We consider the problem of testing a statistical hypothesis where the scientifically meaningful test statistic is a function of latent variables. In particular , we consider detection of genetic linkage, where the latent variables are patterns of inheritance at specific genome locations. Fuzzy p-values, introduced by Geyer & Meeden (2005) are random variables (described by their probability dis...

Latent factor model is one common technique to build recommendation systems. Standard latent factor model however does not take into account the order in which each individual user makes the ratings. Modeling the shift in user behaviour over time will not only allow making better recommendations to users, but also discover their hidden categories, “level of experiences” or “progression stages”....

For manifest variables with additive noise and for a given number of latent variables with an assumed distribution, we propose to nonparametrically estimate the association between latent and manifest variables. Our estimation is a two step procedure: first it employs standard factor analysis to estimate the latent variables as theoretical quantiles of the assumed distribution; second, it emplo...

Assume that cause-effect relationships between variables can be described as a directed acyclic graph and the corresponding linear structural equation model.We consider the identification problem of total effects in the presence of latent variables and selection bias between a treatment variable and a response variable. Pearl and his colleagues provided the back door criterion, the front door c...

Latent variable models are used to estimate variables of interest – quantities which are observable only up to some measurement error. In many studies, such variables are known but not precisely quantifiable (such as “job satisfaction” in social sciences and marketing, “analytical ability” in educational testing, or “inflation” in economics). This leads to the development of measurement instrum...

Peoples' subjective feelings of confidence typically correlate positively with objective measures of task performance, even when no performance feedback is provided. This relationship has seldom been investigated in the field of human time perception. Here we find a positive relationship between the precision of human timing perception and decisional confidence. We first demonstrate that subjec...

Probabilistic models with latent variables are powerful tools that can help explain related phenomena by mediating dependencies among them. Learning in the presence of latent variables can be difficult though, because of the difficulty of marginalizing them out, or, more commonly, maximizing a lower bound on the marginal likelihood. In this work, we show how to learn hinge-loss Markov random fi...

X. Bry Laboratoire LISE-CEREMADE, Université de Paris IX Dauphine Email : [email protected] Abstract : Given R groups of numerical variables X1, ... XR, we assume that each group is the result of one underlying latent variable, and that all latent variables are bound together through a linear equation system. Moreover, we assume that some explanatory latent variables may interact pairwise in o...

OBJECTIVES We aimed to ascertain the relationship between several factors and successful return to work using a structural equation model. METHODS We used original data from the Panel Study of Worker's Compensation Insurance, and defined four latent variables as occupational, individual, supportive, and successful return to work. Each latent variable was defined by its observed variables, inc...

A Bayesian inference framework for supervised Gaussian process latent variable models is introduced. The overcomes the high correlations between variables and hyperparameters by collapsing statistical model through approximate integration of variables. Using an unbiased pseudo estimate marginal likelihood, exact hyperparameter posterior can then be explored using collapsed Gibbs sampling and, c...