A New Maximum Likelihood Algorithm for Piecewise Regression

DOI10.2307/2287599zbMath0474.65099OpenAlexW4233040270MaRDI QIDQ3928993

Asher Tishler, Israel Zang

Publication date: 1981

Full work available at URL: https://doi.org/10.2307/2287599

zbMATH Keywords

likelihood functionmaximum likelihood algorithmlinear and nonlinear regressionpiecewise regression

Mathematics Subject Classification ID

Linear regression; mixed models (62J05) General nonlinear regression (62J02) Probabilistic methods, stochastic differential equations (65C99)

Related Items

Change point models for cognitive tests using semi-parametric maximum likelihood ⋮ Asymptotic theory for bent-cable regression -- the basic case ⋮ A heuristic, iterative algorithm for change-point detection in abrupt change models ⋮ Testing for unit roots in a Bayesian framework ⋮ Simultaneous confidence band for the difference of segmented linear models ⋮ Two-component generalized bent-cable models ⋮ Statistical modeling of changes in relative sea level in Maine during the Holocene Era ⋮ Estimation of Knots in Linear Spline Models ⋮ Least squares estimation of linear splines with unknown knot locations ⋮ Nondifferentiable optimization via smooth approximation: General analytical approach ⋮ Switching regressions and activity analysis. A new approach to frontier estimation ⋮ Longitudinal mixed-effects models for latent cognitive function ⋮ Change-point problems: bibliography and review ⋮ A smoothing-out technique for min—max optimization ⋮ Joint mixture quantile regressions and time-to-event analysis ⋮ A min-max algorithm for non-linear regression models ⋮ A Bayesian analysis of some threshold switching models ⋮ Bayesian analysis of switching regression models ⋮ Bent-cable asymptotics when the bend is missing. ⋮ Penalized likelihood regression for generalized linear models with non-quadratic penalties

This page was built for publication: A New Maximum Likelihood Algorithm for Piecewise Regression