We discuss robust designs for generalized linear models with protection for possible departures from the usual model assumptions. Besides possible inaccuracy in an assumed linear predictor, both problems of overdispersion and misspecification in link function are addressed. For logistic and Poisson models, as examples, we incorporate the variance function prescribed by a superior model similar ...

We present a novel latent space representation of the relative propensity for a respondent to form ties with members of a particular social group, a quantity related to overdispersion. In many applications collecting complete network data is financially or practically infeasible. Instead, we use data where respondents are asked for the number of ties they have with members of various subpopulat...

Introduction Spatial Scan Statistics [1] usually assume Poisson or Binomial distributed data, which is not adequate in many disease surveillance scenarios. For example, small areas distant from hospitals may exhibit a smaller number of cases than expected in those simple models. Also, underreporting may occur in underdeveloped regions, due to inefficient data collection or the difficulty to acc...

The Poisson regression model is widely used for count data. This assumes equidispersion. In practice, equidispersion seldom reflected in However, real-life data, the variance usually exceeds mean. situation known as overdispersion. Negative binomial distribution and other mix models are often to overdispersion Another extension of negative another data univariate generalized Waring. addition, d...

Indonesia is one of the developing countries that struggling to eradicate malnutrition problem. Malnutrition occurs over a long period time can have an impact on deaths sufferers and decrease human quality life. This study aims model case occurred in Provinces during 2015 get main factors cause Variables studied consist (Y), Vitamin A consumption (X1), Exclusive breastfeeding (X2), Immunization...

The M5 competition uncertainty track aims for probabilistic forecasting of sales thousands Walmart retail goods. We show that the data faces strong overdispersion and sporadic demand, especially zero demand. discuss resulting modeling issues concerning adequate such count processes. Unfortunately, majority popular prediction methods used in (e.g. lightgbm xgboost GBMs) fails to address characte...

Bivariate Poisson regression models for ratemaking in car insurance has been previously used. They included zero-inflated models to account for the excess of zeros and the overdispersion in the data set. These models are now revisited in order to consider alternatives. A 2-finite mixture of bivariate Poisson regression models is used to demonstrate that the overdispersion in the data requires m...

In this paper, we address the question of identifiability and learning algorithms for large-scale Poisson Directed Acyclic Graphical (DAG) models. We define general Poisson DAG models as models where each node is a Poisson random variable with rate parameter depending on the values of the parents in the underlying DAG. First, we prove that Poisson DAG models are identifiable from observational ...