Unlikely likelihoods: likelihood analysis for the triangular and random histogram models
Abstract
This paper concerns certain parametric models for densities on the unit interval which lead to nonsmooth and nonregular likelihood functions. (i) The first is the simple triangular model on the unit interval, characterised by a density linearly increasing from zero to the mode position θ and then linearly decreasing to zero from the mode to one. With data from this model the likelihood function is a sum of individually log-convex terms, and with the derivative having discontinuities at each data point. (ii) The second is the one-parameter two-box density which is flat on [0,θ] and (θ,1], with θ the median. The likelihood has jumps at each datapoint. Here the maximum likelihood estimator is sharper than usual, with convergence in distribution of n(θ̂−θ) to a nonnormal limit. We also study the k-box extension of this model, with density being flat on k boxes determined by k quantiles. (iii) This second model is extended to the two-parameter two-box model, with areas γ and 1−γ for boxes [0,θ] and (θ,1]. Again the likelihood is nonregular, and the maximum likelihood estimators exhibit different rates of convergence for the breakpoints and the density values. The model generalises to the 2(k−1) parameter density piecewise flat over k boxes. For each of these models we tend to the delicate task of sorting out the large-sample behaviour of the log-likelihoods, then leading to precise and partly nonstandard limit distributions for the maximum likelihood and Bayes estimators.
Related
- A Proxy-likelihood Estimator for Multivariate Extremes Models with Intractable Likelihoods
- A weak invariance principle for triangular arrays of independent random variables in some Besov spaces
- Bias-Corrected Empirical-Likelihood Inference for Single-Index Expectile Regression Under Missing-at-Random Responses
- Identifiability and likelihood estimation for homogeneous angular regression with random coefficients
- On maximum likelihood estimation in the β-model for random hypergraphs
BibTeX
@misc{hjort2026unlikely,
title = {{Unlikely likelihoods: likelihood analysis for the triangular and random histogram models}},
author = {Nils Lid Hjort},
howpublished = {arXiv},
year = {2026},
month = nov,
doi = {10.48550/arxiv.2611.01030},
eprint = {2611.01030},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2611.01030},
}
RIS
TY - UNPB
TI - Unlikely likelihoods: likelihood analysis for the triangular and random histogram models
AU - Nils Lid Hjort
PY - 2026
DA - 2026/11/01
PB - arXiv
DO - 10.48550/arxiv.2611.01030
UR - https://arxiv.org/abs/2611.01030
AB - This paper concerns certain parametric models for densities on the unit interval which lead to nonsmooth and nonregular likelihood functions. (i) The first is the simple triangular model on the unit interval, characterised by a density linearly increasing from zero to the mode position θ and then linearly decreasing to zero from the mode to one. With data from this model the likelihood function is a sum of individually log-convex terms, and with the derivative having discontinuities at each data point. (ii) The second is the one-parameter two-box density which is flat on [0,θ] and (θ,1], with θ the median. The likelihood has jumps at each datapoint. Here the maximum likelihood estimator is sharper than usual, with convergence in distribution of n(θ̂−θ) to a nonnormal limit. We also study the k-box extension of this model, with density being flat on k boxes determined by k quantiles. (iii) This second model is extended to the two-parameter two-box model, with areas γ and 1−γ for boxes [0,θ] and (θ,1]. Again the likelihood is nonregular, and the maximum likelihood estimators exhibit different rates of convergence for the breakpoints and the density values. The model generalises to the 2(k−1) parameter density piecewise flat over k boxes. For each of these models we tend to the delicate task of sorting out the large-sample behaviour of the log-likelihoods, then leading to precise and partly nonstandard limit distributions for the maximum likelihood and Bayes estimators.
ER -