What question did this study set out to answer?

The aim is to model daily maximum temperature extremes in Nigeria using Extreme Value Theory frameworks.

March 26, 2026Journal of Interdisciplinary Postgraduate ResearchOpen Access

Modeling extreme temperature events: a comparative analysis of the generalized pareto and lindley exponentiated gumbel distributions

View Full Paper

Ask AI

Bookmark

Authors

Comparative analysis models extreme temperature events in Nigerian cities, indicating implications for risk assessment.

The aim is to model daily maximum temperature extremes in Nigeria using Extreme Value Theory frameworks.
Applied Extreme Value Theory to temperature data from Lagos, Abuja, and Kano.
Utilized a Peaks Over Threshold framework to extract extreme temperature events.
Compared the Generalized Pareto Distribution with the Lindley Exponentiated Gumbel distribution.
Estimated model parameters using maximum likelihood and quantified uncertainty with nonparametric bootstrap.
Evaluated model performance through Akaike and Bayesian Information Criteria.
Significant spatial variation in heat extremes across cities, with Kano showing the highest extremes.
Generalized Pareto Distribution shape parameters were negative, indicating bounded temperature tails.
Lindley Exponentiated Gumbel model offered better statistical fit, especially in the upper tail.
Return level estimates were similar for both models, but LEG showed improved tail alignment.
Highlighting the importance of flexible tail models in climate risk assessment.

Olajide, Olajide, (2026) studied this question.

View Full Paper

Ask AI

Bookmark