A Simple Monte Carlo Framework to Assess Suicide Risk in Adolescents: A Study at a High School in Colombia.

It is very common to perform statistical tests to obtain insights about populations based on samples. For instance, in the context of psychology, when a set of instruments are applied to individuals, psychologists typically look for an explanation of particular psychological constructs (variables), such as personality, intelligence, or emotional functioning. It is common to cross statistical information from the results of different psychological tests to measure certain variables or to confirm prior beliefs. Here, we estimate the Joint Probability Density Function of suicide-related vulnerability and protective factors to assess suicide risk in adolescents. A Markov Chain Monte Carlo Method is employed to move away from the typical Gaussian assumption on data. This allows us to estimate probabilities of the development of suicidal ideation based on samples (which form a Markov chain). We employ our proposed statistical method at a high school in Colombia. The results reveal that adolescents can develop suicidal ideation as a consequence of the following factors, together with their corresponding probabilities: poor school performance 52%, low academic expectations 27%, school integration problems 68%, risky eating behaviors (binge-purge) 42%, risky eating behaviors (compensatory measurements) 21%, risky eating habits (restriction) 22%, and low family functionality 16%.

A Maximum Likelihood Ensemble Filter Via A Modified Cholesky Decomposition For Non-Gaussian Data Assimilation.

This paper proposes an efficient and practical implementation of the Maximum Likelihood Ensemble Filter via a Modified Cholesky decomposition (MLEF-MC). The method works as follows: via an ensemble of model realizations, a well-conditioned and full-rank square-root approximation of the background error covariance matrix is obtained. This square-root approximation serves as a control space onto which analysis increments can be computed. These are calculated via Line-Search (LS) optimization. We theoretically prove the convergence of the MLEF-MC. Experimental simulations were performed using an Atmospheric General Circulation Model (AT-GCM) and a highly nonlinear observation operator. The results reveal that the proposed method can obtain posterior error estimates within reasonable accuracies in terms of ℓ - 2 error norms. Furthermore, our analysis estimates are similar to those of the MLEF with large ensemble sizes and full observational networks.