A Flexible Logit-t Distribution with Adaptable Tail Behavior

Mahdavi, Abbas; Contreras-Reyes, Javier E.

doi:10.22034/jirss.2026.2091797.1211

A Flexible Logit-t Distribution with Adaptable Tail Behavior

Articles in Press

Document Type : Original Article

Authors

Abbas Mahdavi ¹

Javier E. Contreras-Reyes ²

¹ Vali-e-Asr University of Rafsanjan, Rafsanjan, Iran.

² Universidad de Las Américas: Viña del Mar, Valparaíso, Chile.

10.22034/jirss.2026.2091797.1211

Abstract

In this study, we introduce a novel unit flexible-t distribution specifically designed for continuous data constrained to the unit interval (0, 1), a common scenario in many applied fields such as medicine, economics, and environmental sciences. By integrating the flexible-t distribution’s capacity to handle heavy tails and multimodality with the logit transformation, the proposed model provides a versatile and robust framework for analyzing rates, proportions, and similar bounded outcomes. To ensure accurate and stable parameter estimation, we employ an EM-type algorithm, which proves efficient even with complex likelihood structures. The effectiveness of our approach is assessed through a comprehensive simulation study, the analysis of two real data sets, and a regression application that illustrates the practical use of the proposed model. Empirical results consistently indicate that the proposed flexible logit-t model
outperforms existing unit-interval models in terms of goodness-of-fit, adaptability to diverse data shapes, and predictive precision. Our findings underscore the model’s practical relevance and establish it as a valuable addition to the analytical toolkit for both researchers and practitioners dealing with bounded continuous responses.

Keywords

EM-type algorithms

flexible-t distribution

logit-transformation

unit distribution

Subjects

Statistical Modelling

Akaike H. Information Theory and an Extension of the Maximum Likelihood Principle. In: Petrov BN, Csaki F, editors. Proceedings of the Second International Symposium on Information Theory. Budapest: Akadémiai Kiadó; 1973. p. 267–281.
Andersen S, Harrison GW, Hole AR, Lau M, Rutström EE. Non-linear mixed logit. Theory and Decision. 2012;73:77–96.
Arnold BC, Groeneveld RA. Some properties of the arcsine distribution. Journal of the American Statistical Association. 1980;75(369):173–175.
Contreras-Reyes JE, Arellano-Valle RB, Mariella-Canales T. Comparing growth curves with asymmetric heavy-tailed errors: Application to the southern blue whiting (Micromesistius australis). Fisheries Research. 2014;159:88–94.
Cordeiro GM, Lemonte AJ. The McDonald arcsine distribution: A new model to proportional data. Statistics. 2014;48(1):182–199.
Dempster AP, Laird NM, Rubin DB. Maximum likelihood from incomplete data via the EM algorithm. Journal of the Royal Statistical Society: Series B (Methodological). 1977;39(1):1–22.
Ferrari S, Cribari-Neto F. Beta regression for modelling rates and proportions. Journal of Applied Statistics. 2004;31(7):799–815.
Gómez-Déniz E, Sarabia JM. A family of generalised beta distributions: properties and applications. Annals of Data Science. 2018;5(3):401–420.
Grassia A. On a family of distributions with argument between 0 and 1 obtained by transformation of the gamma and derived compound distributions. Australian Journal of Statistics. 1977;19(2):108–114.
Korkmaz MÇ. A new heavy-tailed distribution defined on the bounded interval: the logit slash distribution and its application. Journal of Applied Statistics. 2020;47(12):2097–2119.
Kumaraswamy P. A generalized probability density function for double-bounded random processes. Journal of Hydrology. 1980;46(1–2):79–88.
Liang Y, Sun D, He C, Schootman M. Modeling bounded outcome scores using the binomial-logit-normal distribution. Chilean Journal of Statistics. 2014;5:3–14.
Liu C, Rubin DB. The ECME algorithm: a simple extension of EM and ECM with faster monotone convergence. Biometrika. 1994;81(4):633–648.
Mahdavi A, Balakrishnan N, Jamalizadeh A. Robust classification via finite mixtures of matrix variate skew-t distributions. Mathematics. 2024;12(20):3260.
Mahdavi A, Contreras-Reyes JE. Bounded data modeling using logit-skew-normal mixtures. Statistical Papers. 2025;66(3):57.
Mahdavi A, Desmond AF, Wang WL, Jamalizadeh A. Robust mixture modeling of unit data using the multivariate logit-t distribution. Measurement: Interdisciplinary Research and Perspectives. 2026;p. 1–18.
Martínez-Flórez G, Bolfarine H, GómezHW. Censored bimodal symmetric-asymmetric families. Statistics and Its Interface. 2018;11(2):237–249.
Mazucheli J, Menezes AFB, Fernandes LB, de Oliveira RP, Ghitany ME. The unit-Weibull distribution as an alternative to the Kumaraswamy distribution for the modeling of quantiles conditional on covariates. Journal of Applied Statistics. 2020;47(6):954–974.
Mazucheli J, Menezes AFB, Chakraborty S. On the one parameter unit-Lindley distribution and its associated regression model for proportion data. Journal of Applied Statistics. 2019;46(4):700–714.
McDonald JB. Some Generalized Functions for the Size Distribution of Income. Econometrica. 1984;52(3):647–665.
Meng XL, Rubin DB. Maximum likelihood estimation via the ECM algorithm: A general framework. Biometrika. 1993;80(2):267–278.
Pierrot A, Pinson P. Adaptive Generalized Logit-Normal Distributions for Wind Power Short-Term Forecasting. In: Proceedings of the 2021 IEEE Madrid PowerTech IEEE; 2021. p. 1–6.
Pourdarvish A, Mirmostafaee SMTK, Naderi K. The exponentiated Topp-Leone distribution: Properties and application. Journal of Applied Environmental and Biological Sciences. 2015;5(7):251–256.
Quintero FOL, Contreras-Reyes JE. Estimation for finite mixture of simplex models: applications to biomedical data. Statistical Modelling. 2018;18(2):129–148.
Schwarz G. Estimating the dimension of a model. The Annals of Statistics. 1978;6(2):461–464.
Smirnov N. Table for estimating the goodness of fit of empirical distributions. The Annals of Mathematical Statistics. 1948;19(2):279–281.
Smithson M, Verkuilen J. A better lemon squeezer? Maximum-likelihood regression with beta-distributed dependent variables. Psychological Methods. 2006;11(1):54–71.
ToppCW, Leone FC. Afamily of J-shaped frequency functions. Journal of the American Statistical Association. 1955;50(269):209–219.
Van Dorp JR, Kotz S. The standard two-sided power distribution and its properties: with applications in financial engineering. The American Statistician. 2002;56(2):90–99.