A Generalized Log Gamma Approach: Theoretical Contributions and an Application to Companies’ Life Expectancy

Abstract

The survival of a company has been a topic of growing interest in the scientific community. Measuring the life expectancy of Portuguese telecommunications companies using generalized log-gamma (GLG) distribution is a new research endeavor. Regarding the new theoretical contributions, original expressions for the moments and mode of the GLG distribution are presented. In this empirical study, data on the entrepreneurial fabric in the Information and Communication sector from 2004 to 2018, when some companies were born or died, were used. In addition to the GLG, three other statistical distributions with two parameters are analyzed: gamma, Weibull, and log-normal. Maximum likelihood parameters and confidence intervals for survival probabilities are estimated and compared. The Akaike information criterion is used to compare the performance of the four estimated models. The results show that GLG distribution is a promising solution to assess the resilience and longevity of a firm.

Keywords

• probability distributions
• parameter estimation
• parametric models
• generalized log-gamma
• companies’ life expectancy