A comparison of stepwise and lasso regression as well as elastic net using a sample dataset on per capita crime. In addition, the use of principal components to select features is explored using the same dataset and regression methods.

Using the Wisconsin breast cancer data set, explore different methods to impute missing data values.

Determine instances of potential fraud using several predictors.

Data derived from http://unstats.un.org/unsd/demographic/default.htm

Produced with leaflet.

Exploration of developing a multiple linear regression model for predicting the audience score of movies.

Exploratory data analysis and development of a predictive model based on sensor data gathered during a weightlifting exercise done correctly or incorrectly.

A (very) short analysis of self-reported body mass index (BMI) by age, race, and employment status and its association with the mean number of unhealthy (physical or mental) days as reported by the study participant.

Limited analysis of the data in the US NOAA database. This database tracks characteristics of major storms and weather events in the US, including when and where they occur, as well as estimates of any fatalities, injuries, an property damage. Here, an analysis of the top ten events in terms of fatalities, injuries. property damage, and crop damage are presented. Data were aggregated by event type from 1950 onwards.