches to deal the practical identifiability problem, showing the impact that those can have on inferences. We believe this work can help to raise awareness on the way statistical inferences can be affected by a priori parameter assumptions and the underlying relationship between them, as well as those arising by model reparameterizations and incorrect model assumptions.
|Título traducido de la contribución||FLAT LIKELIHOODS: SIR-POISSON MODEL CASE|
|Número de páginas||26|
|Publicación||Revista de la Facultad de Ciencias|
|Estado||Publicada - jul 2022|
Nota bibliográficaPublisher Copyright:
© 2022 by the Author(s).
- Flat likelihood function
- SIR model
- basic reproductive number
- likelihood contours
- ordinary differential equations
- profile likelihood function