R markdown (R) and Jupyter (python) notebooks detailing regression functionality grouped by functions. The functionality demonstrated in each language is in the following files:
- 1_SLR_SumSqs_R_fkingfisher.* : simple linear regression model example with automatic and manual calculations for sums of squares (total, error, regression/response) and coefficient of determination (R2)
- 2_SLR_Significance_Confidence_fkingfisher.* : simple linear regression model example with automatic and manual calculations to test model signficance (t and F test), a slope coefficient hypothesis test (t test), confidence and prediction intervals at a specific predictor variable value, and plots of prediction and interval ranges on a scatter plot.
- 3_SLR_Adequecy_Residuals_fkingfisher.* : simple linear regression model example that tests model adequecy by examining the normality and variance of residuals
- 4_SLR_Adequecy_PowerTransform_fkingfisher.* : simple linear regression model example that demonstrates how to generate a model with greater adequecy for analysis using the Box-Cox power transformation.
- 5_MLR_Determination_Confidence_fkingfisher.* : multiple linear regression model example that demonstrates how to generate interaction terms, test model adequacy, evaluate the contribution of each regressor, calculate coefficient of determination (R2), calculate adjusted CoD (Adjusted R2), and coefficient confidence intervals.