This project investigates the effects of NGN2 viral dose and NT3 treatment on neuronal differentiation efficiency in vitro. Differentiation outcomes were quantified as the proportion of MAP2-positive cells per well, derived from approximately 10,000 cells per condition. To formally assess treatment effects while accounting for the proportional nature of the data and multiple experimental conditions, a binomial generalized linear model (logistic regression) was applied. The analysis identified a clear dose-dependent effect of NGN2, with 5 MOI producing the strongest and most consistent differentiation outcome, and a smaller but significant positive contribution from NT3 treatment. Outlier detection and removal confirmed the robustness of these findings and supported an optimized differentiation protocol.

A logistic regression analysis examining associations between cardiovascular disease and modifiable health and lifestyle factors (physical activity, smoking history, body weight) using 2024 BRFSS survey data. The project emphasizes model comparison, diagnostics, and interpretation through predicted probabilities and visualizations.

This presentation describes a Shiny application that predicts the next word in a phrase using an N-gram language model.

Creditors invest significant efforts in creating algorithms to predict the likelihood of a customer defaulting on a loan (PD). Defaults can result in substantial financial losses, impacting both the profitability and stability of financial institutions. To mitigate these risk, it is essential to develop robust predictive models that help to identify potential defaulters before credit is granted. Our aim here is to develop such models.

This report presents a brief exploratory analysis of the SwiftKey text data, including blogs, news, and Twitter sources. It summarizes basic statistics and outlines plans for building a next-word prediction model.

Mapa que muestra una propuesta de zonas que deberían ser arboladas para ayudar en la regulación de temperatura de la Ciudad de México. El mapa fue elaborado tomando en cuenta solo dos variables: temperatura del suelo proveniente del sensor Landsat y el ndvi calculado a partir de imágenes Landsat. Además, se usó el inventario de parques y áreas verdes para excluir las zonas que ya cuentan con vegetación en la ciudad. El mapa solo es una aproximación.