Fluctuations in email size modeled using a gamma-like distribution

TL;DR

This paper improves the modeling of email size fluctuations by integrating a gamma distribution with a logarithmic equation, resulting in a more accurate fit than previous models, enhancing understanding of email size statistics.

Contribution

The study introduces a gamma-like distribution model that better captures email size fluctuations, advancing prior log-normal-based models with improved accuracy.

Findings

Gamma-like model outperforms log-normal-like model in fitting email size data

Enhanced model provides better characterization of small email sizes

Contributes to statistical understanding of email size variability

Abstract

A previously established frequency distribution model, which integrates a lognormal distribution with a logarithmic equation, effectively characterizes fluctuations in email size during sending requests. In addition, an email size generation model has been developed based on this log-normal-like framework. While the fitting of these models has been deemed satisfactory, they can be further enhanced in the range of small email sizes. This study advances these models by incorporating a gamma distribution alongside a logarithmic equation. The resulting gamma-like model demonstrates a significantly improved fit compared with the log-normal-like model. These results contribute to the knowledge on the statistical properties of sending mail.