Analysis of Diabetes and Oxygen Saturation Data (Blood Pressure)
- Identified key factors for diabetes (Glucose, BMI, Age) through correlation analysis and linear regression.
- Built a logistic regression model to predict diabetes with these factors.
- Evaluated model performance using cross-validation and explored alternative models (KNN).
- Explored the oxygen saturation data distribution.
- Estimated data spread (total deviance) and bias using bootstrap methods.
- Compared methods for estimating a data property (potentially variance) and found agreement.
- psych
- dplyr
- ggplot2
- ggcorrplot
- MASS
- pROC
- caret
- e1071
- janitor
- boot
- Correlation analysis
- Linear regression
- Logistic regression
- Cross-validation
- KNN
- Bootstrap analysis