Explore chapters and articles related to this topic
Complex Innovative Design
Published in Wei Zhang, Fangrong Yan, Feng Chen, Shein-Chung Chow, Advanced Statistics in Regulatory Critical Clinical Initiatives, 2022
The joint distribution is modeled as a mixture of the conditional distribution of weighted by the marginal distribution of . Here we assume that Z always is observed before Y.
Computation
Published in Andrew B. Lawson, Using R for Bayesian Spatial and Spatio-Temporal Health Modeling, 2021
where the are a sample from the marginal distribution
STATISTICS OF CASE-CONTROL STUDIES
Published in Richard G. Cornell, Statistical Methods for Cancer Studies, 2020
Norman E. Breslow, Nicholas E. Day
Estimation of £ from the full likelihood is then a byproduct of normal theory discriminant analysis. However if the assumption of multivariate normality does not hold, severe bias can result from this approach, and it is consequently not recommended (Halperin, Blackwelder and Verter, 1971; Efron, 1975; Press and Wilson, 1978). A more prudent course is to allow the marginal distribution pr(x) to remain completely arbitrary. Quite remarkably, it follows that the joint estimation by maximum likelihood of pr(x) and £ from (9) yields estimates and asymptotic standard errors for £ which are identical to those based on the disease probability model (7) (Anderson, 1972; Prentice and Pyke, 1979). This result justifies fully the basic principle that one applies the same inferential techniques to case-control data as would be applied to forward data from the same population.
Statistical inference for distributions with one Poisson conditional
Published in Journal of Applied Statistics, 2021
Barry C. Arnold, B. G. Manjunath
By considering bivariate models in which one marginal distribution is assumed to be of the Poisson form while the conditional distributions of the second variable, given the first, are also assumed to be of the Poisson form, we have developed flexible models called bivariate pseudo-Poisson distributions. Distributional and inferential issues have been investigated for these models. The models discussed in this paper may be considered as viable alternatives to the various bivariate Poisson models that have been introduced in the literature. The simplicity of the structure of the pseudo models allows simple simulation and straightforward parameter estimation and model fitting. They are not a panacea but we would argue that they, and their extensions to higher dimensions and permuted variants of them, deserve a place in the modelers toolkit.
Parameter estimation of Cambanis-type bivariate uniform distribution with Ranked Set Sampling
Published in Journal of Applied Statistics, 2021
Rohan D. Koshti, Kirtee K. Kamalja
In modeling the bivariate data, when the prior information is in the form of marginal distribution, it is of advantage to consider families of bivariate distributions with specified marginals. Morgenstern [20] provides a flexible family in such a context. One important limitation of the Morgenstern family is that its correlation coefficient is restricted to a narrow range 3,4,6,14,15,30] proposed extensions to the Morgenstern family to enhance the range of correlation between variables and to get a more flexible family. Cambanis [6] introduces a family of distributions that constitutes a natural generalization of the multivariate Morgenstern family and enhances the correlation among variables. With this motivation, we consider the Cambanis family that covers a higher correlation among variables and a higher dimension of association parameter space than the Morgenstern family.
Joint models for mixed categorical outcomes: a study of HIV risk perception and disease status in Mozambique
Published in Journal of Applied Statistics, 2018
Osvaldo Loquiha, Niel Hens, Emilia Martins-Fonteyn, Herman Meulemans, Edwin Wouters, Marleen Temmerman, Nafissa Osman, Marc Aerts
The above defined odds for π for ij subscripts). For the marginal distribution of