1. Know the methods of adding a third variable to a 2D scatter plot, whether categorical or numeric.
2. When faced with a 'compressed' plot, know how to expand the visible information.
3. Be able to interpret a missing value bar chart (what it shows and what it doesn't show).
4. Be able to interpret a missing value bar chart (what it shows and what it doesn't show).
5. Be able to interpret and apply categorical variable encoding for linear regression.
6. Know the strengths of Python libraries regarding exploratory vs. predictive models.
7. Know how to interpret a linear regression explanatory model summary output with categorical variables.
8. Understand how ridge regression or the lasso can affect the bias-variance tradeoff.
9. Understand the Python code RidgeCV and LassoCV and how they create models for selecting the best value of lambda (you may want to consult Sci-Kit Learn API documentation: https://scikitlearn.org/stable/modules/generated/sklearn.linear_model.LassoCV.html?highlight=lassocv#sklearn.linear_model.LassoCV ; https://scikitlearn.org/stable/modules/generated/sklearn.linear_model.RidgeCV.html?highlight=ridgecv#sklearn.linear_model.RidgeCV )
10. Be able to interpret PCA components from a scatter plot.
11. Know how PCA can be used for tasks other than as a data processing stage for additional machine learning models.
12. Know the conditions under which PCA will perform well or poorly, both in terms of the data and the eigenvalue decomposition.
13. Understand how to interpret a box plot, line graph, scatter plot, and histogram regarding distributions, relationships, and extreme values.
14. Understand the different relationships that can be interpreted from a scatter plot (i.e., correlation, linearity, heteroscedasticity, and extreme values)
15. Understand model selection criteria, namely Adjusted R-squared, AIC, and BIC.
16. Know the difference between the minimum number of samples required for fitting a model vs. the number of samples required for testing the fitted model.
17. Understand the advantages and disadvantages of 10-fold cross validation vs. LOOCV.
18. Know how to visually interpret overfitting and underfitting from an error plot.
19. Be able to recognize the equations that describe different cross validation schemes.
20. Understand the relationship between PCA components and the bias-variance tradeoff.
21. Understand the linear relationship between the components in a PCA model.
22. Know the data preprocessing that may be required before building a PCA model.
23. Be able to interpret proportion of variance and cumulative variance from a table.

Answer however many possible. If there is not time to do every question, I am ok with some questions being answered. thanks!