Melanoma is one of the most severe forms of skin cancer and can be life-threatening due to metastasis if not caught early on in its development. Over the past decade, the U.S. Government added a Healthy People 2020 objective to reduce the melanoma skin cancer rate in the U.S. population. Now that the decade has come to a close, this research investigates possible large-scale risk factors that could lead to incidence of melanoma in the population using logistic regression and propensity score matching. Logistic regression results showed that Caucasians are 14.765 times more likely to get melanoma compared to non-Caucasians; however, after adjustment using propensity scoring, this value was adjusted to 11.605 times more likely for Caucasians than non-Caucasians. Cholesterol, Chronic Obstructive Pulmonary Disease, and Hypertension predictors also showed significance in the initial logistic regression. By using the results found in this experiment, the door has been opened for further analysis of larger-scale predictors and gives public health programs the initial information needed to create successful skin safety advocacy plans.
We attempted to apply a novel approach to stock market predictions. The Logistic Regression machine learning algorithm (Joseph Berkson) was applied to analyze news article headlines as represented by a bag-of-words (tri-gram and single-gram) representation in an attempt to predict the trends of stock prices based on the Dow Jones Industrial Average. The results showed that a tri-gram bag led to a 49% trend accuracy, a 1% increase when compared to the single-gram representation’s accuracy of 48%.
sports, banking, and other disciplines. We use predictive analytics and modeling to
determine the impact of certain factors that increase the probability of a successful
fourth down conversion in the Power 5 conferences. The logistic regression models
predict the likelihood of going for fourth down with a 64% or more probability based on
2015-17 data obtained from ESPN’s college football API. Offense type though important
but non-measurable was incorporated as a random effect. We found that distance to go,
play type, field position, and week of the season were key leading covariates in
predictability. On average, our model performed as much as 14% better than coaches
in 2018.