Answers are grounded in this paper and cite their sources.
We propose the Q-Lindley (QLD) distribution, a one-parameter extension of the classical Lindley model designed for skewed and heavy-tailed data. The study develops its key properties, including the density, distribution, survival and hazard functions, moments, quantiles, and entropy, while also examining its shape and hazard behaviour. Parameters are estimated using maximum likelihood, method of moments, and conditional least squares, and simulation results assess their finite-sample performance. Applications to lifetime data show that QLD fits better than common alternatives such as Exponential, Gamma, Weibull, and Lindley models. We also introduce the Marshall-Olkin Q-Lindley (MOQLD) family and use it as the marginal distribution of a minification AR(1) process. For this model, we derive the transition structure, conditional moments, autocovariance, and joint distributions, and prove stationarity, uniqueness, and geometric ergodicity. Simulations and real data applications, including reliability and wind-speed forecasting, show strong fitting and predictive performance.
No takes yet. Share an insight, caveat, or question.
Becila et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: