The contrast is exemplified by the following classification task. Let’s assume that we are given data, X , i.e. the observed variable and we want to determine its class label, Y, the unobserved (target) variable. A generative classifier, such as Naive Bayes, makes use of the joint distribution of X and Y, i.e. P(X ,Y) to perform this inference. While a discriminative classifier, such as a Logis...

The conditional parametric model is an extension of the well known linear regression model, obtained by replacing the parameters by smooth functions. Estimation in such models may be accomplished by fitting a, possibly larger, linear model locally to some explanatory variable(s). In this report the conditional parametric model is described together with a method of estimation. An S-PLUS / R imp...

liquid-phases adsorption equilibrium of phenol onto two naturally available soils namely kalathur soil (kr) and adhanur soil (ar) were studied. the experimental data were analyzed using fourteen isotherm models, ranging from single-parametric model to multi-parametric models (up to 5 parameters) of the system. results show that in general the accuracy of models to fit experimental data improves...

conclusions parametric models may provide complementary data for clinicians and researchers about how risks vary over time. the weibull model seemed to show the best fit among the parametric models of the survival of hemodialysis patients. results the results of a multivariate analysis of the variables in the parametric models showed that the mean serum albumin and the clinic attended were the ...

This paper reviews Bayesian Nonparametric methods and discusses how parametric predictive densities can be constructed using nonparametric ideas.

In this paper we develop an approach that synthesizes the best features of the two main methods in the estimation of production efficiency. Specically, our approach first allows for statistical noise, similar to Stochastic frontier analysis, and second, it allows modeling multiple-inputs-multiple-outputs technologies without imposing parametric assumptions on production relationship, similar to...

Suppose the random vector (X,Y ) satisfies the regression model Y = m(X) + σ(X)ε, where m(·) = E(Y |·), σ2(·) = Var(Y |·) and ε is independent of X. The covariate X is d-dimensional (d ≥ 1), the response Y is one-dimensional, and m and σ are unknown but smooth functions. In this paper we study goodness-of-fit tests for the parametric form of the error distribution under this model, without assu...

Recurrent event time data are common in biomedical follow-up studies, in which a study subject may experience repeated occurrences of an event of interest. In this paper, we evaluate two popular nonparametric tests for recurrent event time data in terms of their relative efficiency. One is the log-rank test for classical survival data and the other a more recently developed nonparametric test b...

Abstract Grouped data in the form of income shares have conventionally been used to estimate inequality due lack individual records. We present a systematic evaluation performance parametric distributions and non-parametric techniques economic using more than 3300 sets. also provide guidance on choice between these two approaches their estimation, for which we develop GB2group R package. Our re...