Final answer:
The RMSE is assessed by comparing model performance on training and test data, and by identifying and potentially removing outliers to improve model accuracy and fit.
Step-by-step explanation:
Assessing the RMSE (Root Mean Square Error) involves comparing the model's performance on the training data against the test data set. Outliers can be identified using a scatter plot by looking for data points that are more than two standard deviations from the best-fit line. Alternatively, conduct a numerical assessment by calculating each residual and comparing it to twice the standard deviation. In either case, adjusting for outliers by removing them can lead to a better model fit, indicated by a lower SSE and a closer correlation coefficient r-value to 1. Excel can be used for graphing regression lines and comparing slopes, providing a visual and numerical way to assess these changes.