Back

Equi-Under-Dispersed Possion Distribution (EUPoisson)

Hassan, M.

2024-10-25 bioinformatics
10.1101/2024.10.22.619660 bioRxiv
Show abstract

In this study, we propose an Equi-Under-dispersed Poisson distribution derived from a finite mixture of weighted Poisson distributions. This probability distribution is a simple, parsimonious, and flexible option suitable for modeling under-dispersed count data. It aims to overcome some of the weaknesses of existing methods in modeling Equi-Under-dispersed count data. Explicit expressions for the moment-generating function, mean, variance, and index of dispersion are derived. Real count data are used to compare its performance with that of the zero-inflated Poisson distribution and the finite mixture of Poisson distributions. Maximum likelihood estimation is implemented to estimate the parameters of the distribution, and goodness-of-fit statistical techniques are used to compare the fit of the competing distributions.

Matching journals

The top 6 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.