The random forest algorithm is a popular non-parametric alternative to more parametric approaches when building risk prediction models. In short, the algorithm averages predictions from …
Background: Prognostic prediction has empirically proven to be a highly effective paradigm that is radically reshaping public health, clinical medicine, and healthcare as a domain. …
The objective of this dissertation is to develop methods for statistical record linkage that are more robust when identifying information is limited or recorded with …
We conducted a secondary data analysis of PECARN (The Pediatric Emergency Care Applied Research Network) traumatic brain injury in children dataset. To keep more information …
Correlation analysis between time series from two regions of interest is popular in the functional magnetic resonance imaging (fMRI) studies. The most widely used approach …
Medical imaging is now a critical tool for identifying and monitoring diseases, which greatly improves the public health for all population. A number of statistical …
Conditional cash transfer (CCT) programs have become important constituents of social protection policy in Latin America. By establishing co-responsibilities tied to health and education, CCTs …
Background: MicroSimulation Models (MSMs) have been used to estimate population-level effects of treatment on disease outcomes and to assess the comparative effectiveness of interventions. Since …
