Interactively visualizing distributional regression models with distreg.vis

TL;DR: The current state of distributional regression is discussed in this article , with a particular focus on the four most prominent model classes: generalized additive models for location, scale and shape, conditional transformation models and distribution regression, density regression, and quantile and expectile regression.

TL;DR: Distributional regression for data analysis reviews various approaches for modeling entire distributions as functions of covariates. It covers statistical and machine learning methods, discusses scalability, trends, and challenges, and provides illustrations using large-scale data.

TL;DR: In this article , a review of state-of-the-art statistical approaches to distributional regression, complemented with alternatives from machine learning, is presented, including similarities and differences between these approaches, extensions, properties and limitations, estimation procedures, and the availability of software.

TL;DR: In this paper , a generalized normal distribution (GND) is proposed to account for heavy tails and heteroscedasticity through the use of a kurtosis-characterizing shape parameter that moves the model smoothly between the normal distribution and the heavier-tailed Laplace distribution.

TL;DR: In this paper, the authors used iterative weighted linear regression to obtain maximum likelihood estimates of the parameters with observations distributed according to some exponential family and systematic effects that can be made linear by a suitable transformation.

TL;DR: The lsmeans package (Lenth 2016) provides a simple way of obtaining least-squares means and contrasts thereof and supports many models fitted by R (R Core Team 2015) core packages that fit linear or mixed models.

TL;DR: A relatively large number of knots and a difference penalty on coefficients of adjacent B-splines are proposed to use and connections to the familiar spline penalty on the integral of the squared second derivative are shown.

TL;DR: The generalized additive model for location, scale and shape (GAMLSS) as mentioned in this paper is a general class of statistical models for a univariate response variable, which assumes independent observations of the response variable y given the parameters, the explanatory variables and the values of the random effects.